{"id":"307b39ee-3201-4feb-ab91-ab76df1a1ef8","entityType":"agent","slug":"clawhub-mirajmahmudul-agentdevx-skill","name":"Agentdevx Skill","canonicalUrl":"https://www.xpersona.co/agent/clawhub-mirajmahmudul-agentdevx-skill","canonicalPath":"/agent/clawhub-mirajmahmudul-agentdevx-skill","generatedAt":"2026-10-13T06:52:16.728Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T22:13:47.462Z","emptyReason":null},"description":"Give your AI hands. The identity and security layer every AI agent needs — register any API, agents get Ed25519 identity, encrypted vault, and audit logging. Skill: Agentdevx Skill Owner: mirajmahmudul Summary: Give your AI hands. The identity and security layer every AI agent needs — register any API, agents get Ed25519 identity, encrypted vault, and audit logging. Tags: latest:1.1.0 Version history: v1.1.0 | 2026-08-15T18:22:13.635Z | auto - Added documentation for built-in native MCP tools (memory.store, memory.recall, webscrape.scrape, webscrape.extractDesign) - Expan","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 986 downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s177y8zpbgpc2r0nts3gt2ap0188kkpg:agentdevx-skill","sourceUrl":"https://clawhub.ai/mirajmahmudul/agentdevx-skill","homepage":"https://clawhub.ai/mirajmahmudul/skills/agentdevx-skill","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/mirajmahmudul/agentdevx-skill","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/mirajmahmudul/skills/agentdevx-skill","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Give your AI hands. The identity and security layer every AI agent needs — register any API, agents get Ed25519 identity, encrypted vault, and audit logging. Sk"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T22:13:47.462Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T22:13:47.462Z","emptyReason":null},"stars":null,"forks":null,"downloads":986,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"1.1.0","tractionLabel":"986 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T22:13:47.410Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T22:13:47.462Z","lastCrawledAt":"2026-10-11T22:13:47.410Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T22:13:47.410Z","lastVerifiedAt":null,"highlights":[{"version":"1.1.0","createdAt":"2026-08-15T18:22:13.635Z","changelog":"- Added documentation for built-in native MCP tools (`memory.store`, `memory.recall`, `webscrape.scrape`, `webscrape.extractDesign`) - Expanded skill description to clarify the availability of native tools beyond API registry - Removed skill-card.md file - Updated version to 1.1.0","fileCount":3,"zipByteSize":4119},{"version":"1.0.9","createdAt":"2026-06-25T08:11:14.078Z","changelog":"- Updated SKILL.md to clarify support for registering any API via OpenAPI spec, not just pre-built tools. - Adjusted tool list description to emphasize agent access to any registered API (with 7 included examples). - Improved documentation on registering custom APIs, expanding beyond the fixed pre-loaded set. - Refined language for transparency and setup flow; no functional code changes.","fileCount":3,"zipByteSize":3927},{"version":"1.0.8","createdAt":"2026-06-25T07:15:49.441Z","changelog":"- Updated skill description in SKILL.md to better highlight API registration and automation features. - Removed the file skill-card.md. - No changes to functionality or version number in SKILL.md. - Project documentation streamlined for clarity; all details remain in SKILL.md.","fileCount":3,"zipByteSize":3893},{"version":"1.0.7","createdAt":"2026-06-24T08:52:12.590Z","changelog":"- Updated SKILL.md to clarify revocation instructions (now directs users to dashboard for account deletion). - Removed the \"curl\" binary requirement from metadata. - Deleted the deprecated skill-card.md file.","fileCount":3,"zipByteSize":3836},{"version":"1.0.6","createdAt":"2026-06-24T07:01:36.757Z","changelog":"- Updated documentation (SKILL.md) with improved descriptions, feature tables, and clearer setup instructions. - Expanded overview of agent bootstrap flow, security, and capabilities. - Added feature comparisons with similar platforms. - Clarified available tools and included an MCP integration example. - Removed outdated skill-card.md file.","fileCount":3,"zipByteSize":3889},{"version":"1.0.5","createdAt":"2026-06-17T11:53:14.819Z","changelog":"**Expanded transparency and setup details for agent self-registration.** - Updated SKILL.md to provide step-by-step transparency on what happens during first agent use, including Ed25519 identity creation and automatic registration with AgentDevX. - Clarified outbound network behavior, account creation, and credential storage. - Added bash examples for bootstrap, tool discovery, proxy calls, secure credential storage, and agent memory. - Expanded documentation of available tools, pricing, and security notes. - Updated environment variable descriptions for clarity. - Removed the outdated skill-card.md file.","fileCount":3,"zipByteSize":3961},{"version":"1.0.3","createdAt":"2026-06-16T23:06:27.538Z","changelog":"- Skill renamed to agentdevx-skill and updated for automatic, no-config setup. - Manual setup and explicit environment variable configuration are no longer required; the skill now auto-bootstraps on first use. - Simplified documentation and installation instructions. - Expanded description of capabilities and available tools. - Removed the skill-card.md file for easier maintenance.","fileCount":3,"zipByteSize":2891},{"version":"1.0.2","createdAt":"2026-06-15T08:50:50.450Z","changelog":"- Added a Security & Trust section to SKILL.md, clearly detailing trust boundaries, data handling, and encryption specifics. - Removed the file skill-card.md.","fileCount":3,"zipByteSize":3059}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s177y8zpbgpc2r0nts3gt2ap0188kkpg:agentdevx-skill","setupComplexity":"low","setupSteps":["Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-mirajmahmudul-agentdevx-skill/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-mirajmahmudul-agentdevx-skill/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-mirajmahmudul-agentdevx-skill/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-mirajmahmudul-agentdevx-skill/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-mirajmahmudul-agentdevx-skill/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-mirajmahmudul-agentdevx-skill/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-13T06:52:16.727Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-mirajmahmudul-agentdevx-skill/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-mirajmahmudul-agentdevx-skill/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-mirajmahmudul-agentdevx-skill/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-mirajmahmudul-agentdevx-skill/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-11T22:13:47.462Z","emptyReason":null},"readme":"Skill: Agentdevx Skill\n\nOwner: mirajmahmudul\n\nSummary: Give your AI hands. The identity and security layer every AI agent needs — register any API, agents get Ed25519 identity, encrypted vault, and audit logging.\n\nTags: latest:1.1.0\n\nVersion history:\n\nv1.1.0 | 2026-08-15T18:22:13.635Z | auto\n\n- Added documentation for built-in native MCP tools (`memory.store`, `memory.recall`, `webscrape.scrape`, `webscrape.extractDesign`)\n- Expanded skill description to clarify the availability of native tools beyond API registry\n- Removed skill-card.md file\n- Updated version to 1.1.0\n\nv1.0.9 | 2026-06-25T08:11:14.078Z | auto\n\n- Updated SKILL.md to clarify support for registering any API via OpenAPI spec, not just pre-built tools.\n- Adjusted tool list description to emphasize agent access to any registered API (with 7 included examples).\n- Improved documentation on registering custom APIs, expanding beyond the fixed pre-loaded set.\n- Refined language for transparency and setup flow; no functional code changes.\n\nv1.0.8 | 2026-06-25T07:15:49.441Z | auto\n\n- Updated skill description in SKILL.md to better highlight API registration and automation features.\n- Removed the file skill-card.md.\n- No changes to functionality or version number in SKILL.md.\n- Project documentation streamlined for clarity; all details remain in SKILL.md.\n\nv1.0.7 | 2026-06-24T08:52:12.590Z | auto\n\n- Updated SKILL.md to clarify revocation instructions (now directs users to dashboard for account deletion).\n- Removed the \"curl\" binary requirement from metadata.\n- Deleted the deprecated skill-card.md file.\n\nv1.0.6 | 2026-06-24T07:01:36.757Z | auto\n\n- Updated documentation (SKILL.md) with improved descriptions, feature tables, and clearer setup instructions.\n- Expanded overview of agent bootstrap flow, security, and capabilities.\n- Added feature comparisons with similar platforms.\n- Clarified available tools and included an MCP integration example.\n- Removed outdated skill-card.md file.\n\nv1.0.5 | 2026-06-17T11:53:14.819Z | auto\n\n**Expanded transparency and setup details for agent self-registration.**\n\n- Updated SKILL.md to provide step-by-step transparency on what happens during first agent use, including Ed25519 identity creation and automatic registration with AgentDevX.\n- Clarified outbound network behavior, account creation, and credential storage.\n- Added bash examples for bootstrap, tool discovery, proxy calls, secure credential storage, and agent memory.\n- Expanded documentation of available tools, pricing, and security notes.\n- Updated environment variable descriptions for clarity.\n- Removed the outdated skill-card.md file.\n\nv1.0.3 | 2026-06-16T23:06:27.538Z | auto\n\n- Skill renamed to agentdevx-skill and updated for automatic, no-config setup.\n- Manual setup and explicit environment variable configuration are no longer required; the skill now auto-bootstraps on first use.\n- Simplified documentation and installation instructions.\n- Expanded description of capabilities and available tools.\n- Removed the skill-card.md file for easier maintenance.\n\nv1.0.2 | 2026-06-15T08:50:50.450Z | auto\n\n- Added a Security & Trust section to SKILL.md, clearly detailing trust boundaries, data handling, and encryption specifics.\n- Removed the file skill-card.md.\n\nv1.0.1 | 2026-06-15T07:48:25.733Z | auto\n\n- Expanded support: Now connect with 50+ APIs (previously 40+).\n- Added live usage stats, security audit results, and ClawHub install count to documentation.\n- Updated available tools list with new integrations (petstore-api, acme-mailer).\n- Clarified that Free tier requires no credit card.\n- Documentation improvements and reorganization for better clarity.\n- Removed deprecated skill-card.md file.\n\nv1.0.0 | 2026-06-13T19:30:52.384Z | auto\n\n- Initial release of agentdevx-gateway.\n- Securely call 40+ APIs (GitHub, Stripe, SendGrid, etc.) with one agent identity.\n- Features encrypted credential vault and full audit log.\n- Supports tool discovery, secret storage, and agent memory.\n- Real-time event streaming and MCP server connection.\n- Free and paid pricing tiers available.\n\nArchive index:\n\nArchive v1.1.0: 3 files, 4119 bytes\n\nFiles: skill-card.md (2255b), SKILL.md (5683b), _meta.json (134b)\n\nFile v1.1.0:SKILL.md\n\n---\nname: agentdevx-skill\ndescription: \"Give your AI hands. Register any API via OpenAPI spec — agents get Ed25519 identity, encrypted credential injection, rate limiting, and audit logging automatically. One bootstrap call, zero human setup.\"\nversion: 1.1.0\nmetadata:\n  openclaw:\n    requires: {}\n    homepage: https://agentdevx.onrender.com\n    primaryEnv: AGENTDEVX_API_KEY\n    envVars:\n      - name: AGENTDEVX_API_KEY\n        required: false\n        description: Auto-obtained on first tool call via self-bootstrap (POST /agents/v1/bootstrap). No human action needed.\n      - name: AGENTDEVX_BASE_URL\n        required: false\n        description: \"Default: https://agentdevx.onrender.com\"\n    tags:\n      - mcp\n      - api-gateway\n      - agent-identity\n      - developer-tools\n      - ai-infrastructure\n      - credential-vault\n      - tool-registry\n    category: data-and-apis\n    homepage: https://agentdevx.onrender.com\n---\n\n# AgentDevX Gateway\n\nThe first infrastructure layer an AI agent can discover, install, and use entirely on its own — no human OAuth, no manual key exchange, no setup.\n\nEvery developer building an AI agent hits the same wall: auth spaghetti, credential sprawl, API integration hell, no stable agent identity, no persistent memory. AgentDevX solves all of this in one gateway.\n\n## Transparency — What Happens On First Use\n\nThis skill connects to **AgentDevX**, a third-party hosted gateway. On first tool call, your agent automatically:\n\n1. **Generates an Ed25519 keypair locally** — private key never leaves your machine\n2. **Registers with AgentDevX** (`POST /agents/v1/bootstrap`) — outbound network call to `https://agentdevx.onrender.com`\n3. **Receives a JWT + 75,000 free credits** — account created automatically\n4. **Gains proxy access to any registered API** — pre-built examples include weather, GitHub, exchange rates, and more. Register your own via OpenAPI spec.\n\nThis is intentional self-provisioning, not a bug. If you do not want your agent registering with a third-party service, do not invoke this skill's tools.\n\nTo revoke access, visit your dashboard at https://agentdevx.onrender.com and delete your account.\n\n## Install\n\n```bash\nopenclaw skills install agentdevx-skill\n```\n\n## What Your Agent Can Do\n\nAfter install, your agent has:\n\n- **Cryptographic identity** — Ed25519, not OAuth. One identity across all tools.\n- **Encrypted credential vault** — AES-256-GCM. Store API keys securely, auto-injected on every call.\n- **Access to any registered API** — 7 pre-built examples included. Register any API via OpenAPI spec and agents can use it instantly.\n- **Per-agent memory** — encrypted state that persists across sessions.\n- **Policy engine** — OPA/Rego access control. Dry-run mode. Full audit log.\n\n## Autonomous Bootstrap Flow\n\nYour agent runs this automatically — no human action needed:\n\n```bash\nPUBLIC_KEY=$(openssl rand -hex 32)\nBOOTSTRAP=$(curl -s -X POST https://agentdevx.onrender.com/agents/v1/bootstrap \\\n  -H \"Content-Type: application/json\" \\\n  -d \"{\\\"name\\\":\\\"openclaw-agent\\\",\\\"email\\\":\\\"agent@local\\\",\\\"public_key\\\":\\\"$PUBLIC_KEY\\\"}\")\nexport AGENTDEVX_API_KEY=$(echo \"$BOOTSTRAP\" | grep -o '\"access_token\":\"[^\"]*\"' | cut -d'\"' -f4)\n```\n\n## MCP Config (Claude Desktop / Cursor / Windsurf / any MCP client)\n\n```json\n{\n  \"mcpServers\": {\n    \"agentdevx\": {\n      \"url\": \"https://agentdevx.onrender.com/mcp\"\n    }\n  }\n}\n```\n\n## Register Any API — Pre-built Examples Included\n\nAgentDevX is not a fixed tool collection. Register any API via OpenAPI spec and it becomes instantly available to all agents with automatic credential injection, rate limiting, and audit logging.\n\nPre-registered examples:\n\n| Tool | What It Does |\n|------|-------------|\n| open-weather | Live weather & forecasts |\n| github-api | Repos, issues, PRs |\n| exchange-rate | Live currency conversion |\n| public-holidays | Holidays by country |\n| acme-mailer | Send emails |\n| jsonplaceholder | REST API testing |\n| petstore-api | OpenAPI 3.0 demo |\n\nThese are examples. POST any OpenAPI spec to register your own API — every agent on the network can use it instantly.\n\n## Native Built-in Tools\n\nBeyond the API registry, AgentDevX ships native MCP tools that don't require registration:\n\n| Tool | What It Does |\n|------|-------------|\n| memory.store | Save a key-value pair to persistent, encrypted agent memory |\n| memory.recall | Retrieve a stored value by key |\n| webscrape.scrape | Extract page title, headings, links, images, text (static HTML) |\n| webscrape.extractDesign | Extract colors, fonts, spacing, layout patterns (static HTML)\n\n## Why AgentDevX vs Composio / Nango / Auth0\n\n| Feature | AgentDevX | Composio/Nango | Auth0 |\n|---------|-----------|----------------|-------|\n| AI self-bootstrap | ✅ Yes | ❌ No | ❌ No |\n| Ed25519 identity | ✅ Yes | ❌ OAuth only | ❌ OAuth only |\n| Encrypted vault | ✅ AES-256-GCM | ✅ OAuth-based | ✅ Enterprise |\n| Per-agent memory | ✅ Yes | ❌ No | ❌ No |\n| MCP native | ✅ Yes | ❌ No | ❌ No |\n| Indie pricing | ✅ Free tier | ❌ Enterprise | ❌ Enterprise |\n\n## Security & Revocation\n\n> ⚠️ **Trust Boundary:** AgentDevX is a third-party hosted gateway. API calls, credentials, and memory contents route through AgentDevX servers. All credentials encrypted at rest with AES-256-GCM. All traffic encrypted via TLS. Full audit log of every action, viewable via the AgentDevX dashboard.\n\n## Links\n\n- 🌐 Gateway: https://agentdevx.onrender.com\n- 📊 Smithery: https://smithery.ai/server/io.github.mirajmahmudul/agentdevx\n- 🔧 SDK: https://github.com/mirajmahmudul/agentdevx-sdk\n- 📦 npm: https://www.npmjs.com/package/@agentdevx/install\n\nFile v1.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn712kvpp6y572wcge6dgpem7h88kgfv\",\n  \"slug\": \"agentdevx-skill\",\n  \"version\": \"1.1.0\",\n  \"publishedAt\": 1786818133635\n}\n\nFile v1.1.0:skill-card.md\n\n## Description:\n\nAgentdevx Skill helps agents use AgentDevX to register APIs from OpenAPI specs and route calls through identity, credential vault, memory, rate limiting, and audit logging features.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[mirajmahmudul](https://clawhub.ai/user/mirajmahmudul)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and agent builders use this skill to connect agents to the AgentDevX gateway, configure MCP access, register APIs from OpenAPI specs, and use persistent memory or credential-backed API calls.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill uses a third-party hosted gateway for setup, API calls, credentials, and persistent memory.\n\nMitigation: Review the gateway trust boundary before installation and use only data or API keys you are willing to expose to AgentDevX.\n\nRisk: The skill can automatically create an AgentDevX account and route credentials through that service on first use.\n\nMitigation: Verify token scope, revocation, retention, and credential isolation outside the skill text before invoking its tools.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/mirajmahmudul/skills/agentdevx-skill)\n- [AgentDevX gateway](https://agentdevx.onrender.com)\n- [Smithery AgentDevX listing](https://smithery.ai/server/io.github.mirajmahmudul/agentdevx)\n- [AgentDevX SDK](https://github.com/mirajmahmudul/agentdevx-sdk)\n- [AgentDevX npm package](https://www.npmjs.com/package/@agentdevx/install)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown guidance with shell command examples and JSON MCP configuration snippets]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May describe outbound AgentDevX calls and environment variables such as AGENTDEVX_API_KEY.]\n\n## Skill Version(s):\n\n1.1.0 (source: frontmatter and server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.0.9: 3 files, 3927 bytes\n\nFiles: skill-card.md (2362b), SKILL.md (5210b), _meta.json (134b)\n\nFile v1.0.9:SKILL.md\n\n---\nname: agentdevx-skill\ndescription: \"Give your AI hands. Register any API via OpenAPI spec — agents get Ed25519 identity, encrypted credential injection, rate limiting, and audit logging automatically. One bootstrap call, zero human setup.\"\nversion: 1.0.6\nmetadata:\n  openclaw:\n    requires: {}\n    homepage: https://agentdevx.onrender.com\n    primaryEnv: AGENTDEVX_API_KEY\n    envVars:\n      - name: AGENTDEVX_API_KEY\n        required: false\n        description: Auto-obtained on first tool call via self-bootstrap (POST /agents/v1/bootstrap). No human action needed.\n      - name: AGENTDEVX_BASE_URL\n        required: false\n        description: \"Default: https://agentdevx.onrender.com\"\n    tags:\n      - mcp\n      - api-gateway\n      - agent-identity\n      - developer-tools\n      - ai-infrastructure\n      - credential-vault\n      - tool-registry\n    category: data-and-apis\n    homepage: https://agentdevx.onrender.com\n---\n\n# AgentDevX Gateway\n\nThe first infrastructure layer an AI agent can discover, install, and use entirely on its own — no human OAuth, no manual key exchange, no setup.\n\nEvery developer building an AI agent hits the same wall: auth spaghetti, credential sprawl, API integration hell, no stable agent identity, no persistent memory. AgentDevX solves all of this in one gateway.\n\n## Transparency — What Happens On First Use\n\nThis skill connects to **AgentDevX**, a third-party hosted gateway. On first tool call, your agent automatically:\n\n1. **Generates an Ed25519 keypair locally** — private key never leaves your machine\n2. **Registers with AgentDevX** (`POST /agents/v1/bootstrap`) — outbound network call to `https://agentdevx.onrender.com`\n3. **Receives a JWT + 75,000 free credits** — account created automatically\n4. **Gains proxy access to any registered API** — pre-built examples include weather, GitHub, exchange rates, and more. Register your own via OpenAPI spec.\n\nThis is intentional self-provisioning, not a bug. If you do not want your agent registering with a third-party service, do not invoke this skill's tools.\n\nTo revoke access, visit your dashboard at https://agentdevx.onrender.com and delete your account.\n\n## Install\n\n```bash\nopenclaw skills install agentdevx-skill\n```\n\n## What Your Agent Can Do\n\nAfter install, your agent has:\n\n- **Cryptographic identity** — Ed25519, not OAuth. One identity across all tools.\n- **Encrypted credential vault** — AES-256-GCM. Store API keys securely, auto-injected on every call.\n- **Access to any registered API** — 7 pre-built examples included. Register any API via OpenAPI spec and agents can use it instantly.\n- **Per-agent memory** — encrypted state that persists across sessions.\n- **Policy engine** — OPA/Rego access control. Dry-run mode. Full audit log.\n\n## Autonomous Bootstrap Flow\n\nYour agent runs this automatically — no human action needed:\n\n```bash\nPUBLIC_KEY=$(openssl rand -hex 32)\nBOOTSTRAP=$(curl -s -X POST https://agentdevx.onrender.com/agents/v1/bootstrap \\\n  -H \"Content-Type: application/json\" \\\n  -d \"{\\\"name\\\":\\\"openclaw-agent\\\",\\\"email\\\":\\\"agent@local\\\",\\\"public_key\\\":\\\"$PUBLIC_KEY\\\"}\")\nexport AGENTDEVX_API_KEY=$(echo \"$BOOTSTRAP\" | grep -o '\"access_token\":\"[^\"]*\"' | cut -d'\"' -f4)\n```\n\n## MCP Config (Claude Desktop / Cursor / Windsurf / any MCP client)\n\n```json\n{\n  \"mcpServers\": {\n    \"agentdevx\": {\n      \"url\": \"https://agentdevx.onrender.com/mcp\"\n    }\n  }\n}\n```\n\n## Register Any API — Pre-built Examples Included\n\nAgentDevX is not a fixed tool collection. Register any API via OpenAPI spec and it becomes instantly available to all agents with automatic credential injection, rate limiting, and audit logging.\n\nPre-registered examples:\n\n| Tool | What It Does |\n|------|-------------|\n| open-weather | Live weather & forecasts |\n| github-api | Repos, issues, PRs |\n| exchange-rate | Live currency conversion |\n| public-holidays | Holidays by country |\n| acme-mailer | Send emails |\n| jsonplaceholder | REST API testing |\n| petstore-api | OpenAPI 3.0 demo |\n\nThese are examples. POST any OpenAPI spec to register your own API — every agent on the network can use it instantly.\n\n## Why AgentDevX vs Composio / Nango / Auth0\n\n| Feature | AgentDevX | Composio/Nango | Auth0 |\n|---------|-----------|----------------|-------|\n| AI self-bootstrap | ✅ Yes | ❌ No | ❌ No |\n| Ed25519 identity | ✅ Yes | ❌ OAuth only | ❌ OAuth only |\n| Encrypted vault | ✅ AES-256-GCM | ✅ OAuth-based | ✅ Enterprise |\n| Per-agent memory | ✅ Yes | ❌ No | ❌ No |\n| MCP native | ✅ Yes | ❌ No | ❌ No |\n| Indie pricing | ✅ Free tier | ❌ Enterprise | ❌ Enterprise |\n\n## Security & Revocation\n\n> ⚠️ **Trust Boundary:** AgentDevX is a third-party hosted gateway. API calls, credentials, and memory contents route through AgentDevX servers. All credentials encrypted at rest with AES-256-GCM. All traffic encrypted via TLS. Full audit log of every action, viewable via the AgentDevX dashboard.\n\n## Links\n\n- 🌐 Gateway: https://agentdevx.onrender.com\n- 📊 Smithery: https://smithery.ai/server/io.github.mirajmahmudul/agentdevx\n- 🔧 SDK: https://github.com/mirajmahmudul/agentdevx-sdk\n- 📦 npm: https://www.npmjs.com/package/@agentdevx/install\n\nFile v1.0.9:_meta.json\n\n{\n  \"ownerId\": \"kn712kvpp6y572wcge6dgpem7h88kgfv\",\n  \"slug\": \"agentdevx-skill\",\n  \"version\": \"1.0.9\",\n  \"publishedAt\": 1782375074078\n}\n\nFile v1.0.9:skill-card.md\n\n## Description: <br>\nAgentdevx Skill lets agents register and call APIs through the AgentDevX gateway with Ed25519 identity, encrypted credential injection, rate limiting, and audit logging. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[mirajmahmudul](https://clawhub.ai/user/mirajmahmudul) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and agent builders use this skill to give agents access to registered APIs through a hosted gateway with agent identity, credential routing, rate limiting, and audit logging. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill automatically registers the agent with AgentDevX and sends outbound requests to a third-party hosted gateway. <br>\nMitigation: Install only where automatic third-party registration is acceptable, and review the AgentDevX dashboard and revocation process before use. <br>\nRisk: API calls, credentials stored in the vault, and memory contents may route through AgentDevX. <br>\nMitigation: Avoid sensitive APIs or production credentials until the service trust boundary, dashboard controls, and account deletion process are reviewed. <br>\n\n\n## Reference(s): <br>\n- [AgentDevX Gateway](https://agentdevx.onrender.com) <br>\n- [Smithery AgentDevX Server](https://smithery.ai/server/io.github.mirajmahmudul/agentdevx) <br>\n- [AgentDevX SDK](https://github.com/mirajmahmudul/agentdevx-sdk) <br>\n- [AgentDevX npm Package](https://www.npmjs.com/package/@agentdevx/install) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [API Calls, Shell commands, Configuration instructions, Guidance] <br>\n**Output Format:** [Markdown with inline bash and JSON code blocks; API responses depend on registered APIs.] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Routes requests through a third-party gateway; API response shape depends on the registered OpenAPI spec.] <br>\n\n## Skill Version(s): <br>\n1.0.9 (source: server release metadata; artifact frontmatter says 1.0.6) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.0.8: 3 files, 3893 bytes\n\nFiles: skill-card.md (2513b), SKILL.md (4802b), _meta.json (134b)\n\nFile v1.0.8:SKILL.md\n\n---\nname: agentdevx-skill\ndescription: \"Give your AI hands. Register any API via OpenAPI spec — agents get Ed25519 identity, encrypted credential injection, rate limiting, and audit logging automatically. One bootstrap call, zero human setup.\"\nversion: 1.0.6\nmetadata:\n  openclaw:\n    requires: {}\n    homepage: https://agentdevx.onrender.com\n    primaryEnv: AGENTDEVX_API_KEY\n    envVars:\n      - name: AGENTDEVX_API_KEY\n        required: false\n        description: Auto-obtained on first tool call via self-bootstrap (POST /agents/v1/bootstrap). No human action needed.\n      - name: AGENTDEVX_BASE_URL\n        required: false\n        description: \"Default: https://agentdevx.onrender.com\"\n    tags:\n      - mcp\n      - api-gateway\n      - agent-identity\n      - developer-tools\n      - ai-infrastructure\n      - credential-vault\n      - tool-registry\n    category: data-and-apis\n    homepage: https://agentdevx.onrender.com\n---\n\n# AgentDevX Gateway\n\nThe first infrastructure layer an AI agent can discover, install, and use entirely on its own — no human OAuth, no manual key exchange, no setup.\n\nEvery developer building an AI agent hits the same wall: auth spaghetti, credential sprawl, API integration hell, no stable agent identity, no persistent memory. AgentDevX solves all of this in one gateway.\n\n## Transparency — What Happens On First Use\n\nThis skill connects to **AgentDevX**, a third-party hosted gateway. On first tool call, your agent automatically:\n\n1. **Generates an Ed25519 keypair locally** — private key never leaves your machine\n2. **Registers with AgentDevX** (`POST /agents/v1/bootstrap`) — outbound network call to `https://agentdevx.onrender.com`\n3. **Receives a JWT + 75,000 free credits** — account created automatically\n4. **Gains access to 42+ tools** — weather, GitHub, exchange rates, email, and more\n\nThis is intentional self-provisioning, not a bug. If you do not want your agent registering with a third-party service, do not invoke this skill's tools.\n\nTo revoke access, visit your dashboard at https://agentdevx.onrender.com and delete your account.\n\n## Install\n\n```bash\nopenclaw skills install agentdevx-skill\n```\n\n## What Your Agent Can Do\n\nAfter install, your agent has:\n\n- **Cryptographic identity** — Ed25519, not OAuth. One identity across all tools.\n- **Encrypted credential vault** — AES-256-GCM. Store API keys securely, auto-injected on every call.\n- **42+ real-world tools** — weather, GitHub, exchange rates, public holidays, email, and more.\n- **Per-agent memory** — encrypted state that persists across sessions.\n- **Policy engine** — OPA/Rego access control. Dry-run mode. Full audit log.\n\n## Autonomous Bootstrap Flow\n\nYour agent runs this automatically — no human action needed:\n\n```bash\nPUBLIC_KEY=$(openssl rand -hex 32)\nBOOTSTRAP=$(curl -s -X POST https://agentdevx.onrender.com/agents/v1/bootstrap \\\n  -H \"Content-Type: application/json\" \\\n  -d \"{\\\"name\\\":\\\"openclaw-agent\\\",\\\"email\\\":\\\"agent@local\\\",\\\"public_key\\\":\\\"$PUBLIC_KEY\\\"}\")\nexport AGENTDEVX_API_KEY=$(echo \"$BOOTSTRAP\" | grep -o '\"access_token\":\"[^\"]*\"' | cut -d'\"' -f4)\n```\n\n## MCP Config (Claude Desktop / Cursor / Windsurf / any MCP client)\n\n```json\n{\n  \"mcpServers\": {\n    \"agentdevx\": {\n      \"url\": \"https://agentdevx.onrender.com/mcp\"\n    }\n  }\n}\n```\n\n## Available Tools (42+ via MCP)\n\n| Tool | What It Does |\n|------|-------------|\n| open-weather | Live weather & forecasts |\n| github-api | Repos, issues, PRs |\n| exchange-rate | Live currency conversion |\n| public-holidays | Holidays by country |\n| acme-mailer | Send emails |\n| jsonplaceholder | REST API testing |\n| petstore-api | OpenAPI 3.0 demo |\n\nMore tools added continuously. Any OpenAPI spec can be ingested.\n\n## Why AgentDevX vs Composio / Nango / Auth0\n\n| Feature | AgentDevX | Composio/Nango | Auth0 |\n|---------|-----------|----------------|-------|\n| AI self-bootstrap | ✅ Yes | ❌ No | ❌ No |\n| Ed25519 identity | ✅ Yes | ❌ OAuth only | ❌ OAuth only |\n| Encrypted vault | ✅ AES-256-GCM | ✅ OAuth-based | ✅ Enterprise |\n| Per-agent memory | ✅ Yes | ❌ No | ❌ No |\n| MCP native | ✅ Yes | ❌ No | ❌ No |\n| Indie pricing | ✅ Free tier | ❌ Enterprise | ❌ Enterprise |\n\n## Security & Revocation\n\n> ⚠️ **Trust Boundary:** AgentDevX is a third-party hosted gateway. API calls, credentials, and memory contents route through AgentDevX servers. All credentials encrypted at rest with AES-256-GCM. All traffic encrypted via TLS. Full audit log of every action, viewable via the AgentDevX dashboard.\n\n## Links\n\n- 🌐 Gateway: https://agentdevx.onrender.com\n- 📊 Smithery: https://smithery.ai/server/io.github.mirajmahmudul/agentdevx\n- 🔧 SDK: https://github.com/mirajmahmudul/agentdevx-sdk\n- 📦 npm: https://www.npmjs.com/package/@agentdevx/install\n\nFile v1.0.8:_meta.json\n\n{\n  \"ownerId\": \"kn712kvpp6y572wcge6dgpem7h88kgfv\",\n  \"slug\": \"agentdevx-skill\",\n  \"version\": \"1.0.8\",\n  \"publishedAt\": 1782371749441\n}\n\nFile v1.0.8:skill-card.md\n\n## Description: <br>\nAgentDevX registers APIs from OpenAPI specs so agents can use Ed25519 identity, encrypted credential injection, rate limiting, and audit logging through a third-party gateway. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[mirajmahmudul](https://clawhub.ai/user/mirajmahmudul) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and agent builders use this skill to connect agents to the AgentDevX hosted gateway, register APIs from OpenAPI specs, and configure MCP access to third-party tools with agent identity, credential vaulting, and audit logging. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill can automatically register an agent with AgentDevX on first use and receive an access token from that third-party service. <br>\nMitigation: Review the AgentDevX dashboard and revocation flow before invoking the skill, and avoid use in environments where automatic third-party registration is not acceptable. <br>\nRisk: Tool calls, stored credentials, and persistent memory route through AgentDevX as a third-party hosted gateway. <br>\nMitigation: Connect only APIs and data appropriate for that trust boundary, review audit logs, and revoke or delete the AgentDevX account when access is no longer needed. <br>\n\n\n## Reference(s): <br>\n- [AgentDevX Gateway](https://agentdevx.onrender.com) <br>\n- [AgentDevX Smithery Server](https://smithery.ai/server/io.github.mirajmahmudul/agentdevx) <br>\n- [AgentDevX SDK](https://github.com/mirajmahmudul/agentdevx-sdk) <br>\n- [AgentDevX npm Package](https://www.npmjs.com/package/@agentdevx/install) <br>\n- [ClawHub Skill Page](https://clawhub.ai/mirajmahmudul/skills/agentdevx-skill) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [guidance, shell commands, configuration] <br>\n**Output Format:** [Markdown with bash and JSON code blocks] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Requires outbound HTTPS to AgentDevX and may use AGENTDEVX_API_KEY and AGENTDEVX_BASE_URL environment variables.] <br>\n\n## Skill Version(s): <br>\n1.0.8 (source: server release metadata; artifact frontmatter says 1.0.6) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.0.7: 3 files, 3836 bytes\n\nFiles: skill-card.md (2382b), SKILL.md (4848b), _meta.json (134b)\n\nFile v1.0.7:SKILL.md\n\n---\nname: agentdevx-skill\ndescription: \"The only AI agent gateway that bootstraps itself. Give your AI cryptographic identity, an encrypted credential vault, and access to 42+ real-world APIs — with zero human setup. Ed25519 identity, AES-256-GCM vault, OPA policy engine, full audit log.\"\nversion: 1.0.6\nmetadata:\n  openclaw:\n    requires: {}\n    homepage: https://agentdevx.onrender.com\n    primaryEnv: AGENTDEVX_API_KEY\n    envVars:\n      - name: AGENTDEVX_API_KEY\n        required: false\n        description: Auto-obtained on first tool call via self-bootstrap (POST /agents/v1/bootstrap). No human action needed.\n      - name: AGENTDEVX_BASE_URL\n        required: false\n        description: \"Default: https://agentdevx.onrender.com\"\n    tags:\n      - mcp\n      - api-gateway\n      - agent-identity\n      - developer-tools\n      - ai-infrastructure\n      - credential-vault\n      - tool-registry\n    category: data-and-apis\n    homepage: https://agentdevx.onrender.com\n---\n\n# AgentDevX Gateway\n\nThe first infrastructure layer an AI agent can discover, install, and use entirely on its own — no human OAuth, no manual key exchange, no setup.\n\nEvery developer building an AI agent hits the same wall: auth spaghetti, credential sprawl, API integration hell, no stable agent identity, no persistent memory. AgentDevX solves all of this in one gateway.\n\n## Transparency — What Happens On First Use\n\nThis skill connects to **AgentDevX**, a third-party hosted gateway. On first tool call, your agent automatically:\n\n1. **Generates an Ed25519 keypair locally** — private key never leaves your machine\n2. **Registers with AgentDevX** (`POST /agents/v1/bootstrap`) — outbound network call to `https://agentdevx.onrender.com`\n3. **Receives a JWT + 75,000 free credits** — account created automatically\n4. **Gains access to 42+ tools** — weather, GitHub, exchange rates, email, and more\n\nThis is intentional self-provisioning, not a bug. If you do not want your agent registering with a third-party service, do not invoke this skill's tools.\n\nTo revoke access, visit your dashboard at https://agentdevx.onrender.com and delete your account.\n\n## Install\n\n```bash\nopenclaw skills install agentdevx-skill\n```\n\n## What Your Agent Can Do\n\nAfter install, your agent has:\n\n- **Cryptographic identity** — Ed25519, not OAuth. One identity across all tools.\n- **Encrypted credential vault** — AES-256-GCM. Store API keys securely, auto-injected on every call.\n- **42+ real-world tools** — weather, GitHub, exchange rates, public holidays, email, and more.\n- **Per-agent memory** — encrypted state that persists across sessions.\n- **Policy engine** — OPA/Rego access control. Dry-run mode. Full audit log.\n\n## Autonomous Bootstrap Flow\n\nYour agent runs this automatically — no human action needed:\n\n```bash\nPUBLIC_KEY=$(openssl rand -hex 32)\nBOOTSTRAP=$(curl -s -X POST https://agentdevx.onrender.com/agents/v1/bootstrap \\\n  -H \"Content-Type: application/json\" \\\n  -d \"{\\\"name\\\":\\\"openclaw-agent\\\",\\\"email\\\":\\\"agent@local\\\",\\\"public_key\\\":\\\"$PUBLIC_KEY\\\"}\")\nexport AGENTDEVX_API_KEY=$(echo \"$BOOTSTRAP\" | grep -o '\"access_token\":\"[^\"]*\"' | cut -d'\"' -f4)\n```\n\n## MCP Config (Claude Desktop / Cursor / Windsurf / any MCP client)\n\n```json\n{\n  \"mcpServers\": {\n    \"agentdevx\": {\n      \"url\": \"https://agentdevx.onrender.com/mcp\"\n    }\n  }\n}\n```\n\n## Available Tools (42+ via MCP)\n\n| Tool | What It Does |\n|------|-------------|\n| open-weather | Live weather & forecasts |\n| github-api | Repos, issues, PRs |\n| exchange-rate | Live currency conversion |\n| public-holidays | Holidays by country |\n| acme-mailer | Send emails |\n| jsonplaceholder | REST API testing |\n| petstore-api | OpenAPI 3.0 demo |\n\nMore tools added continuously. Any OpenAPI spec can be ingested.\n\n## Why AgentDevX vs Composio / Nango / Auth0\n\n| Feature | AgentDevX | Composio/Nango | Auth0 |\n|---------|-----------|----------------|-------|\n| AI self-bootstrap | ✅ Yes | ❌ No | ❌ No |\n| Ed25519 identity | ✅ Yes | ❌ OAuth only | ❌ OAuth only |\n| Encrypted vault | ✅ AES-256-GCM | ✅ OAuth-based | ✅ Enterprise |\n| Per-agent memory | ✅ Yes | ❌ No | ❌ No |\n| MCP native | ✅ Yes | ❌ No | ❌ No |\n| Indie pricing | ✅ Free tier | ❌ Enterprise | ❌ Enterprise |\n\n## Security & Revocation\n\n> ⚠️ **Trust Boundary:** AgentDevX is a third-party hosted gateway. API calls, credentials, and memory contents route through AgentDevX servers. All credentials encrypted at rest with AES-256-GCM. All traffic encrypted via TLS. Full audit log of every action, viewable via the AgentDevX dashboard.\n\n## Links\n\n- 🌐 Gateway: https://agentdevx.onrender.com\n- 📊 Smithery: https://smithery.ai/server/io.github.mirajmahmudul/agentdevx\n- 🔧 SDK: https://github.com/mirajmahmudul/agentdevx-sdk\n- 📦 npm: https://www.npmjs.com/package/@agentdevx/install\n\nFile v1.0.7:_meta.json\n\n{\n  \"ownerId\": \"kn712kvpp6y572wcge6dgpem7h88kgfv\",\n  \"slug\": \"agentdevx-skill\",\n  \"version\": \"1.0.7\",\n  \"publishedAt\": 1782291132590\n}\n\nFile v1.0.7:skill-card.md\n\n## Description: <br>\nAgentDevX gives AI agents a third-party hosted gateway for cryptographic identity, an encrypted credential vault, persistent memory, audit logging, and access to 42+ real-world APIs. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[mirajmahmudul](https://clawhub.ai/user/mirajmahmudul) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and agent operators use this skill to connect an agent to AgentDevX for hosted MCP/API access, credential storage, persistent memory, policy controls, and audit visibility. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill can register an agent with a third-party hosted service and route tool calls, credentials, and memory through that service. <br>\nMitigation: Install only after reviewing the AgentDevX dashboard, audit log, credential handling, and account deletion path. <br>\nRisk: Connected tools may send email, modify GitHub resources, or access business data when credentials are stored and used through the gateway. <br>\nMitigation: Store sensitive API keys only after reviewing the service trust boundary and limit connected credentials to the permissions required for the intended workflow. <br>\n\n\n## Reference(s): <br>\n- [ClawHub Skill Page](https://clawhub.ai/mirajmahmudul/skills/agentdevx-skill) <br>\n- [AgentDevX Gateway](https://agentdevx.onrender.com) <br>\n- [AgentDevX MCP Server on Smithery](https://smithery.ai/server/io.github.mirajmahmudul/agentdevx) <br>\n- [AgentDevX SDK](https://github.com/mirajmahmudul/agentdevx-sdk) <br>\n- [AgentDevX npm Package](https://www.npmjs.com/package/@agentdevx/install) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Guidance, Configuration, Shell commands] <br>\n**Output Format:** [Markdown with JSON and bash code blocks] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Configures a hosted MCP endpoint and optional AGENTDEVX environment variables.] <br>\n\n## Skill Version(s): <br>\n1.0.7 (source: server release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.0.6: 3 files, 3889 bytes\n\nFiles: skill-card.md (2476b), SKILL.md (4843b), _meta.json (134b)\n\nFile v1.0.6:SKILL.md\n\n---\nname: agentdevx-skill\ndescription: \"The only AI agent gateway that bootstraps itself. Give your AI cryptographic identity, an encrypted credential vault, and access to 42+ real-world APIs — with zero human setup. Ed25519 identity, AES-256-GCM vault, OPA policy engine, full audit log.\"\nversion: 1.0.6\nmetadata:\n  openclaw:\n    requires:\n      bins:\n        - curl\n    homepage: https://agentdevx.onrender.com\n    primaryEnv: AGENTDEVX_API_KEY\n    envVars:\n      - name: AGENTDEVX_API_KEY\n        required: false\n        description: Auto-obtained on first tool call via self-bootstrap (POST /agents/v1/bootstrap). No human action needed.\n      - name: AGENTDEVX_BASE_URL\n        required: false\n        description: \"Default: https://agentdevx.onrender.com\"\n    tags:\n      - mcp\n      - api-gateway\n      - agent-identity\n      - developer-tools\n      - ai-infrastructure\n      - credential-vault\n      - tool-registry\n    category: data-and-apis\n    homepage: https://agentdevx.onrender.com\n---\n\n# AgentDevX Gateway\n\nThe first infrastructure layer an AI agent can discover, install, and use entirely on its own — no human OAuth, no manual key exchange, no setup.\n\nEvery developer building an AI agent hits the same wall: auth spaghetti, credential sprawl, API integration hell, no stable agent identity, no persistent memory. AgentDevX solves all of this in one gateway.\n\n## Transparency — What Happens On First Use\n\nThis skill connects to **AgentDevX**, a third-party hosted gateway. On first tool call, your agent automatically:\n\n1. **Generates an Ed25519 keypair locally** — private key never leaves your machine\n2. **Registers with AgentDevX** (`POST /agents/v1/bootstrap`) — outbound network call to `https://agentdevx.onrender.com`\n3. **Receives a JWT + 75,000 free credits** — account created automatically\n4. **Gains access to 42+ tools** — weather, GitHub, exchange rates, email, and more\n\nThis is intentional self-provisioning, not a bug. If you do not want your agent registering with a third-party service, do not invoke this skill's tools.\n\nRevoke access anytime: `rm ~/.agentdevx/token ~/.agentdevx/identity`\n\n## Install\n\n```bash\nopenclaw skills install agentdevx-skill\n```\n\n## What Your Agent Can Do\n\nAfter install, your agent has:\n\n- **Cryptographic identity** — Ed25519, not OAuth. One identity across all tools.\n- **Encrypted credential vault** — AES-256-GCM. Store API keys securely, auto-injected on every call.\n- **42+ real-world tools** — weather, GitHub, exchange rates, public holidays, email, and more.\n- **Per-agent memory** — encrypted state that persists across sessions.\n- **Policy engine** — OPA/Rego access control. Dry-run mode. Full audit log.\n\n## Autonomous Bootstrap Flow\n\nYour agent runs this automatically — no human action needed:\n\n```bash\nPUBLIC_KEY=$(openssl rand -hex 32)\nBOOTSTRAP=$(curl -s -X POST https://agentdevx.onrender.com/agents/v1/bootstrap \\\n  -H \"Content-Type: application/json\" \\\n  -d \"{\\\"name\\\":\\\"openclaw-agent\\\",\\\"email\\\":\\\"agent@local\\\",\\\"public_key\\\":\\\"$PUBLIC_KEY\\\"}\")\nexport AGENTDEVX_API_KEY=$(echo \"$BOOTSTRAP\" | grep -o '\"access_token\":\"[^\"]*\"' | cut -d'\"' -f4)\n```\n\n## MCP Config (Claude Desktop / Cursor / Windsurf / any MCP client)\n\n```json\n{\n  \"mcpServers\": {\n    \"agentdevx\": {\n      \"url\": \"https://agentdevx.onrender.com/mcp\"\n    }\n  }\n}\n```\n\n## Available Tools (42+ via MCP)\n\n| Tool | What It Does |\n|------|-------------|\n| open-weather | Live weather & forecasts |\n| github-api | Repos, issues, PRs |\n| exchange-rate | Live currency conversion |\n| public-holidays | Holidays by country |\n| acme-mailer | Send emails |\n| jsonplaceholder | REST API testing |\n| petstore-api | OpenAPI 3.0 demo |\n\nMore tools added continuously. Any OpenAPI spec can be ingested.\n\n## Why AgentDevX vs Composio / Nango / Auth0\n\n| Feature | AgentDevX | Composio/Nango | Auth0 |\n|---------|-----------|----------------|-------|\n| AI self-bootstrap | ✅ Yes | ❌ No | ❌ No |\n| Ed25519 identity | ✅ Yes | ❌ OAuth only | ❌ OAuth only |\n| Encrypted vault | ✅ AES-256-GCM | ✅ OAuth-based | ✅ Enterprise |\n| Per-agent memory | ✅ Yes | ❌ No | ❌ No |\n| MCP native | ✅ Yes | ❌ No | ❌ No |\n| Indie pricing | ✅ Free tier | ❌ Enterprise | ❌ Enterprise |\n\n## Security & Revocation\n\n> ⚠️ **Trust Boundary:** AgentDevX is a third-party hosted gateway. API calls, credentials, and memory contents route through AgentDevX servers. All credentials encrypted at rest with AES-256-GCM. All traffic encrypted via TLS. Full audit log of every action, viewable via the AgentDevX dashboard.\n\n## Links\n\n- 🌐 Gateway: https://agentdevx.onrender.com\n- 📊 Smithery: https://smithery.ai/server/io.github.mirajmahmudul/agentdevx\n- 🔧 SDK: https://github.com/mirajmahmudul/agentdevx-sdk\n- 📦 npm: https://www.npmjs.com/package/@agentdevx/install\n\nFile v1.0.6:_meta.json\n\n{\n  \"ownerId\": \"kn712kvpp6y572wcge6dgpem7h88kgfv\",\n  \"slug\": \"agentdevx-skill\",\n  \"version\": \"1.0.6\",\n  \"publishedAt\": 1782284496757\n}\n\nFile v1.0.6:skill-card.md\n\n## Description: <br>\nAgentDevX Skill helps an agent bootstrap an AgentDevX identity, use an encrypted credential vault, configure MCP access, and call third-party API tools. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[mirajmahmudul](https://clawhub.ai/user/mirajmahmudul) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and agent operators use this skill to connect an AI agent to the AgentDevX gateway, self-provision an API credential, and access real-world API tools such as weather, GitHub, exchange rates, public holidays, and email. It is most relevant when an agent needs hosted API access, persistent identity, credential vaulting, policy checks, or MCP configuration. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: On first use, the skill may contact AgentDevX, auto-create or obtain a credential, and store local identity tokens. <br>\nMitigation: Use the skill only after approving this third-party registration flow; revoke local access by removing ~/.agentdevx/token and ~/.agentdevx/identity as documented. <br>\nRisk: API calls, credentials, prompts, repositories, or private memory may pass through a third-party hosted gateway. <br>\nMitigation: Review AgentDevX data handling and avoid sensitive inputs unless the service is approved for that data. <br>\n\n\n## Reference(s): <br>\n- [AgentDevX Gateway](https://agentdevx.onrender.com) <br>\n- [AgentDevX Smithery Server](https://smithery.ai/server/io.github.mirajmahmudul/agentdevx) <br>\n- [AgentDevX SDK](https://github.com/mirajmahmudul/agentdevx-sdk) <br>\n- [AgentDevX npm Package](https://www.npmjs.com/package/@agentdevx/install) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance] <br>\n**Output Format:** [Markdown with inline shell commands and JSON configuration] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Outputs may include setup commands, MCP configuration, revocation guidance, and descriptions of API gateway behavior.] <br>\n\n## Skill Version(s): <br>\n1.0.6 (source: frontmatter and release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.0.5: 3 files, 3961 bytes\n\nFiles: skill-card.md (2653b), SKILL.md (5201b), _meta.json (134b)\n\nFile v1.0.5:SKILL.md\n\n---\nname: agentdevx-skill\ndescription: Call any API securely from your agent — GitHub, weather, exchange rates, email and 50+ more. Agent self-registers on first use via Ed25519 identity. Encrypted credential vault, full audit log.\nversion: 1.0.5\nmetadata:\n  openclaw:\n    requires:\n      bins:\n        - curl\n    primaryEnv: AGENTDEVX_API_KEY\n    envVars:\n      - name: AGENTDEVX_API_KEY\n        required: false\n        description: Obtained automatically on first tool call via self-bootstrap (POST /agents/v1/bootstrap). No human action needed. See Transparency section.\n      - name: AGENTDEVX_BASE_URL\n        required: false\n        description: Override the default gateway URL (default https://agentdevx.onrender.com)\n    homepage: https://agentdevx.onrender.com\n---\n\n# AgentDevX Gateway\n\nGive your agent hands. Call any real API securely — GitHub, weather, exchange rates, email — with one Ed25519 identity and an encrypted credential vault.\n\n## Transparency — What Happens On First Use\n\nThis skill is designed to be used by an AI agent without human setup. Here is exactly what happens, so you know what to expect before your agent uses it:\n\n1. **Identity creation:** Your agent generates an Ed25519 keypair locally. The private key never leaves your machine.\n2. **Registration:** Your agent sends the public key to `https://agentdevx.onrender.com/agents/v1/bootstrap`, a third-party server not operated by ClawHub or OpenClaw. This is an outbound network call.\n3. **Account creation:** AgentDevX creates a user account and agent record tied to that public key, and returns a JWT access token plus 75,000 free credits.\n4. **Token storage:** The JWT is held in your agent's environment/session for subsequent calls. It is not written to disk unless your agent explicitly does so.\n5. **Subsequent use:** Every tool call after this point (weather, GitHub, email, etc.) is routed through AgentDevX's proxy using that token, and is recorded in AgentDevX's audit log.\n\nNo manual signup, browser step, or credential copying is required — registration happens automatically the first time a tool from this skill is invoked. This is intentional self-provisioning, not a bug or unexpected behavior.\n\n**If you do not want your agent to register with a third-party service, do not invoke tools from this skill.**\n\n## Setup (Fully Automatic)\n\nYour agent issues this on first use — no human action needed:\n\n```bash\nPUBLIC_KEY=$(openssl rand -hex 32)\nBOOTSTRAP=$(curl -s -X POST https://agentdevx.onrender.com/agents/v1/bootstrap \\\n  -H \"Content-Type: application/json\" \\\n  -d \"{\\\"name\\\":\\\"openclaw-agent\\\",\\\"email\\\":\\\"agent@local\\\",\\\"public_key\\\":\\\"$PUBLIC_KEY\\\"}\")\nexport AGENTDEVX_API_KEY=$(echo \"$BOOTSTRAP\" | grep -o '\"access_token\":\"[^\"]*\"' | cut -d'\"' -f4)\n```\n\n## What Your Agent Can Do\n\n### Discover available tools\n```bash\ncurl https://agentdevx.onrender.com/tools \\\n  -H \"Authorization: Bearer $AGENTDEVX_API_KEY\"\n```\n\n### Call any tool via proxy\n```bash\ncurl -X POST https://agentdevx.onrender.com/proxy/call \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $AGENTDEVX_API_KEY\" \\\n  -d '{\"tool_name\":\"github-api\",\"action\":\"getRepo\",\"params\":{\"owner\":\"openai\",\"repo\":\"openai-python\"}}'\n```\n\n### Store secrets securely (AES-256-GCM encrypted)\n```bash\ncurl -X POST https://agentdevx.onrender.com/credentials \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $AGENTDEVX_API_KEY\" \\\n  -d '{\"provider_id\":\"stripe\",\"type\":\"api_key\",\"value\":\"sk_live_...\"}'\n```\n\n### Save agent memory\n```bash\ncurl -X POST https://agentdevx.onrender.com/agents/me/memory \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $AGENTDEVX_API_KEY\" \\\n  -d '{\"key\":\"last_task\",\"value\":\"sent invoice to client\"}'\n```\n\n### Connect via MCP\n```json\n{\n  \"mcpServers\": {\n    \"agentdevx\": {\n      \"url\": \"https://agentdevx.onrender.com/mcp\"\n    }\n  }\n}\n```\n\n## Available Tools\n- **github-api** — repos, issues, search\n- **open-weather** — current weather, forecasts\n- **exchange-rate** — live currency conversion\n- **public-holidays** — holidays by country/year\n- **jsonplaceholder** — free REST test API\n- **petstore-api** — OpenAPI 3.0 demo\n- **acme-mailer** — send emails\n\n## Pricing\n- **Free:** 75,000 credits/month — granted automatically on registration\n- **Starter:** $8/month — 500 calls/day\n- **Pro:** $12/month — 5,000 calls/day\n- **Scale:** $29/month — unlimited\n\n## Security & Revocation\n\n> ⚠️ **Trust Boundary:** AgentDevX is a third-party hosted gateway. API calls, credentials, and memory contents are routed through AgentDevX servers. All credentials encrypted at rest with AES-256-GCM, all traffic encrypted in transit via TLS. Full audit log of every action maintained and viewable via the AgentDevX dashboard.\n\nTo stop using this skill and revoke the agent's access, delete the stored token from your agent's environment and contact AgentDevX support to delete the associated account.\n\n## Links\n- Gateway: https://agentdevx.onrender.com\n- Smithery: https://smithery.ai/server/io.github.mirajmahmudul/agentdevx\n- SDK: https://github.com/mirajmahmudul/agentdevx-sdk\n- npm: https://www.npmjs.com/package/@agentdevx/install\n\nFile v1.0.5:_meta.json\n\n{\n  \"ownerId\": \"kn712kvpp6y572wcge6dgpem7h88kgfv\",\n  \"slug\": \"agentdevx-skill\",\n  \"version\": \"1.0.5\",\n  \"publishedAt\": 1781697194819\n}\n\nFile v1.0.5:skill-card.md\n\n## Description: <br>\nCall APIs from an agent through AgentDevX, including GitHub, weather, exchange rates, email, credential storage, and memory features, with automatic first-use registration. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[mirajmahmudul](https://clawhub.ai/user/mirajmahmudul) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and agent operators use this skill to let agents self-register with AgentDevX, discover hosted tools, call third-party APIs, store credentials, and save agent memory through a hosted gateway. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill automatically registers an agent with the third-party AgentDevX service and makes outbound network calls on first use. <br>\nMitigation: Invoke the skill only after approving AgentDevX as a third-party service for the environment where the agent runs. <br>\nRisk: API requests, possible credentials, and memory contents may be routed through AgentDevX servers. <br>\nMitigation: Avoid storing sensitive production credentials or confidential memory unless AgentDevX's security, audit logging, and deletion process meet the user's requirements. <br>\nRisk: The skill gives an agent broad API-proxy, credential-storage, memory, and account-registration behavior. <br>\nMitigation: Use least-privilege credentials, review audit logs, and remove the token from the agent environment when access should be revoked. <br>\n\n\n## Reference(s): <br>\n- [AgentDevX Gateway](https://agentdevx.onrender.com) <br>\n- [AgentDevX Smithery Server](https://smithery.ai/server/io.github.mirajmahmudul/agentdevx) <br>\n- [AgentDevX SDK](https://github.com/mirajmahmudul/agentdevx-sdk) <br>\n- [AgentDevX npm Package](https://www.npmjs.com/package/@agentdevx/install) <br>\n- [ClawHub Skill Page](https://clawhub.ai/mirajmahmudul/agentdevx-skill) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance] <br>\n**Output Format:** [Markdown with bash and JSON code blocks] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Outputs guide an agent to make curl-based calls to the AgentDevX gateway and configure MCP access.] <br>\n\n## Skill Version(s): <br>\n1.0.5 (source: frontmatter and server release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.0.3: 3 files, 2891 bytes\n\nFiles: skill-card.md (2500b), SKILL.md (2286b), _meta.json (134b)\n\nFile v1.0.3:SKILL.md\n\n---\nname: agentdevx-skill\ndescription: Give your local AI access to 50+ real-world APIs — weather, GitHub, payments, food delivery and more. Auto-bootstraps. No config needed.\nversion: 1.0.3\nmetadata:\n  openclaw:\n    requires:\n      bins:\n        - curl\n    homepage: https://agentdevx.onrender.com\n    primaryEnv: AGENTDEVX_API_KEY\n    envVars:\n      - name: AGENTDEVX_API_KEY\n        required: false\n        description: Auto-generated on first use. Leave blank — skill bootstraps itself.\n      - name: AGENTDEVX_BASE_URL\n        required: false\n        description: \"Default: https://agentdevx.onrender.com\"\n---\n\n# AgentDevX Gateway\n\nGive your local AI hands. Connect to 50+ real-world APIs instantly — no config, no keys, no setup.\n\nYour AI auto-registers itself on first use and gets 75,000 free credits.\n\n## What Your AI Can Do After Install\n\n- 🍕 Order food\n- 🌤️ Get live weather\n- 💸 Check exchange rates\n- 📦 Query GitHub repos\n- 📅 Get public holidays\n- 📧 Send emails\n- 🔐 Store secrets securely\n- 🧠 Remember things between sessions\n\n## Install\n\n```bash\nopenclaw skills install agentdevx-skill\n```\n\nThat's it. Your AI is now connected to the real world.\n\n## How It Works\n\nOn first use your AI automatically:\n1. Generates an Ed25519 identity\n2. Bootstraps with AgentDevX\n3. Receives 75,000 free credits\n4. Gets access to all 50+ tools\n\nNo human setup needed.\n\n## MCP Config (Claude Desktop / Cursor / Windsurf)\n\n```json\n{\n  \"mcpServers\": {\n    \"agentdevx\": {\n      \"url\": \"https://agentdevx.onrender.com/mcp\"\n    }\n  }\n}\n```\n\n## Available Tools\n\n| Tool | What It Does |\n|------|-------------|\n| open-weather | Live weather & forecasts |\n| github-api | Repos, issues, PRs |\n| exchange-rate | Live currency conversion |\n| public-holidays | Holidays by country |\n| acme-mailer | Send emails |\n| jsonplaceholder | REST API testing |\n| petstore-api | OpenAPI demo |\n\n## Security\n\n> ⚠️ **Trust Boundary:** AgentDevX is a third-party hosted gateway. API calls route through AgentDevX servers. All credentials encrypted at rest with AES-256-GCM. Full audit log of every call.\n\n## Links\n\n- 🌐 Gateway: https://agentdevx.onrender.com\n- 📦 npm: https://www.npmjs.com/package/@agentdevx/install\n- 🔧 SDK: https://github.com/mirajmahmudul/agentdevx-sdk\n\nFile v1.0.3:_meta.json\n\n{\n  \"ownerId\": \"kn712kvpp6y572wcge6dgpem7h88kgfv\",\n  \"slug\": \"agentdevx-skill\",\n  \"version\": \"1.0.3\",\n  \"publishedAt\": 1781651187538\n}\n\nFile v1.0.3:skill-card.md\n\n## Description: <br>\nGive your local AI access to 50+ real-world APIs, including weather, GitHub, payments, food delivery, email, public holidays, exchange rates, and memory, with automatic bootstrap on first use. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[mirajmahmudul](https://clawhub.ai/user/mirajmahmudul) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and external users use this skill to let an agent reach AgentDevX-hosted tools for live data, GitHub queries, messaging, payments, food ordering, and other real-world API actions. It is best suited for users who understand that requests route through a third-party gateway and that bootstrap happens automatically. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill automatically connects the agent to a third-party gateway and creates an identity on first use. <br>\nMitigation: Review the publisher and service before installing, and use the skill only if routed API calls and automatic bootstrap are acceptable for the environment. <br>\nRisk: The gateway exposes broad real-world capabilities, including payments, email, food ordering, memory, and secrets-related features. <br>\nMitigation: Avoid sensitive credentials and high-impact actions until the publisher documents approval prompts, data retention, revocation, and how to disable automatic bootstrap. <br>\n\n\n## Reference(s): <br>\n- [AgentDevX Gateway](https://agentdevx.onrender.com) <br>\n- [AgentDevX MCP Endpoint](https://agentdevx.onrender.com/mcp) <br>\n- [AgentDevX npm Package](https://www.npmjs.com/package/@agentdevx/install) <br>\n- [AgentDevX SDK](https://github.com/mirajmahmudul/agentdevx-sdk) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, shell commands, configuration, guidance] <br>\n**Output Format:** [Markdown with inline bash and JSON code blocks] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Requires curl; may use AGENTDEVX_API_KEY and AGENTDEVX_BASE_URL, with the API key auto-generated on first use when absent.] <br>\n\n## Skill Version(s): <br>\n1.0.3 (source: frontmatter and server release metadata) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.0.2: 3 files, 3059 bytes\n\nFiles: skill-card.md (2089b), SKILL.md (3658b), _meta.json (134b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: agentdevx-gateway\ndescription: Call any API securely from your agent — GitHub, Stripe, SendGrid and 50+ more. One Ed25519 identity, encrypted credential vault, full audit log.\nversion: 1.0.1\nmetadata:\n  openclaw:\n    requires:\n      env:\n        - AGENTDEVX_API_KEY\n      bins:\n        - curl\n    primaryEnv: AGENTDEVX_API_KEY\n    envVars:\n      - name: AGENTDEVX_API_KEY\n        required: true\n        description: Your AgentDevX JWT token from POST /agents/v1/bootstrap\n      - name: AGENTDEVX_BASE_URL\n        required: false\n        description: Override the default gateway URL\n    homepage: https://agentdevx.onrender.com\n---\n\n# AgentDevX Gateway\n\nGive your agent hands. Call any real API securely with one Ed25519 identity and an encrypted credential vault.\n\n## Live Stats\n- ✅ 53 users · 62 agents · 955 proxy calls\n- ✅ 99/100 on Smithery · Security audit: Pass\n- ✅ 70+ installs on ClawHub\n\n## Security & Trust\n\n> ⚠️ **Trust Boundary Notice:** AgentDevX is a third-party gateway hosted on Render. API calls, credentials, and memory contents are routed through AgentDevX servers. All credentials are encrypted at rest using AES-256-GCM and all traffic is encrypted in transit via TLS. Full audit log of every action is maintained.\n\n## Setup\n\n1. Sign up at https://agentdevx.onrender.com/signup\n2. Bootstrap your agent:\n\n```bash\nPUBLIC_KEY=$(openssl rand -hex 32)\ncurl -X POST https://agentdevx.onrender.com/agents/v1/bootstrap \\\n  -H \"Content-Type: application/json\" \\\n  -d \"{\\\"name\\\":\\\"my-agent\\\",\\\"email\\\":\\\"you@example.com\\\",\\\"public_key\\\":\\\"$PUBLIC_KEY\\\"}\"\n```\n\n3. Export your token:\n```bash\nexport AGENTDEVX_API_KEY=<your_access_token>\n```\n\n## What Your Agent Can Do\n\n### Call any tool\n```bash\ncurl -X POST https://agentdevx.onrender.com/proxy/call \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $AGENTDEVX_API_KEY\" \\\n  -d '{\"tool_name\":\"github-api\",\"action\":\"getRepo\",\"params\":{\"owner\":\"openai\",\"repo\":\"openai-python\"}}'\n```\n\n### Discover tools\n```bash\ncurl https://agentdevx.onrender.com/tools \\\n  -H \"Authorization: Bearer $AGENTDEVX_API_KEY\"\n```\n\n### Store secrets (AES-256-GCM encrypted)\n```bash\ncurl -X POST https://agentdevx.onrender.com/credentials \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $AGENTDEVX_API_KEY\" \\\n  -d '{\"provider_id\":\"stripe\",\"type\":\"api_key\",\"value\":\"sk_live_...\"}'\n```\n\n### Save agent memory\n```bash\ncurl -X POST https://agentdevx.onrender.com/agents/me/memory \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $AGENTDEVX_API_KEY\" \\\n  -d '{\"key\":\"last_task\",\"value\":\"sent invoice to client\"}'\n```\n\n### Real-time event stream\n```bash\ncurl -N https://agentdevx.onrender.com/stream/events \\\n  -H \"Authorization: Bearer $AGENTDEVX_API_KEY\"\n```\n\n### Connect via MCP\n```json\n{\n  \"mcpServers\": {\n    \"agentdevx\": {\n      \"url\": \"https://agentdevx.onrender.com/mcp\"\n    }\n  }\n}\n```\n\n## Available Tools (50+)\n- **github-api** — repos, issues, search\n- **open-weather** — current weather, forecasts\n- **exchange-rate** — live currency conversion\n- **public-holidays** — holidays by country/year\n- **jsonplaceholder** — free REST test API\n- **petstore-api** — OpenAPI 3.0 demo\n- **acme-mailer** — send emails\n\n## Pricing\n- **Free:** 75,000 credits/month — no card needed\n- **Starter:** $8/month — 500 calls/day\n- **Pro:** $12/month — 5,000 calls/day\n- **Scale:** $29/month — unlimited\n\n## Links\n- Gateway: https://agentdevx.onrender.com\n- Smithery: https://smithery.ai/servers/mirajmahmudul57/agentdevx\n- SDK: https://github.com/mirajmahmudul/agentdevx-sdk\n- npm: https://www.npmjs.com/package/@agentdevx/install\n\nFile v1.0.2:_meta.json\n\n{\n  \"ownerId\": \"kn712kvpp6y572wcge6dgpem7h88kgfv\",\n  \"slug\": \"agentdevx-skill\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1781513450450\n}\n\nFile v1.0.2:skill-card.md\n\n## Description: <br>\nCalls third-party API tools from an agent through the AgentDevX gateway using a bearer token, credential vault, and audit log. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[mirajmahmudul](https://clawhub.ai/user/mirajmahmudul) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nExternal developers and agent builders use this skill to route API calls, tool discovery, credential storage, and agent memory operations through AgentDevX from agents that can run curl or connect over MCP. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill requires a bearer token and can route API calls, credentials, and memory through AgentDevX infrastructure. <br>\nMitigation: Use a scoped, revocable token; avoid connecting high-impact accounts unless necessary; review tool calls before execution; and confirm AgentDevX supports allowlists, audit logs, and approval prompts. <br>\n\n\n## Reference(s): <br>\n- [AgentDevX Gateway](https://agentdevx.onrender.com) <br>\n- [ClawHub Skill Page](https://clawhub.ai/mirajmahmudul/agentdevx-skill) <br>\n- [AgentDevX Smithery Server](https://smithery.ai/servers/mirajmahmudul57/agentdevx) <br>\n- [AgentDevX SDK](https://github.com/mirajmahmudul/agentdevx-sdk) <br>\n- [AgentDevX npm Package](https://www.npmjs.com/package/@agentdevx/install) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [shell commands, configuration, guidance] <br>\n**Output Format:** [Markdown guidance with curl commands and JSON snippets] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Requires AGENTDEVX_API_KEY bearer token and curl; AGENTDEVX_BASE_URL is optional.] <br>\n\n## Skill Version(s): <br>\n1.0.2 (source: server release metadata) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.0.1: 3 files, 2937 bytes\n\nFiles: skill-card.md (2119b), SKILL.md (3314b), _meta.json (134b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: agentdevx-gateway\ndescription: Call any API securely from your agent — GitHub, Stripe, SendGrid and 50+ more. One Ed25519 identity, encrypted credential vault, full audit log.\nversion: 1.0.1\nmetadata:\n  openclaw:\n    requires:\n      env:\n        - AGENTDEVX_API_KEY\n      bins:\n        - curl\n    primaryEnv: AGENTDEVX_API_KEY\n    envVars:\n      - name: AGENTDEVX_API_KEY\n        required: true\n        description: Your AgentDevX JWT token from POST /agents/v1/bootstrap\n      - name: AGENTDEVX_BASE_URL\n        required: false\n        description: Override the default gateway URL\n    homepage: https://agentdevx.onrender.com\n---\n\n# AgentDevX Gateway\n\nGive your agent hands. Call any real API securely with one Ed25519 identity and an encrypted credential vault.\n\n## Live Stats\n- ✅ 53 users · 62 agents · 955 proxy calls\n- ✅ 99/100 on Smithery · Security audit: Pass\n- ✅ 70+ installs on ClawHub\n\n## Setup\n\n1. Sign up at https://agentdevx.onrender.com/signup\n2. Bootstrap your agent:\n\n```bash\nPUBLIC_KEY=$(openssl rand -hex 32)\ncurl -X POST https://agentdevx.onrender.com/agents/v1/bootstrap \\\n  -H \"Content-Type: application/json\" \\\n  -d \"{\\\"name\\\":\\\"my-agent\\\",\\\"email\\\":\\\"you@example.com\\\",\\\"public_key\\\":\\\"$PUBLIC_KEY\\\"}\"\n```\n\n3. Export your token:\n```bash\nexport AGENTDEVX_API_KEY=<your_access_token>\n```\n\n## What Your Agent Can Do\n\n### Call any tool\n```bash\ncurl -X POST https://agentdevx.onrender.com/proxy/call \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $AGENTDEVX_API_KEY\" \\\n  -d '{\"tool_name\":\"github-api\",\"action\":\"getRepo\",\"params\":{\"owner\":\"openai\",\"repo\":\"openai-python\"}}'\n```\n\n### Discover tools\n```bash\ncurl https://agentdevx.onrender.com/tools \\\n  -H \"Authorization: Bearer $AGENTDEVX_API_KEY\"\n```\n\n### Store secrets (AES-256-GCM encrypted)\n```bash\ncurl -X POST https://agentdevx.onrender.com/credentials \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $AGENTDEVX_API_KEY\" \\\n  -d '{\"provider_id\":\"stripe\",\"type\":\"api_key\",\"value\":\"sk_live_...\"}'\n```\n\n### Save agent memory\n```bash\ncurl -X POST https://agentdevx.onrender.com/agents/me/memory \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $AGENTDEVX_API_KEY\" \\\n  -d '{\"key\":\"last_task\",\"value\":\"sent invoice to client\"}'\n```\n\n### Real-time event stream\n```bash\ncurl -N https://agentdevx.onrender.com/stream/events \\\n  -H \"Authorization: Bearer $AGENTDEVX_API_KEY\"\n```\n\n### Connect via MCP\n```json\n{\n  \"mcpServers\": {\n    \"agentdevx\": {\n      \"url\": \"https://agentdevx.onrender.com/mcp\"\n    }\n  }\n}\n```\n\n## Available Tools (50+)\n- **github-api** — repos, issues, search\n- **open-weather** — current weather, forecasts\n- **exchange-rate** — live currency conversion\n- **public-holidays** — holidays by country/year\n- **jsonplaceholder** — free REST test API\n- **petstore-api** — OpenAPI 3.0 demo\n- **acme-mailer** — send emails\n\n## Pricing\n- **Free:** 75,000 credits/month — no card needed\n- **Starter:** $8/month — 500 calls/day\n- **Pro:** $12/month — 5,000 calls/day\n- **Scale:** $29/month — unlimited\n\n## Links\n- Gateway: https://agentdevx.onrender.com\n- Smithery: https://smithery.ai/servers/mirajmahmudul57/agentdevx\n- SDK: https://github.com/mirajmahmudul/agentdevx-sdk\n- npm: https://www.npmjs.com/package/@agentdevx/install\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn712kvpp6y572wcge6dgpem7h88kgfv\",\n  \"slug\": \"agentdevx-skill\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1781509705733\n}\n\nFile v1.0.1:skill-card.md\n\n## Description: <br>\nCall APIs from an agent through AgentDevX, including GitHub, Stripe, SendGrid, and other integrations, using an Ed25519 identity, credential vault, and audit log. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[mirajmahmudul](https://clawhub.ai/user/mirajmahmudul) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and agent builders use this skill to configure agents that call third-party APIs, store credentials, discover available tools, save agent memory, and connect to AgentDevX through HTTP or MCP. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: AgentDevX can handle API credentials, proxied requests, and saved agent memory without enough scoping or data-handling detail in the evidence. <br>\nMitigation: Use least-privilege API keys, avoid regulated or highly sensitive data until provider security and retention policies are reviewed, and rotate credentials if use stops. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/mirajmahmudul/agentdevx-skill) <br>\n- [AgentDevX gateway homepage](https://agentdevx.onrender.com) <br>\n- [Smithery AgentDevX server](https://smithery.ai/servers/mirajmahmudul57/agentdevx) <br>\n- [AgentDevX SDK](https://github.com/mirajmahmudul/agentdevx-sdk) <br>\n- [AgentDevX npm package](https://www.npmjs.com/package/@agentdevx/install) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Shell commands, Configuration, Guidance] <br>\n**Output Format:** [Markdown with inline shell and JSON examples] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Requires curl and AGENTDEVX_API_KEY; AGENTDEVX_BASE_URL is optional.] <br>\n\n## Skill Version(s): <br>\n1.0.1 (source: server evidence and SKILL.md frontmatter) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.0.0: 3 files, 2852 bytes\n\nFiles: skill-card.md (2265b), SKILL.md (3014b), _meta.json (134b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: agentdevx-gateway\ndescription: Call any API securely from your agent — GitHub, Stripe, SendGrid and 40+ more. One Ed25519 identity, encrypted credential vault, full audit log.\nversion: 1.0.0\nmetadata:\n  openclaw:\n    requires:\n      env:\n        - AGENTDEVX_API_KEY\n      bins:\n        - curl\n    primaryEnv: AGENTDEVX_API_KEY\n    envVars:\n      - name: AGENTDEVX_API_KEY\n        required: true\n        description: Your AgentDevX JWT token from POST /agents/v1/bootstrap\n      - name: AGENTDEVX_BASE_URL\n        required: false\n        description: Override the default gateway URL\n    homepage: https://agentdevx.onrender.com\n---\n\n# AgentDevX Gateway\n\nGive your agent hands. Call any real API securely with one Ed25519 identity and an encrypted credential vault.\n\n## Setup\n\n1. Sign up at https://agentdevx.onrender.com/signup\n2. Bootstrap your agent:\n\n```bash\nPUBLIC_KEY=$(openssl rand -hex 32)\ncurl -X POST https://agentdevx.onrender.com/agents/v1/bootstrap \\\n  -H \"Content-Type: application/json\" \\\n  -d \"{\\\"name\\\":\\\"my-agent\\\",\\\"email\\\":\\\"you@example.com\\\",\\\"public_key\\\":\\\"$PUBLIC_KEY\\\"}\"\n```\n\n3. Export your token:\n```bash\nexport AGENTDEVX_API_KEY=<your_access_token>\n```\n\n## What Your Agent Can Do\n\n### Call any tool\n```bash\ncurl -X POST https://agentdevx.onrender.com/proxy/call \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $AGENTDEVX_API_KEY\" \\\n  -d '{\"tool_name\":\"github-api\",\"action\":\"getRepo\",\"params\":{\"owner\":\"openai\",\"repo\":\"openai-python\"}}'\n```\n\n### Discover tools\n```bash\ncurl https://agentdevx.onrender.com/tools \\\n  -H \"Authorization: Bearer $AGENTDEVX_API_KEY\"\n```\n\n### Store secrets (AES-256-GCM encrypted)\n```bash\ncurl -X POST https://agentdevx.onrender.com/credentials \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $AGENTDEVX_API_KEY\" \\\n  -d '{\"provider_id\":\"stripe\",\"type\":\"api_key\",\"value\":\"sk_live_...\"}'\n```\n\n### Save agent memory\n```bash\ncurl -X POST https://agentdevx.onrender.com/agents/me/memory \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $AGENTDEVX_API_KEY\" \\\n  -d '{\"key\":\"last_task\",\"value\":\"sent invoice to client\"}'\n```\n\n### Connect via MCP\n```json\n{\n  \"mcpServers\": {\n    \"agentdevx\": {\n      \"url\": \"https://agentdevx.onrender.com/mcp\"\n    }\n  }\n}\n```\n\n## Available Tools\n- **github-api** — repos, issues, search\n- **open-weather** — current weather, forecasts\n- **exchange-rate** — live currency conversion\n- **public-holidays** — holidays by country/year\n- **jsonplaceholder** — free REST test API\n\n## Real-time Streaming\n```bash\ncurl -N https://agentdevx.onrender.com/stream/events \\\n  -H \"Authorization: Bearer $AGENTDEVX_API_KEY\"\n```\n\n## Pricing\n- **Free:** 75,000 credits/month\n- **Starter:** $8/month — 500 calls/day\n- **Pro:** $12/month — 5,000 calls/day\n- **Scale:** $29/month — unlimited\n\n## Links\n- Gateway: https://agentdevx.onrender.com\n- Smithery: https://smithery.ai/servers/mirajmahmudul57/agentdevx\n- SDK: https://github.com/mirajmahmudul/agentdevx-sdk\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn712kvpp6y572wcge6dgpem7h88kgfv\",\n  \"slug\": \"agentdevx-skill\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1781379052384\n}\n\nFile v1.0.0:skill-card.md\n\n## Description: <br>\nCall any API securely from your agent, including GitHub, Stripe, SendGrid, and 40+ more, using one Ed25519 identity, an encrypted credential vault, and a full audit log. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[mirajmahmudul](https://clawhub.ai/user/mirajmahmudul) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and agent operators use this skill to connect an agent to hosted API gateway capabilities for tool discovery, API calls, credential storage, agent memory, event streaming, and MCP access. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: API requests, tool payloads, credentials, and saved memory are routed through the hosted AgentDevX service. <br>\nMitigation: Use least-privilege or test credentials, avoid regulated or unnecessary sensitive data, and confirm AgentDevX retention, deletion, and access-control policies before production use. <br>\nRisk: The skill requires an AGENTDEVX_API_KEY for access to the hosted gateway. <br>\nMitigation: Store the token in the agent runtime secret manager, rotate it if exposed, and avoid placing it in prompts, logs, or checked-in files. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/mirajmahmudul/agentdevx-skill) <br>\n- [AgentDevX gateway homepage](https://agentdevx.onrender.com) <br>\n- [Smithery server listing](https://smithery.ai/servers/mirajmahmudul57/agentdevx) <br>\n- [AgentDevX SDK](https://github.com/mirajmahmudul/agentdevx-sdk) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [guidance, shell commands, configuration, API calls] <br>\n**Output Format:** [Markdown with bash and JSON examples] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Requires AGENTDEVX_API_KEY and curl; AGENTDEVX_BASE_URL is optional.] <br>\n\n## Skill Version(s): <br>\n1.0.0 (source: server release evidence and SKILL.md frontmatter) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>","readmeExcerpt":"Skill: Agentdevx Skill Owner: mirajmahmudul Summary: Give your AI hands. The identity and security layer every AI agent needs — register any API, agents get Ed25519 identity, encrypted vault, and audit logging. Tags: latest:1.1.0 Version history: v1.1.0 | 2026-08-15T18:22:13.635Z | auto - Added documentation for built-in native MCP tools (memory.store, memory.recall, webscrape.scrape, webscrape.extractDesign) - Expan","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"openclaw skills install agentdevx-skill"},{"language":"bash","snippet":"PUBLIC_KEY=$(openssl rand -hex 32)\nBOOTSTRAP=$(curl -s -X POST https://agentdevx.onrender.com/agents/v1/bootstrap \\\n  -H \"Content-Type: application/json\" \\\n  -d \"{\\\"name\\\":\\\"openclaw-agent\\\",\\\"email\\\":\\\"agent@local\\\",\\\"public_key\\\":\\\"$PUBLIC_KEY\\\"}\")\nexport AGENTDEVX_API_KEY=$(echo \"$BOOTSTRAP\" | grep -o '\"access_token\":\"[^\"]*\"' | cut -d'\"' -f4)"},{"language":"json","snippet":"{\n  \"mcpServers\": {\n    \"agentdevx\": {\n      \"url\": \"https://agentdevx.onrender.com/mcp\"\n    }\n  }\n}"},{"language":"bash","snippet":"openclaw skills install agentdevx-skill"},{"language":"bash","snippet":"PUBLIC_KEY=$(openssl rand -hex 32)\nBOOTSTRAP=$(curl -s -X POST https://agentdevx.onrender.com/agents/v1/bootstrap \\\n  -H \"Content-Type: application/json\" \\\n  -d \"{\\\"name\\\":\\\"openclaw-agent\\\",\\\"email\\\":\\\"agent@local\\\",\\\"public_key\\\":\\\"$PUBLIC_KEY\\\"}\")\nexport AGENTDEVX_API_KEY=$(echo \"$BOOTSTRAP\" | grep -o '\"access_token\":\"[^\"]*\"' | cut -d'\"' -f4)"},{"language":"json","snippet":"{\n  \"mcpServers\": {\n    \"agentdevx\": {\n      \"url\": \"https://agentdevx.onrender.com/mcp\"\n    }\n  }\n}"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: agentdevx-skill\ndescription: \"Give your AI hands. Register any API via OpenAPI spec — agents get Ed25519 identity, encrypted credential injection, rate limiting, and audit logging automatically. One bootstrap call, zero human setup.\"\nversion: 1.1.0\nmetadata:\n  openclaw:\n    requires: {}\n    homepage: https://agentdevx.onrender.com\n    primaryEnv: AGENTDEVX_API_KEY\n    envVars:\n      - name: AGENTDEVX_API_KEY\n        required: false\n        description: Auto-obtained on first tool call via self-bootstrap (POST /agents/v1/bootstrap). No human action needed.\n      - name: AGENTDEVX_BASE_URL\n        required: false\n        description: \"Default: https://agentdevx.onrender.com\"\n    tags:\n      - mcp\n      - api-gateway\n      - agent-identity\n      - developer-tools\n      - ai-infrastructure\n      - credential-vault\n      - tool-registry\n    category: data-and-apis\n    homepage: https://agentdevx.onrender.com\n---\n\n# AgentDevX Gateway\n\nThe first infrastructure layer an AI agent can discover, install, and use entirely on its own — no human OAuth, no manual key exchange, no setup.\n\nEvery developer building an AI agent hits the same wall: auth spaghetti, credential sprawl, API integration hell, no stable agent identity, no persistent memory. AgentDevX solves all of this in one gateway.\n\n## Transparency — What Happens On First Use\n\nThis skill connects to **AgentDevX**, a third-party hosted gateway. On first tool call, your agent automatically:\n\n1. **Generates an Ed25519 keypair locally** — private key never leaves your machine\n2. **Registers with AgentDevX** (`POST /agents/v1/bootstrap`) — outbound network call to `https://agentdevx.onrender.com`\n3. **Receives a JWT + 75,000 free credits** — account created automatically\n4. **Gains proxy access to any registered API** — pre-built examples include weather, GitHub, exchange rates, and more. Register your own via OpenAPI spec.\n\nThis is intentional self-provisioning, not a bug. If you do not want your agent registering with a third-party service, do not invoke this skill's tools.\n\nTo revoke access, visit your dashboard at https://agentdevx.onrender.com and delete your account.\n\n## Install\n\n```bash\nopenclaw skills install agentdevx-skill\n```\n\n## What Your Agent Can Do\n\nAfter install, your agent has:\n\n- **Cryptographic identity** — Ed25519, not OAuth. One identity across all tools.\n- **Encrypted credential vault** — AES-256-GCM. Store API keys securely, auto-injected on every call.\n- **Access to any registered API** — 7 pre-built examples included. Register any API via OpenAPI spec and agents can use it instantly.\n- **Per-agent memory** — encrypted state that persists across sessions.\n- **Policy engine** — OPA/Rego access control. Dry-run mode. Full audit log.\n\n## Autonomous Bootstrap Flow\n\nYour agent runs this automatically — no human action needed:\n\n```bash\nPUBLIC_KEY=$(openssl rand -hex 32)\nBOOTSTRAP=$(curl -s -X POST https://agentdevx.onrender.com/agents/v1/bootstrap \\\n  -H \"Content-Type: applicatio"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn712kvpp6y572wcge6dgpem7h88kgfv\",\n  \"slug\": \"agentdevx-skill\",\n  \"version\": \"1.1.0\",\n  \"publishedAt\": 1786818133635\n}"},{"path":"skill-card.md","content":"## Description:\n\nAgentdevx Skill helps agents use AgentDevX to register APIs from OpenAPI specs and route calls through identity, credential vault, memory, rate limiting, and audit logging features.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[mirajmahmudul](https://clawhub.ai/user/mirajmahmudul)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and agent builders use this skill to connect agents to the AgentDevX gateway, configure MCP access, register APIs from OpenAPI specs, and use persistent memory or credential-backed API calls.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill uses a third-party hosted gateway for setup, API calls, credentials, and persistent memory.\n\nMitigation: Review the gateway trust boundary before installation and use only data or API keys you are willing to expose to AgentDevX.\n\nRisk: The skill can automatically create an AgentDevX account and route credentials through that service on first use.\n\nMitigation: Verify token scope, revocation, retention, and credential isolation outside the skill text before invoking its tools.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/mirajmahmudul/skills/agentdevx-skill)\n- [AgentDevX gateway](https://agentdevx.onrender.com)\n- [Smithery AgentDevX listing](https://smithery.ai/server/io.github.mirajmahmudul/agentdevx)\n- [AgentDevX SDK](https://github.com/mirajmahmudul/agentdevx-sdk)\n- [AgentDevX npm package](https://www.npmjs.com/package/@agentdevx/install)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown guidance with shell command examples and JSON MCP configuration snippets]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May describe outbound AgentDevX calls and environment variables such as AGENTDEVX_API_KEY.]\n\n## Skill Version(s):\n\n1.1.0 (source: frontmatter and server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Give your AI hands. The identity and security layer every AI agent needs — register any API, agents get Ed25519 identity, encrypted vault, and audit logging. Skill: Agentdevx Skill Owner: mirajmahmudul Summary: Give your AI hands. The identity and security layer every AI agent needs — register any API, agents get Ed25519 identity, encrypted vault, and audit logging. Tags: latest:1.1.0 Version history: v1.1.0 | 2026-08-15T18:22:13.635Z | auto - Added documentation for built-in native MCP tools (memory.store, memory.recall, webscrape.scrape, webscrape.extractDesign) - Expan","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1420,"uniquenessScore":45,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T22:13:47.462Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-11T22:13:47.462Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-13T06:52:16.728Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}