{"id":"e77ae84f-bb6c-45ce-ab18-e3de6a515fbd","entityType":"agent","slug":"clawhub-ezpeasydave-claude-code-dispatch","name":"Claude Code Dispatch","canonicalUrl":"https://www.xpersona.co/agent/clawhub-ezpeasydave-claude-code-dispatch","canonicalPath":"/agent/clawhub-ezpeasydave-claude-code-dispatch","generatedAt":"2026-10-10T14:42:33.264Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-10T11:57:59.533Z","emptyReason":null},"description":"Invoke Claude Code CLI as a subprocess for coding tasks that require file access, editing, and shell execution Skill: Claude Code Dispatch Owner: ezpeasydave Summary: Invoke Claude Code CLI as a subprocess for coding tasks that require file access, editing, and shell execution Tags: latest:1.0.0 Version history: v1.0.0 | 2026-03-15T10:52:33.478Z | user - Initial release of claude-code-dispatch skill. - Enables delegating coding tasks to Claude Code CLI for operations requiring file access, editing, and shell command execution","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.4K downloads reported by the source. Last updated 10/10/2026.","installCommand":"clawhub skill install s172me68ynsbw74pq90aj25tw584xywe:claude-code-dispatch","sourceUrl":"https://clawhub.ai/ezpeasydave/claude-code-dispatch","homepage":"https://clawhub.ai/ezpeasydave/skills/claude-code-dispatch","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/ezpeasydave/claude-code-dispatch","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/ezpeasydave/skills/claude-code-dispatch","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":63,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Invoke Claude Code CLI as a subprocess for coding tasks that require file access, editing, and shell execution Skill: Claude Code Dispatch Owner: ezpeasydave Su"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-10T11:57:59.533Z","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":"2026-10-10T11:57:59.533Z","emptyReason":null},"stars":null,"forks":null,"downloads":1448,"packageName":null,"latestVersion":"1.0.0","tractionLabel":"1.4K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T11:57:59.532Z","emptyReason":null},"lastUpdatedAt":"2026-10-10T11:57:59.533Z","lastCrawledAt":"2026-10-10T11:57:59.532Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-11T11:57:59.532Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.0","createdAt":"2026-03-15T10:52:33.478Z","changelog":"- Initial release of claude-code-dispatch skill. - Enables delegating coding tasks to Claude Code CLI for operations requiring file access, editing, and shell command execution. - Supports triggering via phrases like \"use claude code\" or \"run claude on\". - Requires pre-installed and authenticated Claude Code CLI and jq. - Provides detailed usage instructions, toolset selection, and model options. - Includes structured output and clear guidelines on when and how to use the skill.","fileCount":5,"zipByteSize":5991}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s172me68ynsbw74pq90aj25tw584xywe:claude-code-dispatch","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","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-ezpeasydave-claude-code-dispatch/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ezpeasydave-claude-code-dispatch/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ezpeasydave-claude-code-dispatch/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-ezpeasydave-claude-code-dispatch/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-ezpeasydave-claude-code-dispatch/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-ezpeasydave-claude-code-dispatch/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T14:42:33.263Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ezpeasydave-claude-code-dispatch/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ezpeasydave-claude-code-dispatch/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ezpeasydave-claude-code-dispatch/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ezpeasydave-claude-code-dispatch/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":"2026-10-10T11:57:59.533Z","emptyReason":null},"readme":"Skill: Claude Code Dispatch\n\nOwner: ezpeasydave\n\nSummary: Invoke Claude Code CLI as a subprocess for coding tasks that require file access, editing, and shell execution\n\nTags: latest:1.0.0\n\nVersion history:\n\nv1.0.0 | 2026-03-15T10:52:33.478Z | user\n\n- Initial release of claude-code-dispatch skill.\n- Enables delegating coding tasks to Claude Code CLI for operations requiring file access, editing, and shell command execution.\n- Supports triggering via phrases like \"use claude code\" or \"run claude on\".\n- Requires pre-installed and authenticated Claude Code CLI and jq.\n- Provides detailed usage instructions, toolset selection, and model options.\n- Includes structured output and clear guidelines on when and how to use the skill.\n\nArchive index:\n\nArchive v1.0.0: 5 files, 5991 bytes\n\nFiles: _meta.json (139b), .clawhub/origin.json (140b), scripts/invoke-claude.sh (4253b), skill-card.md (2111b), SKILL.md (5130b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: claude-code-dispatch\ndescription: Invoke Claude Code CLI as a subprocess for coding tasks that require file access, editing, and shell execution\nversion: 1.0.0\nauthor: Claude Code (Anthropic)\ntriggers:\n  - \"use claude code\"\n  - \"have claude fix\"\n  - \"claude code task\"\n  - \"run claude on\"\n  - \"send this to claude code\"\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"claude\",\"jq\"]},\"install\":[{\"id\":\"claude\",\"kind\":\"npm\",\"package\":\"@anthropic-ai/claude-code\",\"bins\":[\"claude\"],\"label\":\"Install Claude Code (npm)\"},{\"id\":\"jq\",\"kind\":\"brew\",\"formula\":\"jq\",\"bins\":[\"jq\"],\"label\":\"Install jq (brew)\"}]}}\n---\n\n# Claude Code Dispatch\n\nDelegate coding tasks to Claude Code CLI. Use this when a task requires capabilities beyond what the current agent can do: file editing, shell commands, multi-file debugging, code review with file access, or any work that needs direct filesystem interaction.\n\n## Prerequisites\n\nClaude Code must be installed and authenticated on the host machine. The host's `~/.claude/settings.json` must pre-authorize the tools this skill will use. Example minimal config:\n\n```json\n{\n  \"permissions\": {\n    \"allow\": [\n      \"Read\",\n      \"Edit\",\n      \"Glob\",\n      \"Grep\",\n      \"Bash(git:*)\",\n      \"Bash(npm:*)\"\n    ]\n  }\n}\n```\n\nWithout pre-authorized permissions, Claude Code will fail in non-interactive mode because it cannot prompt for approval.\n\n## When to Use\n\nRoute tasks to Claude Code when they require:\n- File reading, editing, or creation on the host filesystem\n- Shell command execution (builds, tests, git operations)\n- Multi-file debugging or refactoring\n- Code review with actual file access\n- Any task where the agent needs to interact with the local filesystem\n\nDo NOT use when:\n- The task is purely conversational (answering questions, planning)\n- You can handle it with your own capabilities or other skills\n- The task involves external APIs you already have access to\n\n## Usage\n\n```bash\nbash {baseDir}/scripts/invoke-claude.sh \\\n  --prompt \"Fix the broken import in src/App.tsx\" \\\n  --workdir \"/path/to/project\" \\\n  --model sonnet \\\n  --tools \"Read,Edit,Glob,Grep,Bash\"\n```\n\n### Parameters\n\n| Parameter | Required | Default | Description |\n|-----------|----------|---------|-------------|\n| `--prompt` | Yes | — | Task description for Claude Code |\n| `--workdir` | Yes | — | Working directory (must exist) |\n| `--model` | No | `sonnet` | Model: `sonnet`, `opus`, or `haiku` |\n| `--tools` | No | `Read,Edit,Glob,Grep` | Comma-separated allowed tools |\n| `--budget` | No | `2.00` | Max budget in USD (for cost reporting) |\n| `--timeout` | No | `300` | Timeout in seconds |\n| `--system` | No | — | Additional system prompt text |\n\n### Model Selection Guide\n\n- **sonnet** (default): Fast. Good for single-file fixes, simple refactors, code review, running tests.\n- **opus**: Slower but more capable. Use for complex multi-file debugging, architectural changes, tasks requiring deep reasoning across many files.\n- **haiku**: Fastest and cheapest. Use for trivial tasks like renaming, formatting, or simple lookups.\n\n### Tool Presets\n\nCommon tool combinations for different task types:\n\n- **Read-only** (code review, analysis): `Read,Glob,Grep`\n- **Standard editing** (default): `Read,Edit,Glob,Grep`\n- **Full access** (builds, tests, git): `Read,Edit,Glob,Grep,Bash`\n\n## Output Format\n\nThe script returns a structured summary:\n\n```\nSTATUS: success|failure\nMODEL: sonnet|opus|haiku\nCOST: $0.04\nDURATION: 12s\nRESULT: <Claude Code's response>\n```\n\nExit codes: 0 = success, 1 = Claude Code error, 2 = preflight failure, 3 = timeout.\n\n## Examples\n\n**Fix a build error:**\n```bash\nbash {baseDir}/scripts/invoke-claude.sh \\\n  --prompt \"The build is failing with 'Cannot find module ./utils'. Diagnose and fix.\" \\\n  --workdir \"/Users/dave/WebProjects/summer-camps\" \\\n  --tools \"Read,Edit,Glob,Grep,Bash\"\n```\n\n**Code review:**\n```bash\nbash {baseDir}/scripts/invoke-claude.sh \\\n  --prompt \"Review the changes in the last commit. Focus on correctness and security.\" \\\n  --workdir \"/Users/dave/WebProjects/summer-camps\" \\\n  --model opus \\\n  --tools \"Read,Glob,Grep,Bash\"\n```\n\n**Run tests and fix failures:**\n```bash\nbash {baseDir}/scripts/invoke-claude.sh \\\n  --prompt \"Run the test suite, then fix any failing tests.\" \\\n  --workdir \"/Users/dave/WebProjects/summer-camps\" \\\n  --tools \"Read,Edit,Glob,Grep,Bash\" \\\n  --timeout 600\n```\n\n## Limitations\n\n- **No concurrent invocations** to the same working directory. Queue tasks sequentially.\n- **No multi-turn conversations.** Each invocation is independent. For follow-up work, dispatch a new invocation with more context in the prompt.\n- **Result truncation.** Responses longer than 2000 characters are truncated at the nearest line boundary.\n\n## Notes\n\n- Cost is reported for observability. Subscription users are not charged per-token but the field shows what the task would cost on the API.\n- Claude Code inherits environment variables from the host, including any API keys loaded by `load-openclaw-env` or similar scripts.\n- The prompt is passed via stdin pipe, not shell interpolation, so special characters in prompts are safe.\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn7efj8ddecxgrrrs2kb7g7m3d826rjy\",\n  \"slug\": \"claude-code-dispatch\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1773571953478\n}\n\nFile v1.0.0:skill-card.md\n\n## Description:\n\nInvoke Claude Code CLI as a subprocess for coding tasks that require file access, editing, and shell execution.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[ezpeasydave](https://clawhub.ai/user/ezpeasydave)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and coding agents use this skill to delegate local coding tasks to an authenticated Claude Code CLI when work requires file access, file editing, shell command execution, tests, code review, or multi-file debugging.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Delegating local coding tasks can expose project data and local environment secrets to Claude Code.\n\nMitigation: Run the skill from an environment with only the credentials needed for the task, avoid passing secrets in prompts, and prefer read-only tool access for review work.\n\nRisk: Broad filesystem or shell access can modify files or execute commands beyond the intended task.\n\nMitigation: Use the narrowest Claude Code tool preset that works and pre-authorize only the required tools in Claude Code settings.\n\nRisk: Unpinned CLI dependencies can affect reproducibility across installs.\n\nMitigation: Pin or separately manage the Claude Code dependency when reproducible installs matter.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/ezpeasydave/skills/claude-code-dispatch)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Plain text structured summary with status, model, cost, duration, and result fields.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Results longer than 2000 characters are truncated at a line boundary.]\n\n## Skill Version(s):\n\n1.0.0 (source: SKILL.md frontmatter and server release evidence)\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\nFile v1.0.0:.clawhub/origin.json\n\n{\n  \"version\": 1,\n  \"registry\": \"https://clawhub.ai\",\n  \"slug\": \"claude-code-dispatch\",\n  \"installedVersion\": null,\n  \"installedAt\": null\n}","readmeExcerpt":"Skill: Claude Code Dispatch Owner: ezpeasydave Summary: Invoke Claude Code CLI as a subprocess for coding tasks that require file access, editing, and shell execution Tags: latest:1.0.0 Version history: v1.0.0 | 2026-03-15T10:52:33.478Z | user - Initial release of claude-code-dispatch skill. - Enables delegating coding tasks to Claude Code CLI for operations requiring file access, editing, and shell command execution","codeSnippets":[],"executableExamples":[{"language":"json","snippet":"{\n  \"permissions\": {\n    \"allow\": [\n      \"Read\",\n      \"Edit\",\n      \"Glob\",\n      \"Grep\",\n      \"Bash(git:*)\",\n      \"Bash(npm:*)\"\n    ]\n  }\n}"},{"language":"bash","snippet":"bash {baseDir}/scripts/invoke-claude.sh \\\n  --prompt \"Fix the broken import in src/App.tsx\" \\\n  --workdir \"/path/to/project\" \\\n  --model sonnet \\\n  --tools \"Read,Edit,Glob,Grep,Bash\""},{"language":"text","snippet":"STATUS: success|failure\nMODEL: sonnet|opus|haiku\nCOST: $0.04\nDURATION: 12s\nRESULT: <Claude Code's response>"},{"language":"bash","snippet":"bash {baseDir}/scripts/invoke-claude.sh \\\n  --prompt \"The build is failing with 'Cannot find module ./utils'. Diagnose and fix.\" \\\n  --workdir \"/Users/dave/WebProjects/summer-camps\" \\\n  --tools \"Read,Edit,Glob,Grep,Bash\""},{"language":"bash","snippet":"bash {baseDir}/scripts/invoke-claude.sh \\\n  --prompt \"Review the changes in the last commit. Focus on correctness and security.\" \\\n  --workdir \"/Users/dave/WebProjects/summer-camps\" \\\n  --model opus \\\n  --tools \"Read,Glob,Grep,Bash\""},{"language":"bash","snippet":"bash {baseDir}/scripts/invoke-claude.sh \\\n  --prompt \"Run the test suite, then fix any failing tests.\" \\\n  --workdir \"/Users/dave/WebProjects/summer-camps\" \\\n  --tools \"Read,Edit,Glob,Grep,Bash\" \\\n  --timeout 600"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: claude-code-dispatch\ndescription: Invoke Claude Code CLI as a subprocess for coding tasks that require file access, editing, and shell execution\nversion: 1.0.0\nauthor: Claude Code (Anthropic)\ntriggers:\n  - \"use claude code\"\n  - \"have claude fix\"\n  - \"claude code task\"\n  - \"run claude on\"\n  - \"send this to claude code\"\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"claude\",\"jq\"]},\"install\":[{\"id\":\"claude\",\"kind\":\"npm\",\"package\":\"@anthropic-ai/claude-code\",\"bins\":[\"claude\"],\"label\":\"Install Claude Code (npm)\"},{\"id\":\"jq\",\"kind\":\"brew\",\"formula\":\"jq\",\"bins\":[\"jq\"],\"label\":\"Install jq (brew)\"}]}}\n---\n\n# Claude Code Dispatch\n\nDelegate coding tasks to Claude Code CLI. Use this when a task requires capabilities beyond what the current agent can do: file editing, shell commands, multi-file debugging, code review with file access, or any work that needs direct filesystem interaction.\n\n## Prerequisites\n\nClaude Code must be installed and authenticated on the host machine. The host's `~/.claude/settings.json` must pre-authorize the tools this skill will use. Example minimal config:\n\n```json\n{\n  \"permissions\": {\n    \"allow\": [\n      \"Read\",\n      \"Edit\",\n      \"Glob\",\n      \"Grep\",\n      \"Bash(git:*)\",\n      \"Bash(npm:*)\"\n    ]\n  }\n}\n```\n\nWithout pre-authorized permissions, Claude Code will fail in non-interactive mode because it cannot prompt for approval.\n\n## When to Use\n\nRoute tasks to Claude Code when they require:\n- File reading, editing, or creation on the host filesystem\n- Shell command execution (builds, tests, git operations)\n- Multi-file debugging or refactoring\n- Code review with actual file access\n- Any task where the agent needs to interact with the local filesystem\n\nDo NOT use when:\n- The task is purely conversational (answering questions, planning)\n- You can handle it with your own capabilities or other skills\n- The task involves external APIs you already have access to\n\n## Usage\n\n```bash\nbash {baseDir}/scripts/invoke-claude.sh \\\n  --prompt \"Fix the broken import in src/App.tsx\" \\\n  --workdir \"/path/to/project\" \\\n  --model sonnet \\\n  --tools \"Read,Edit,Glob,Grep,Bash\"\n```\n\n### Parameters\n\n| Parameter | Required | Default | Description |\n|-----------|----------|---------|-------------|\n| `--prompt` | Yes | — | Task description for Claude Code |\n| `--workdir` | Yes | — | Working directory (must exist) |\n| `--model` | No | `sonnet` | Model: `sonnet`, `opus`, or `haiku` |\n| `--tools` | No | `Read,Edit,Glob,Grep` | Comma-separated allowed tools |\n| `--budget` | No | `2.00` | Max budget in USD (for cost reporting) |\n| `--timeout` | No | `300` | Timeout in seconds |\n| `--system` | No | — | Additional system prompt text |\n\n### Model Selection Guide\n\n- **sonnet** (default): Fast. Good for single-file fixes, simple refactors, code review, running tests.\n- **opus**: Slower but more capable. Use for complex multi-file debugging, architectural changes, tasks requiring deep reasoning across many files.\n- **haiku**: Fastest and cheapest. U"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7efj8ddecxgrrrs2kb7g7m3d826rjy\",\n  \"slug\": \"claude-code-dispatch\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1773571953478\n}"},{"path":"skill-card.md","content":"## Description:\n\nInvoke Claude Code CLI as a subprocess for coding tasks that require file access, editing, and shell execution.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[ezpeasydave](https://clawhub.ai/user/ezpeasydave)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and coding agents use this skill to delegate local coding tasks to an authenticated Claude Code CLI when work requires file access, file editing, shell command execution, tests, code review, or multi-file debugging.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Delegating local coding tasks can expose project data and local environment secrets to Claude Code.\n\nMitigation: Run the skill from an environment with only the credentials needed for the task, avoid passing secrets in prompts, and prefer read-only tool access for review work.\n\nRisk: Broad filesystem or shell access can modify files or execute commands beyond the intended task.\n\nMitigation: Use the narrowest Claude Code tool preset that works and pre-authorize only the required tools in Claude Code settings.\n\nRisk: Unpinned CLI dependencies can affect reproducibility across installs.\n\nMitigation: Pin or separately manage the Claude Code dependency when reproducible installs matter.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/ezpeasydave/skills/claude-code-dispatch)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Plain text structured summary with status, model, cost, duration, and result fields.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Results longer than 2000 characters are truncated at a line boundary.]\n\n## Skill Version(s):\n\n1.0.0 (source: SKILL.md frontmatter and server release evidence)\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."},{"path":".clawhub/origin.json","content":"{\n  \"version\": 1,\n  \"registry\": \"https://clawhub.ai\",\n  \"slug\": \"claude-code-dispatch\",\n  \"installedVersion\": null,\n  \"installedAt\": null\n}"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Invoke Claude Code CLI as a subprocess for coding tasks that require file access, editing, and shell execution Skill: Claude Code Dispatch Owner: ezpeasydave Summary: Invoke Claude Code CLI as a subprocess for coding tasks that require file access, editing, and shell execution Tags: latest:1.0.0 Version history: v1.0.0 | 2026-03-15T10:52:33.478Z | user - Initial release of claude-code-dispatch skill. - Enables delegating coding tasks to Claude Code CLI for operations requiring file access, editing, and shell command execution","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1114,"uniquenessScore":49,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-10T11:57:59.533Z","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":"2026-10-10T11:57:59.533Z","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":"2026-10-10T14:42:33.264Z","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"}]}}}