{"id":"f2a0a91b-7050-43a7-9be0-9dccfdf5c3e2","entityType":"agent","slug":"clawhub-dietrichgebert-ponytail-help","name":"ponytail-help","canonicalUrl":"https://www.xpersona.co/agent/clawhub-dietrichgebert-ponytail-help","canonicalPath":"/agent/clawhub-dietrichgebert-ponytail-help","generatedAt":"2026-10-10T10:43:48.449Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-10T08:24:58.682Z","emptyReason":null},"description":"Quick reference for ponytail's modes, skills, and commands. One-shot display. Skill: ponytail-help Owner: dietrichgebert Summary: Quick reference for ponytail's modes, skills, and commands. One-shot display. Tags: latest:5.1.0 Version history: v5.1.0 | 2026-10-08T16:21:21.522Z | auto - Updated SKILL.md to clarify level and skill descriptions for greater accuracy and detail. - Improved the definitions for each mode (\"lite\", \"full\", \"ultra\") and their triggers. - Expanded skill explanations, esp","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.6K downloads reported by the source. Last updated 10/10/2026.","installCommand":"clawhub skill install s17beee6vfcnpy9kq5vh15rzzh88rnca:ponytail-help","sourceUrl":"https://clawhub.ai/dietrichgebert/ponytail-help","homepage":"https://clawhub.ai/dietrichgebert/skills/ponytail-help","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/dietrichgebert/ponytail-help","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/dietrichgebert/skills/ponytail-help","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":64,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Quick reference for ponytail's modes, skills, and commands. One-shot display. Skill: ponytail-help Owner: dietrichgebert Summary: Quick reference for ponytail's"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-10T08:24:58.682Z","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":"2026-10-10T08:24:58.682Z","emptyReason":null},"stars":null,"forks":null,"downloads":1559,"packageName":null,"latestVersion":"5.1.0","tractionLabel":"1.6K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T08:24:58.682Z","emptyReason":null},"lastUpdatedAt":"2026-10-10T08:24:58.682Z","lastCrawledAt":"2026-10-10T08:24:58.682Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-11T08:24:58.682Z","lastVerifiedAt":null,"highlights":[{"version":"5.1.0","createdAt":"2026-10-08T16:21:21.522Z","changelog":"- Updated SKILL.md to clarify level and skill descriptions for greater accuracy and detail. - Improved the definitions for each mode (\"lite\", \"full\", \"ultra\") and their triggers. - Expanded skill explanations, especially for review and audit commands. - Adjusted instructions and terminology for clarity (e.g., \"YAGNI\" references removed). - Removed the redundant skill-card.md file.","fileCount":3,"zipByteSize":2666},{"version":"4.13.0","createdAt":"2026-10-05T18:57:57.795Z","changelog":"- Updated skill invocation instructions: Codex CLI and IDE extension now use $ponytail:ponytail instead of $ponytail, and similarly for other skills. - Removed the file skill-card.md.","fileCount":3,"zipByteSize":2663},{"version":"4.12.0","createdAt":"2026-10-05T03:45:28.286Z","changelog":"- Removed the skill-card.md file. - No changes to functionality or the main help documentation.","fileCount":3,"zipByteSize":2617},{"version":"4.11.0","createdAt":"2026-10-04T22:56:23.248Z","changelog":"- Updated skill invocation instructions: Codex CLI and IDE extension now use $ponytail commands. - Clarified which platforms use slash-command vs dollar-sign command forms. - Removed the redundant skill-card.md file.","fileCount":3,"zipByteSize":2697},{"version":"4.10.3","createdAt":"2026-10-03T02:37:17.191Z","changelog":"- Removed the skill-card.md file. - No changes to functionality or documentation in SKILL.md.","fileCount":3,"zipByteSize":2648},{"version":"4.10.2","createdAt":"2026-10-03T01:32:33.865Z","changelog":"- Removed the file skill-card.md. - No user-facing features or functionality were changed.","fileCount":3,"zipByteSize":2668},{"version":"4.10.1","createdAt":"2026-10-02T15:12:53.960Z","changelog":"- Removed the file skill-card.md. - No changes to documentation or features in SKILL.md. - No other functional updates in this version.","fileCount":3,"zipByteSize":2599},{"version":"4.9.0","createdAt":"2026-08-07T21:16:50.276Z","changelog":"- Expanded the skills list: added `/ponytail-audit` (whole-repo audit) and `/ponytail-debt` (debt tracking) commands. - Clarified that OpenCode now supports all six slash commands. - Removed the redundant skill-card.md file.","fileCount":3,"zipByteSize":2756}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17beee6vfcnpy9kq5vh15rzzh88rnca:ponytail-help","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-dietrichgebert-ponytail-help/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dietrichgebert-ponytail-help/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dietrichgebert-ponytail-help/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dietrichgebert-ponytail-help/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dietrichgebert-ponytail-help/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dietrichgebert-ponytail-help/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T10:43:48.448Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dietrichgebert-ponytail-help/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dietrichgebert-ponytail-help/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dietrichgebert-ponytail-help/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dietrichgebert-ponytail-help/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":"2026-10-10T08:24:58.682Z","emptyReason":null},"readme":"Skill: ponytail-help\n\nOwner: dietrichgebert\n\nSummary: Quick reference for ponytail's modes, skills, and commands. One-shot display.\n\nTags: latest:5.1.0\n\nVersion history:\n\nv5.1.0 | 2026-10-08T16:21:21.522Z | auto\n\n- Updated SKILL.md to clarify level and skill descriptions for greater accuracy and detail.\n- Improved the definitions for each mode (\"lite\", \"full\", \"ultra\") and their triggers.\n- Expanded skill explanations, especially for review and audit commands.\n- Adjusted instructions and terminology for clarity (e.g., \"YAGNI\" references removed).\n- Removed the redundant skill-card.md file.\n\nv4.13.0 | 2026-10-05T18:57:57.795Z | auto\n\n- Updated skill invocation instructions: Codex CLI and IDE extension now use $ponytail:ponytail instead of $ponytail, and similarly for other skills.\n- Removed the file skill-card.md.\n\nv4.12.0 | 2026-10-05T03:45:28.286Z | auto\n\n- Removed the skill-card.md file.\n- No changes to functionality or the main help documentation.\n\nv4.11.0 | 2026-10-04T22:56:23.248Z | auto\n\n- Updated skill invocation instructions: Codex CLI and IDE extension now use $ponytail commands.\n- Clarified which platforms use slash-command vs dollar-sign command forms.\n- Removed the redundant skill-card.md file.\n\nv4.10.3 | 2026-10-03T02:37:17.191Z | auto\n\n- Removed the skill-card.md file.  \n- No changes to functionality or documentation in SKILL.md.\n\nv4.10.2 | 2026-10-03T01:32:33.865Z | auto\n\n- Removed the file skill-card.md.\n- No user-facing features or functionality were changed.\n\nv4.10.1 | 2026-10-02T15:12:53.960Z | auto\n\n- Removed the file skill-card.md.\n- No changes to documentation or features in SKILL.md.\n- No other functional updates in this version.\n\nv4.9.0 | 2026-08-07T21:16:50.276Z | auto\n\n- Expanded the skills list: added `/ponytail-audit` (whole-repo audit) and `/ponytail-debt` (debt tracking) commands.\n- Clarified that OpenCode now supports all six slash commands.\n- Removed the redundant skill-card.md file.\n\nv4.8.4 | 2026-06-29T05:34:40.946Z | auto\n\n- Removed the skill reference file skill-card.md.\n- No changes to skill functionality or documentation.\n- Skill documentation and help remain available in SKILL.md.\n\nv4.8.3 | 2026-06-24T02:37:24.536Z | auto\n\n- Removed the sample reference card file skill-card.md from the project.\n- No changes to the help content or commands; all core features remain the same.\n\nv4.8.1 | 2026-06-23T21:02:03.660Z | auto\n\n- Improved reference card with concise descriptions for all ponytail modes, skills, and commands.\n- Added clear tables detailing mode triggers, what each level does, and all available skills.\n- Included instructions for deactivation and changing the default mode via environment variable or config file.\n- Updated auto-update and manual update instructions for different hosts.\n- Linked to full documentation for further information.\n\nArchive index:\n\nArchive v5.1.0: 3 files, 2666 bytes\n\nFiles: skill-card.md (1556b), SKILL.md (2899b), _meta.json (132b)\n\nFile v5.1.0:SKILL.md\n\n---\nname: ponytail-help\ndescription: \"Quick reference for ponytail's modes, skills, and commands. One-shot display.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\n# Ponytail Help\n\nDisplay this reference card when invoked. One-shot, do NOT change mode,\nwrite flag files, or persist anything.\n\n## Levels\n\n| Level | Trigger | What change |\n|-------|---------|-------------|\n| **Lite** | `/ponytail lite` | Build what was asked, name the smaller option in one line. |\n| **Full** | `/ponytail` | The smallest complete change, a check where the logic needs one, and a reply that names what was skipped and any risk. Default. |\n| **Ultra** | `/ponytail ultra` | Also questions the request and pushes back before building. |\n\nLevel sticks until changed or session end.\n\n## Skills\n\n| Skill | Trigger | What it does |\n|-------|---------|--------------|\n| **ponytail** | `/ponytail` | Lazy mode itself: least new code, clear replies that name skipped work and risks. |\n| **ponytail-review** | `/ponytail-review` | Quality review of a diff: bugs, security, load, missing tests, speed, what to cut. Each finding says what goes wrong and how to fix it. |\n| **ponytail-audit** | `/ponytail-audit` | The same quality review for the whole repo, ranked. |\n| **ponytail-debt** | `/ponytail-debt` | Harvest `shortcut:` comments into a tracked ledger. |\n| **ponytail-gain** | `/ponytail-gain` | Measured-impact scoreboard: less code, less cost, more speed. |\n| **ponytail-help** | `/ponytail-help` | This card. |\n\nIn Codex CLI and the IDE extension, invoke skills with `$ponytail:ponytail`,\n`$ponytail:ponytail-review`, or `$ponytail:ponytail-help`. Claude Code and OpenCode use the\nslash-command forms above (OpenCode ships all six as slash commands).\n\n## Deactivate\n\nSay \"stop ponytail\" or \"normal mode\". Resume anytime with `/ponytail`.\n`/ponytail off` also works.\n\n## Configure Default Mode\n\nDefault mode = `full`, auto-active every session. Change it:\n\n**Environment variable** (highest priority):\n```bash\nexport PONYTAIL_DEFAULT_MODE=ultra\n```\n\n**Config file** (`~/.config/ponytail/config.json`, Windows: `%APPDATA%\\ponytail\\config.json`):\n```json\n{ \"defaultMode\": \"lite\" }\n```\n\nSet `\"off\"` to disable auto-activation on session start, activate manually\nwith `/ponytail` when wanted.\n\nResolution: env var > config file > `full`.\n\n## Update\n\nEnable auto-update once: open `/plugin`, go to Marketplaces, pick ponytail, Enable auto-update. Claude Code then pulls new versions at startup (run `/reload-plugins` when it prompts). Manual refresh: `/plugin marketplace update ponytail` then `/reload-plugins`.\n\nIf `/plugin` is not recognized, your Claude Code is out of date. Update it (`npm install -g @anthropic-ai/claude-code@latest`, or `brew upgrade claude-code`) and restart. Other hosts use their own update flow.\n\n## More\n\nFull docs + examples: https://github.com/DietrichGebert/ponytail\n\nFile v5.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-help\",\n  \"version\": \"5.1.0\",\n  \"publishedAt\": 1791476481522\n}\n\nFile v5.1.0:skill-card.md\n\n## Description:\n\nQuick reference for ponytail's modes, skills, and commands. One-shot display.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dietrichgebert](https://clawhub.ai/user/dietrichgebert)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and other Ponytail users can display a quick reference to its modes, available skills, configuration options, and update commands.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Running the documented update or configuration commands may change local tooling or defaults.\n\nMitigation: Review the commands and settings before applying them; displaying this help card does not execute them.\n\n## Reference(s):\n\n- [Ponytail documentation and examples](https://github.com/DietrichGebert/ponytail)\n- [Ponytail Help on ClawHub](https://clawhub.ai/dietrichgebert/skills/ponytail-help)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Guidance, Shell commands, Configuration instructions]\n\n**Output Format:** [Markdown reference card with example commands and configuration]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [One-shot display; does not change settings or run commands.]\n\n## Skill Version(s):\n\n5.1.0 (source: ClawHub 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 v4.13.0: 3 files, 2663 bytes\n\nFiles: skill-card.md (1544b), SKILL.md (2803b), _meta.json (133b)\n\nFile v4.13.0:SKILL.md\n\n---\nname: ponytail-help\ndescription: \"Quick reference for ponytail's modes, skills, and commands. One-shot display.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\n# Ponytail Help\n\nDisplay this reference card when invoked. One-shot, do NOT change mode,\nwrite flag files, or persist anything.\n\n## Levels\n\n| Level | Trigger | What change |\n|-------|---------|-------------|\n| **Lite** | `/ponytail lite` | Build what's asked, name the lazier alternative in one line. |\n| **Full** | `/ponytail` | The ladder enforced: YAGNI → stdlib → native → one line → minimum. Default. |\n| **Ultra** | `/ponytail ultra` | YAGNI extremist. Deletion before addition. Challenges requirements before building. |\n\nLevel sticks until changed or session end.\n\n## Skills\n\n| Skill | Trigger | What it does |\n|-------|---------|--------------|\n| **ponytail** | `/ponytail` | Lazy mode itself. Simplest solution that works. |\n| **ponytail-review** | `/ponytail-review` | Over-engineering review: `L42: yagni: factory, one product. Inline.` |\n| **ponytail-audit** | `/ponytail-audit` | Whole-repo over-engineering audit: ranked list of what to delete. |\n| **ponytail-debt** | `/ponytail-debt` | Harvest `ponytail:` shortcut comments into a tracked ledger. |\n| **ponytail-gain** | `/ponytail-gain` | Measured-impact scoreboard: less code, less cost, more speed. |\n| **ponytail-help** | `/ponytail-help` | This card. |\n\nIn Codex CLI and the IDE extension, invoke skills with `$ponytail:ponytail`,\n`$ponytail:ponytail-review`, or `$ponytail:ponytail-help`. Claude Code and OpenCode use the\nslash-command forms above (OpenCode ships all six as slash commands).\n\n## Deactivate\n\nSay \"stop ponytail\" or \"normal mode\". Resume anytime with `/ponytail`.\n`/ponytail off` also works.\n\n## Configure Default Mode\n\nDefault mode = `full`, auto-active every session. Change it:\n\n**Environment variable** (highest priority):\n```bash\nexport PONYTAIL_DEFAULT_MODE=ultra\n```\n\n**Config file** (`~/.config/ponytail/config.json`, Windows: `%APPDATA%\\ponytail\\config.json`):\n```json\n{ \"defaultMode\": \"lite\" }\n```\n\nSet `\"off\"` to disable auto-activation on session start, activate manually\nwith `/ponytail` when wanted.\n\nResolution: env var > config file > `full`.\n\n## Update\n\nEnable auto-update once: open `/plugin`, go to Marketplaces, pick ponytail, Enable auto-update. Claude Code then pulls new versions at startup (run `/reload-plugins` when it prompts). Manual refresh: `/plugin marketplace update ponytail` then `/reload-plugins`.\n\nIf `/plugin` is not recognized, your Claude Code is out of date. Update it (`npm install -g @anthropic-ai/claude-code@latest`, or `brew upgrade claude-code`) and restart. Other hosts use their own update flow.\n\n## More\n\nFull docs + examples: https://github.com/DietrichGebert/ponytail\n\nFile v4.13.0:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-help\",\n  \"version\": \"4.13.0\",\n  \"publishedAt\": 1791226677795\n}\n\nFile v4.13.0:skill-card.md\n\n## Description:\n\nQuick reference for ponytail's modes, skills, and commands. One-shot display.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dietrichgebert](https://clawhub.ai/user/dietrichgebert)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers use this one-shot reference to look up Ponytail's modes, skill commands, deactivation, and configuration options without changing their current mode.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The help card describes host auto-update and global package-manager update options that can change the local environment if followed.\n\nMitigation: Review update and default-mode configuration options before using them; enable auto-update or run global updates only when intended.\n\n## Reference(s):\n\n- [Ponytail documentation](https://github.com/DietrichGebert/ponytail)\n- [Ponytail Help on ClawHub](https://clawhub.ai/dietrichgebert/skills/ponytail-help)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Guidance]\n\n**Output Format:** [Markdown reference card]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [One-shot display; does not change mode or persist files.]\n\n## Skill Version(s):\n\n4.13.0 (source: 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 v4.12.0: 3 files, 2617 bytes\n\nFiles: skill-card.md (1454b), SKILL.md (2776b), _meta.json (133b)\n\nFile v4.12.0:SKILL.md\n\n---\nname: ponytail-help\ndescription: \"Quick reference for ponytail's modes, skills, and commands. One-shot display.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\n# Ponytail Help\n\nDisplay this reference card when invoked. One-shot, do NOT change mode,\nwrite flag files, or persist anything.\n\n## Levels\n\n| Level | Trigger | What change |\n|-------|---------|-------------|\n| **Lite** | `/ponytail lite` | Build what's asked, name the lazier alternative in one line. |\n| **Full** | `/ponytail` | The ladder enforced: YAGNI → stdlib → native → one line → minimum. Default. |\n| **Ultra** | `/ponytail ultra` | YAGNI extremist. Deletion before addition. Challenges requirements before building. |\n\nLevel sticks until changed or session end.\n\n## Skills\n\n| Skill | Trigger | What it does |\n|-------|---------|--------------|\n| **ponytail** | `/ponytail` | Lazy mode itself. Simplest solution that works. |\n| **ponytail-review** | `/ponytail-review` | Over-engineering review: `L42: yagni: factory, one product. Inline.` |\n| **ponytail-audit** | `/ponytail-audit` | Whole-repo over-engineering audit: ranked list of what to delete. |\n| **ponytail-debt** | `/ponytail-debt` | Harvest `ponytail:` shortcut comments into a tracked ledger. |\n| **ponytail-gain** | `/ponytail-gain` | Measured-impact scoreboard: less code, less cost, more speed. |\n| **ponytail-help** | `/ponytail-help` | This card. |\n\nIn Codex CLI and the IDE extension, invoke skills with `$ponytail`,\n`$ponytail-review`, or `$ponytail-help`. Claude Code and OpenCode use the\nslash-command forms above (OpenCode ships all six as slash commands).\n\n## Deactivate\n\nSay \"stop ponytail\" or \"normal mode\". Resume anytime with `/ponytail`.\n`/ponytail off` also works.\n\n## Configure Default Mode\n\nDefault mode = `full`, auto-active every session. Change it:\n\n**Environment variable** (highest priority):\n```bash\nexport PONYTAIL_DEFAULT_MODE=ultra\n```\n\n**Config file** (`~/.config/ponytail/config.json`, Windows: `%APPDATA%\\ponytail\\config.json`):\n```json\n{ \"defaultMode\": \"lite\" }\n```\n\nSet `\"off\"` to disable auto-activation on session start, activate manually\nwith `/ponytail` when wanted.\n\nResolution: env var > config file > `full`.\n\n## Update\n\nEnable auto-update once: open `/plugin`, go to Marketplaces, pick ponytail, Enable auto-update. Claude Code then pulls new versions at startup (run `/reload-plugins` when it prompts). Manual refresh: `/plugin marketplace update ponytail` then `/reload-plugins`.\n\nIf `/plugin` is not recognized, your Claude Code is out of date. Update it (`npm install -g @anthropic-ai/claude-code@latest`, or `brew upgrade claude-code`) and restart. Other hosts use their own update flow.\n\n## More\n\nFull docs + examples: https://github.com/DietrichGebert/ponytail\n\nFile v4.12.0:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-help\",\n  \"version\": \"4.12.0\",\n  \"publishedAt\": 1791171928286\n}\n\nFile v4.12.0:skill-card.md\n\n## Description:\n\nDisplays a one-shot reference to Ponytail's modes, skills, and commands.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dietrichgebert](https://clawhub.ai/user/dietrichgebert)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and other Ponytail users can quickly look up its modes, skill commands, deactivation, and optional configuration or update steps.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Optional configuration or update commands may enable broader Ponytail behavior.\n\nMitigation: Review the linked project and run those commands only if you want those behaviors.\n\n## Reference(s):\n\n- [Ponytail project documentation](https://github.com/DietrichGebert/ponytail)\n- [Ponytail Help on ClawHub](https://clawhub.ai/dietrichgebert/skills/ponytail-help)\n\n## Skill Output:\n\n**Output Type(s):** [Markdown, Guidance]\n\n**Output Format:** [Markdown reference card with tables and command examples]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [One-shot display; no automatic file changes or persistence.]\n\n## Skill Version(s):\n\n4.12.0 (source: ClawHub 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 v4.11.0: 3 files, 2697 bytes\n\nFiles: skill-card.md (1720b), SKILL.md (2776b), _meta.json (133b)\n\nFile v4.11.0:SKILL.md\n\n---\nname: ponytail-help\ndescription: \"Quick reference for ponytail's modes, skills, and commands. One-shot display.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\n# Ponytail Help\n\nDisplay this reference card when invoked. One-shot, do NOT change mode,\nwrite flag files, or persist anything.\n\n## Levels\n\n| Level | Trigger | What change |\n|-------|---------|-------------|\n| **Lite** | `/ponytail lite` | Build what's asked, name the lazier alternative in one line. |\n| **Full** | `/ponytail` | The ladder enforced: YAGNI → stdlib → native → one line → minimum. Default. |\n| **Ultra** | `/ponytail ultra` | YAGNI extremist. Deletion before addition. Challenges requirements before building. |\n\nLevel sticks until changed or session end.\n\n## Skills\n\n| Skill | Trigger | What it does |\n|-------|---------|--------------|\n| **ponytail** | `/ponytail` | Lazy mode itself. Simplest solution that works. |\n| **ponytail-review** | `/ponytail-review` | Over-engineering review: `L42: yagni: factory, one product. Inline.` |\n| **ponytail-audit** | `/ponytail-audit` | Whole-repo over-engineering audit: ranked list of what to delete. |\n| **ponytail-debt** | `/ponytail-debt` | Harvest `ponytail:` shortcut comments into a tracked ledger. |\n| **ponytail-gain** | `/ponytail-gain` | Measured-impact scoreboard: less code, less cost, more speed. |\n| **ponytail-help** | `/ponytail-help` | This card. |\n\nIn Codex CLI and the IDE extension, invoke skills with `$ponytail`,\n`$ponytail-review`, or `$ponytail-help`. Claude Code and OpenCode use the\nslash-command forms above (OpenCode ships all six as slash commands).\n\n## Deactivate\n\nSay \"stop ponytail\" or \"normal mode\". Resume anytime with `/ponytail`.\n`/ponytail off` also works.\n\n## Configure Default Mode\n\nDefault mode = `full`, auto-active every session. Change it:\n\n**Environment variable** (highest priority):\n```bash\nexport PONYTAIL_DEFAULT_MODE=ultra\n```\n\n**Config file** (`~/.config/ponytail/config.json`, Windows: `%APPDATA%\\ponytail\\config.json`):\n```json\n{ \"defaultMode\": \"lite\" }\n```\n\nSet `\"off\"` to disable auto-activation on session start, activate manually\nwith `/ponytail` when wanted.\n\nResolution: env var > config file > `full`.\n\n## Update\n\nEnable auto-update once: open `/plugin`, go to Marketplaces, pick ponytail, Enable auto-update. Claude Code then pulls new versions at startup (run `/reload-plugins` when it prompts). Manual refresh: `/plugin marketplace update ponytail` then `/reload-plugins`.\n\nIf `/plugin` is not recognized, your Claude Code is out of date. Update it (`npm install -g @anthropic-ai/claude-code@latest`, or `brew upgrade claude-code`) and restart. Other hosts use their own update flow.\n\n## More\n\nFull docs + examples: https://github.com/DietrichGebert/ponytail\n\nFile v4.11.0:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-help\",\n  \"version\": \"4.11.0\",\n  \"publishedAt\": 1791154583248\n}\n\nFile v4.11.0:skill-card.md\n\n## Description:\n\nQuick reference for Ponytail's modes, skills, and commands, displayed on request.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dietrichgebert](https://clawhub.ai/user/dietrichgebert)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nPonytail users can display a one-shot reference to its modes, skill commands, default-mode settings, and update options without changing their active mode or configuration.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Enabling auto-update may introduce future changes to the Ponytail project.\n\nMitigation: Review the linked project and update instructions before opting into auto-update.\n\nRisk: Changing the default mode can affect behavior in later sessions.\n\nMitigation: Review the default-mode instructions before changing environment variables or configuration.\n\n## Reference(s):\n\n- [Ponytail project and documentation](https://github.com/DietrichGebert/ponytail)\n- [Ponytail Help on ClawHub](https://clawhub.ai/dietrichgebert/skills/ponytail-help)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Shell commands, Configuration guidance]\n\n**Output Format:** [Markdown reference card with command and configuration examples]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [One-shot display; does not change modes, write files, or execute commands.]\n\n## Skill Version(s):\n\n4.11.0 (source: ClawHub release)\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 v4.10.3: 3 files, 2648 bytes\n\nFiles: skill-card.md (1588b), SKILL.md (2733b), _meta.json (133b)\n\nFile v4.10.3:SKILL.md\n\n---\nname: ponytail-help\ndescription: \"Quick reference for ponytail's modes, skills, and commands. One-shot display.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\n# Ponytail Help\n\nDisplay this reference card when invoked. One-shot, do NOT change mode,\nwrite flag files, or persist anything.\n\n## Levels\n\n| Level | Trigger | What change |\n|-------|---------|-------------|\n| **Lite** | `/ponytail lite` | Build what's asked, name the lazier alternative in one line. |\n| **Full** | `/ponytail` | The ladder enforced: YAGNI → stdlib → native → one line → minimum. Default. |\n| **Ultra** | `/ponytail ultra` | YAGNI extremist. Deletion before addition. Challenges requirements before building. |\n\nLevel sticks until changed or session end.\n\n## Skills\n\n| Skill | Trigger | What it does |\n|-------|---------|--------------|\n| **ponytail** | `/ponytail` | Lazy mode itself. Simplest solution that works. |\n| **ponytail-review** | `/ponytail-review` | Over-engineering review: `L42: yagni: factory, one product. Inline.` |\n| **ponytail-audit** | `/ponytail-audit` | Whole-repo over-engineering audit: ranked list of what to delete. |\n| **ponytail-debt** | `/ponytail-debt` | Harvest `ponytail:` shortcut comments into a tracked ledger. |\n| **ponytail-gain** | `/ponytail-gain` | Measured-impact scoreboard: less code, less cost, more speed. |\n| **ponytail-help** | `/ponytail-help` | This card. |\n\nCodex uses `@ponytail`, `@ponytail-review`, and `@ponytail-help`; Claude Code\nand OpenCode use the slash-command forms above (OpenCode ships all six as\nslash commands).\n\n## Deactivate\n\nSay \"stop ponytail\" or \"normal mode\". Resume anytime with `/ponytail`.\n`/ponytail off` also works.\n\n## Configure Default Mode\n\nDefault mode = `full`, auto-active every session. Change it:\n\n**Environment variable** (highest priority):\n```bash\nexport PONYTAIL_DEFAULT_MODE=ultra\n```\n\n**Config file** (`~/.config/ponytail/config.json`, Windows: `%APPDATA%\\ponytail\\config.json`):\n```json\n{ \"defaultMode\": \"lite\" }\n```\n\nSet `\"off\"` to disable auto-activation on session start, activate manually\nwith `/ponytail` when wanted.\n\nResolution: env var > config file > `full`.\n\n## Update\n\nEnable auto-update once: open `/plugin`, go to Marketplaces, pick ponytail, Enable auto-update. Claude Code then pulls new versions at startup (run `/reload-plugins` when it prompts). Manual refresh: `/plugin marketplace update ponytail` then `/reload-plugins`.\n\nIf `/plugin` is not recognized, your Claude Code is out of date. Update it (`npm install -g @anthropic-ai/claude-code@latest`, or `brew upgrade claude-code`) and restart. Other hosts use their own update flow.\n\n## More\n\nFull docs + examples: https://github.com/DietrichGebert/ponytail\n\nFile v4.10.3:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-help\",\n  \"version\": \"4.10.3\",\n  \"publishedAt\": 1790995037191\n}\n\nFile v4.10.3:skill-card.md\n\n## Description:\n\nQuick reference for Ponytail's modes, skills, and commands.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dietrichgebert](https://clawhub.ai/user/dietrichgebert)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nPonytail users and developers consult this one-shot help card for mode commands, deactivation, default-mode configuration, and updates without changing the current mode.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Enabling default modes or auto-update in the broader Ponytail system can change agent behavior across sessions.\n\nMitigation: Review the broader Ponytail behavior before enabling these settings; this help card only displays instructions.\n\n## Reference(s):\n\n- [Ponytail documentation and examples](https://github.com/DietrichGebert/ponytail)\n- [Ponytail Help on ClawHub](https://clawhub.ai/dietrichgebert/skills/ponytail-help)\n\n## Skill Output:\n\n**Output Type(s):** [Markdown, Guidance, Shell commands, Configuration examples]\n\n**Output Format:** [Markdown reference card with inline commands and shell/JSON examples]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [One-shot display; does not change modes or persist settings.]\n\n## Skill Version(s):\n\n4.10.3 (source: server-resolved release)\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 v4.10.2: 3 files, 2668 bytes\n\nFiles: skill-card.md (1652b), SKILL.md (2733b), _meta.json (133b)\n\nFile v4.10.2:SKILL.md\n\n---\nname: ponytail-help\ndescription: \"Quick reference for ponytail's modes, skills, and commands. One-shot display.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\n# Ponytail Help\n\nDisplay this reference card when invoked. One-shot, do NOT change mode,\nwrite flag files, or persist anything.\n\n## Levels\n\n| Level | Trigger | What change |\n|-------|---------|-------------|\n| **Lite** | `/ponytail lite` | Build what's asked, name the lazier alternative in one line. |\n| **Full** | `/ponytail` | The ladder enforced: YAGNI → stdlib → native → one line → minimum. Default. |\n| **Ultra** | `/ponytail ultra` | YAGNI extremist. Deletion before addition. Challenges requirements before building. |\n\nLevel sticks until changed or session end.\n\n## Skills\n\n| Skill | Trigger | What it does |\n|-------|---------|--------------|\n| **ponytail** | `/ponytail` | Lazy mode itself. Simplest solution that works. |\n| **ponytail-review** | `/ponytail-review` | Over-engineering review: `L42: yagni: factory, one product. Inline.` |\n| **ponytail-audit** | `/ponytail-audit` | Whole-repo over-engineering audit: ranked list of what to delete. |\n| **ponytail-debt** | `/ponytail-debt` | Harvest `ponytail:` shortcut comments into a tracked ledger. |\n| **ponytail-gain** | `/ponytail-gain` | Measured-impact scoreboard: less code, less cost, more speed. |\n| **ponytail-help** | `/ponytail-help` | This card. |\n\nCodex uses `@ponytail`, `@ponytail-review`, and `@ponytail-help`; Claude Code\nand OpenCode use the slash-command forms above (OpenCode ships all six as\nslash commands).\n\n## Deactivate\n\nSay \"stop ponytail\" or \"normal mode\". Resume anytime with `/ponytail`.\n`/ponytail off` also works.\n\n## Configure Default Mode\n\nDefault mode = `full`, auto-active every session. Change it:\n\n**Environment variable** (highest priority):\n```bash\nexport PONYTAIL_DEFAULT_MODE=ultra\n```\n\n**Config file** (`~/.config/ponytail/config.json`, Windows: `%APPDATA%\\ponytail\\config.json`):\n```json\n{ \"defaultMode\": \"lite\" }\n```\n\nSet `\"off\"` to disable auto-activation on session start, activate manually\nwith `/ponytail` when wanted.\n\nResolution: env var > config file > `full`.\n\n## Update\n\nEnable auto-update once: open `/plugin`, go to Marketplaces, pick ponytail, Enable auto-update. Claude Code then pulls new versions at startup (run `/reload-plugins` when it prompts). Manual refresh: `/plugin marketplace update ponytail` then `/reload-plugins`.\n\nIf `/plugin` is not recognized, your Claude Code is out of date. Update it (`npm install -g @anthropic-ai/claude-code@latest`, or `brew upgrade claude-code`) and restart. Other hosts use their own update flow.\n\n## More\n\nFull docs + examples: https://github.com/DietrichGebert/ponytail\n\nFile v4.10.2:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-help\",\n  \"version\": \"4.10.2\",\n  \"publishedAt\": 1790991153865\n}\n\nFile v4.10.2:skill-card.md\n\n## Description:\n\nQuick reference for ponytail's modes, skills, and commands. One-shot display.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dietrichgebert](https://clawhub.ai/user/dietrichgebert)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers use this one-shot reference to find Ponytail modes, related skills, configuration options, and update instructions without activating a mode or changing settings.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Activating the separate Ponytail modes can change an agent's coding style.\n\nMitigation: Use this help card as a reference only; activate a mode separately when intended.\n\nRisk: Optional update commands may update external tooling.\n\nMitigation: Run update commands only when you intend to update that tooling.\n\n## Reference(s):\n\n- [Ponytail documentation and examples](https://github.com/DietrichGebert/ponytail)\n- [Ponytail Help on ClawHub](https://clawhub.ai/dietrichgebert/skills/ponytail-help)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Shell commands, Configuration guidance]\n\n**Output Format:** [Markdown reference card with shell and JSON examples]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [One-shot display; does not change mode or persist settings.]\n\n## Skill Version(s):\n\n4.10.2 (source: ClawHub 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\nArchive v4.10.1: 3 files, 2599 bytes\n\nFiles: skill-card.md (1506b), SKILL.md (2733b), _meta.json (133b)\n\nFile v4.10.1:SKILL.md\n\n---\nname: ponytail-help\ndescription: \"Quick reference for ponytail's modes, skills, and commands. One-shot display.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\n# Ponytail Help\n\nDisplay this reference card when invoked. One-shot, do NOT change mode,\nwrite flag files, or persist anything.\n\n## Levels\n\n| Level | Trigger | What change |\n|-------|---------|-------------|\n| **Lite** | `/ponytail lite` | Build what's asked, name the lazier alternative in one line. |\n| **Full** | `/ponytail` | The ladder enforced: YAGNI → stdlib → native → one line → minimum. Default. |\n| **Ultra** | `/ponytail ultra` | YAGNI extremist. Deletion before addition. Challenges requirements before building. |\n\nLevel sticks until changed or session end.\n\n## Skills\n\n| Skill | Trigger | What it does |\n|-------|---------|--------------|\n| **ponytail** | `/ponytail` | Lazy mode itself. Simplest solution that works. |\n| **ponytail-review** | `/ponytail-review` | Over-engineering review: `L42: yagni: factory, one product. Inline.` |\n| **ponytail-audit** | `/ponytail-audit` | Whole-repo over-engineering audit: ranked list of what to delete. |\n| **ponytail-debt** | `/ponytail-debt` | Harvest `ponytail:` shortcut comments into a tracked ledger. |\n| **ponytail-gain** | `/ponytail-gain` | Measured-impact scoreboard: less code, less cost, more speed. |\n| **ponytail-help** | `/ponytail-help` | This card. |\n\nCodex uses `@ponytail`, `@ponytail-review`, and `@ponytail-help`; Claude Code\nand OpenCode use the slash-command forms above (OpenCode ships all six as\nslash commands).\n\n## Deactivate\n\nSay \"stop ponytail\" or \"normal mode\". Resume anytime with `/ponytail`.\n`/ponytail off` also works.\n\n## Configure Default Mode\n\nDefault mode = `full`, auto-active every session. Change it:\n\n**Environment variable** (highest priority):\n```bash\nexport PONYTAIL_DEFAULT_MODE=ultra\n```\n\n**Config file** (`~/.config/ponytail/config.json`, Windows: `%APPDATA%\\ponytail\\config.json`):\n```json\n{ \"defaultMode\": \"lite\" }\n```\n\nSet `\"off\"` to disable auto-activation on session start, activate manually\nwith `/ponytail` when wanted.\n\nResolution: env var > config file > `full`.\n\n## Update\n\nEnable auto-update once: open `/plugin`, go to Marketplaces, pick ponytail, Enable auto-update. Claude Code then pulls new versions at startup (run `/reload-plugins` when it prompts). Manual refresh: `/plugin marketplace update ponytail` then `/reload-plugins`.\n\nIf `/plugin` is not recognized, your Claude Code is out of date. Update it (`npm install -g @anthropic-ai/claude-code@latest`, or `brew upgrade claude-code`) and restart. Other hosts use their own update flow.\n\n## More\n\nFull docs + examples: https://github.com/DietrichGebert/ponytail\n\nFile v4.10.1:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-help\",\n  \"version\": \"4.10.1\",\n  \"publishedAt\": 1790953973960\n}\n\nFile v4.10.1:skill-card.md\n\n## Description:\n\nQuick reference for ponytail's modes, skills, and commands. One-shot display.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dietrichgebert](https://clawhub.ai/user/dietrichgebert)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers using ponytail can display a quick reference to its modes, companion skills, commands, and configuration options without changing the current mode.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Enabling ponytail auto-update can change the broader plugin across sessions.\n\nMitigation: Review ponytail configuration and auto-update options separately before enabling them.\n\n## Reference(s):\n\n- [Ponytail documentation](https://github.com/DietrichGebert/ponytail)\n- [Ponytail Help on ClawHub](https://clawhub.ai/dietrichgebert/skills/ponytail-help)\n\n## Skill Output:\n\n**Output Type(s):** [Markdown, Configuration guidance, Shell commands]\n\n**Output Format:** [Markdown reference card with configuration and shell examples]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [One-shot display; does not change modes or persist settings.]\n\n## Skill Version(s):\n\n4.10.1 (source: ClawHub 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 v4.9.0: 3 files, 2756 bytes\n\nFiles: skill-card.md (1816b), SKILL.md (2733b), _meta.json (132b)\n\nFile v4.9.0:SKILL.md\n\n---\nname: ponytail-help\ndescription: \"Quick reference for ponytail's modes, skills, and commands. One-shot display.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\n# Ponytail Help\n\nDisplay this reference card when invoked. One-shot, do NOT change mode,\nwrite flag files, or persist anything.\n\n## Levels\n\n| Level | Trigger | What change |\n|-------|---------|-------------|\n| **Lite** | `/ponytail lite` | Build what's asked, name the lazier alternative in one line. |\n| **Full** | `/ponytail` | The ladder enforced: YAGNI → stdlib → native → one line → minimum. Default. |\n| **Ultra** | `/ponytail ultra` | YAGNI extremist. Deletion before addition. Challenges requirements before building. |\n\nLevel sticks until changed or session end.\n\n## Skills\n\n| Skill | Trigger | What it does |\n|-------|---------|--------------|\n| **ponytail** | `/ponytail` | Lazy mode itself. Simplest solution that works. |\n| **ponytail-review** | `/ponytail-review` | Over-engineering review: `L42: yagni: factory, one product. Inline.` |\n| **ponytail-audit** | `/ponytail-audit` | Whole-repo over-engineering audit: ranked list of what to delete. |\n| **ponytail-debt** | `/ponytail-debt` | Harvest `ponytail:` shortcut comments into a tracked ledger. |\n| **ponytail-gain** | `/ponytail-gain` | Measured-impact scoreboard: less code, less cost, more speed. |\n| **ponytail-help** | `/ponytail-help` | This card. |\n\nCodex uses `@ponytail`, `@ponytail-review`, and `@ponytail-help`; Claude Code\nand OpenCode use the slash-command forms above (OpenCode ships all six as\nslash commands).\n\n## Deactivate\n\nSay \"stop ponytail\" or \"normal mode\". Resume anytime with `/ponytail`.\n`/ponytail off` also works.\n\n## Configure Default Mode\n\nDefault mode = `full`, auto-active every session. Change it:\n\n**Environment variable** (highest priority):\n```bash\nexport PONYTAIL_DEFAULT_MODE=ultra\n```\n\n**Config file** (`~/.config/ponytail/config.json`, Windows: `%APPDATA%\\ponytail\\config.json`):\n```json\n{ \"defaultMode\": \"lite\" }\n```\n\nSet `\"off\"` to disable auto-activation on session start, activate manually\nwith `/ponytail` when wanted.\n\nResolution: env var > config file > `full`.\n\n## Update\n\nEnable auto-update once: open `/plugin`, go to Marketplaces, pick ponytail, Enable auto-update. Claude Code then pulls new versions at startup (run `/reload-plugins` when it prompts). Manual refresh: `/plugin marketplace update ponytail` then `/reload-plugins`.\n\nIf `/plugin` is not recognized, your Claude Code is out of date. Update it (`npm install -g @anthropic-ai/claude-code@latest`, or `brew upgrade claude-code`) and restart. Other hosts use their own update flow.\n\n## More\n\nFull docs + examples: https://github.com/DietrichGebert/ponytail\n\nFile v4.9.0:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-help\",\n  \"version\": \"4.9.0\",\n  \"publishedAt\": 1786137410276\n}\n\nFile v4.9.0:skill-card.md\n\n## Description:\n\nQuick reference for ponytail's modes, skills, and commands. One-shot display.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dietrichgebert](https://clawhub.ai/user/dietrichgebert)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and agent users use this skill to display a one-shot reference for Ponytail modes, related skills, slash commands, deactivation, default-mode configuration, and update steps.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Users could unintentionally deactivate Ponytail by saying \"normal mode\" where a mode change would be disruptive.\n\nMitigation: Use explicit commands such as `/ponytail off` or `stop ponytail` when changing modes, and confirm the intended mode after switching.\n\nRisk: Enabling marketplace auto-update can change the installed behavior at host startup.\n\nMitigation: Review the host marketplace auto-update setting and release notes before enabling automatic updates.\n\n## Reference(s):\n\n- [Ponytail documentation and examples](https://github.com/DietrichGebert/ponytail)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown reference text with inline shell commands and JSON configuration examples]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [One-shot display; the skill states that it should not change mode, write flag files, or persist state.]\n\n## Skill Version(s):\n\n4.9.0 (source: 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 v4.8.4: 3 files, 2676 bytes\n\nFiles: skill-card.md (1944b), SKILL.md (2527b), _meta.json (132b)\n\nFile v4.8.4:SKILL.md\n\n---\nname: ponytail-help\ndescription: \"Quick reference for ponytail's modes, skills, and commands. One-shot display.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\n# Ponytail Help\n\nDisplay this reference card when invoked. One-shot, do NOT change mode,\nwrite flag files, or persist anything.\n\n## Levels\n\n| Level | Trigger | What change |\n|-------|---------|-------------|\n| **Lite** | `/ponytail lite` | Build what's asked, name the lazier alternative in one line. |\n| **Full** | `/ponytail` | The ladder enforced: YAGNI → stdlib → native → one line → minimum. Default. |\n| **Ultra** | `/ponytail ultra` | YAGNI extremist. Deletion before addition. Challenges requirements before building. |\n\nLevel sticks until changed or session end.\n\n## Skills\n\n| Skill | Trigger | What it does |\n|-------|---------|--------------|\n| **ponytail** | `/ponytail` | Lazy mode itself. Simplest solution that works. |\n| **ponytail-review** | `/ponytail-review` | Over-engineering review: `L42: yagni: factory, one product. Inline.` |\n| **ponytail-gain** | `/ponytail-gain` | Measured-impact scoreboard: less code, less cost, more speed. |\n| **ponytail-help** | `/ponytail-help` | This card. |\n\nCodex uses `@ponytail`, `@ponytail-review`, and `@ponytail-help`; Claude Code\nand OpenCode use the slash-command forms above (OpenCode ships `/ponytail` and\n`/ponytail-review`).\n\n## Deactivate\n\nSay \"stop ponytail\" or \"normal mode\". Resume anytime with `/ponytail`.\n`/ponytail off` also works.\n\n## Configure Default Mode\n\nDefault mode = `full`, auto-active every session. Change it:\n\n**Environment variable** (highest priority):\n```bash\nexport PONYTAIL_DEFAULT_MODE=ultra\n```\n\n**Config file** (`~/.config/ponytail/config.json`, Windows: `%APPDATA%\\ponytail\\config.json`):\n```json\n{ \"defaultMode\": \"lite\" }\n```\n\nSet `\"off\"` to disable auto-activation on session start, activate manually\nwith `/ponytail` when wanted.\n\nResolution: env var > config file > `full`.\n\n## Update\n\nEnable auto-update once: open `/plugin`, go to Marketplaces, pick ponytail, Enable auto-update. Claude Code then pulls new versions at startup (run `/reload-plugins` when it prompts). Manual refresh: `/plugin marketplace update ponytail` then `/reload-plugins`.\n\nIf `/plugin` is not recognized, your Claude Code is out of date. Update it (`npm install -g @anthropic-ai/claude-code@latest`, or `brew upgrade claude-code`) and restart. Other hosts use their own update flow.\n\n## More\n\nFull docs + examples: https://github.com/DietrichGebert/ponytail\n\nFile v4.8.4:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-help\",\n  \"version\": \"4.8.4\",\n  \"publishedAt\": 1782711280946\n}\n\nFile v4.8.4:skill-card.md\n\n## Description: <br>\nQuick reference for ponytail's modes, skills, and commands. One-shot display. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[dietrichgebert](https://clawhub.ai/user/dietrichgebert) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and agent users use Ponytail Help to display a quick reference for Ponytail modes, related skills, activation and deactivation commands, default-mode configuration, and update steps. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Activating the broader Ponytail workflow can change an agent's behavior for the session. <br>\nMitigation: Enable Ponytail modes intentionally and use the documented stop or normal-mode commands when the workflow is no longer wanted. <br>\nRisk: Optional default-mode and auto-update settings can make Ponytail active or update automatically in supported hosts. <br>\nMitigation: Review configuration and marketplace auto-update settings before enabling them. <br>\n\n\n## Reference(s): <br>\n- [Ponytail documentation](https://github.com/DietrichGebert/ponytail) <br>\n- [Ponytail Help on ClawHub](https://clawhub.ai/dietrichgebert/skills/ponytail-help) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance] <br>\n**Output Format:** [Markdown reference text with inline shell and JSON code blocks] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [One-shot display; no persistence, credentials, or file writes.] <br>\n\n## Skill Version(s): <br>\n4.8.4 (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 v4.8.3: 3 files, 2595 bytes\n\nFiles: skill-card.md (1705b), SKILL.md (2527b), _meta.json (132b)\n\nFile v4.8.3:SKILL.md\n\n---\nname: ponytail-help\ndescription: \"Quick reference for ponytail's modes, skills, and commands. One-shot display.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\n# Ponytail Help\n\nDisplay this reference card when invoked. One-shot, do NOT change mode,\nwrite flag files, or persist anything.\n\n## Levels\n\n| Level | Trigger | What change |\n|-------|---------|-------------|\n| **Lite** | `/ponytail lite` | Build what's asked, name the lazier alternative in one line. |\n| **Full** | `/ponytail` | The ladder enforced: YAGNI → stdlib → native → one line → minimum. Default. |\n| **Ultra** | `/ponytail ultra` | YAGNI extremist. Deletion before addition. Challenges requirements before building. |\n\nLevel sticks until changed or session end.\n\n## Skills\n\n| Skill | Trigger | What it does |\n|-------|---------|--------------|\n| **ponytail** | `/ponytail` | Lazy mode itself. Simplest solution that works. |\n| **ponytail-review** | `/ponytail-review` | Over-engineering review: `L42: yagni: factory, one product. Inline.` |\n| **ponytail-gain** | `/ponytail-gain` | Measured-impact scoreboard: less code, less cost, more speed. |\n| **ponytail-help** | `/ponytail-help` | This card. |\n\nCodex uses `@ponytail`, `@ponytail-review`, and `@ponytail-help`; Claude Code\nand OpenCode use the slash-command forms above (OpenCode ships `/ponytail` and\n`/ponytail-review`).\n\n## Deactivate\n\nSay \"stop ponytail\" or \"normal mode\". Resume anytime with `/ponytail`.\n`/ponytail off` also works.\n\n## Configure Default Mode\n\nDefault mode = `full`, auto-active every session. Change it:\n\n**Environment variable** (highest priority):\n```bash\nexport PONYTAIL_DEFAULT_MODE=ultra\n```\n\n**Config file** (`~/.config/ponytail/config.json`, Windows: `%APPDATA%\\ponytail\\config.json`):\n```json\n{ \"defaultMode\": \"lite\" }\n```\n\nSet `\"off\"` to disable auto-activation on session start, activate manually\nwith `/ponytail` when wanted.\n\nResolution: env var > config file > `full`.\n\n## Update\n\nEnable auto-update once: open `/plugin`, go to Marketplaces, pick ponytail, Enable auto-update. Claude Code then pulls new versions at startup (run `/reload-plugins` when it prompts). Manual refresh: `/plugin marketplace update ponytail` then `/reload-plugins`.\n\nIf `/plugin` is not recognized, your Claude Code is out of date. Update it (`npm install -g @anthropic-ai/claude-code@latest`, or `brew upgrade claude-code`) and restart. Other hosts use their own update flow.\n\n## More\n\nFull docs + examples: https://github.com/DietrichGebert/ponytail\n\nFile v4.8.3:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-help\",\n  \"version\": \"4.8.3\",\n  \"publishedAt\": 1782268644536\n}\n\nFile v4.8.3:skill-card.md\n\n## Description: <br>\nQuick reference for Ponytail's modes, skills, and commands. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[dietrichgebert](https://clawhub.ai/user/dietrichgebert) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and coding agents use this skill as a one-shot reference for Ponytail mode levels, related commands, deactivation, configuration, and update steps. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The documented phrase \"normal mode\" is a broad Ponytail deactivation alias and could be triggered unintentionally. <br>\nMitigation: Prefer explicit commands such as `/ponytail off` when changing modes. <br>\n\n\n## Reference(s): <br>\n- [Ponytail Help on ClawHub](https://clawhub.ai/dietrichgebert/skills/ponytail-help) <br>\n- [Ponytail project homepage](https://github.com/DietrichGebert/ponytail) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance] <br>\n**Output Format:** [Markdown reference text with inline shell commands and JSON configuration examples] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [One-shot help content; the skill instructs agents not to change mode, write flag files, or persist anything.] <br>\n\n## Skill Version(s): <br>\n4.8.3 (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>","readmeExcerpt":"Skill: ponytail-help Owner: dietrichgebert Summary: Quick reference for ponytail's modes, skills, and commands. One-shot display. Tags: latest:5.1.0 Version history: v5.1.0 | 2026-10-08T16:21:21.522Z | auto - Updated SKILL.md to clarify level and skill descriptions for greater accuracy and detail. - Improved the definitions for each mode (\"lite\", \"full\", \"ultra\") and their triggers. - Expanded skill explanations, esp","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"export PONYTAIL_DEFAULT_MODE=ultra"},{"language":"json","snippet":"{ \"defaultMode\": \"lite\" }"},{"language":"bash","snippet":"export PONYTAIL_DEFAULT_MODE=ultra"},{"language":"json","snippet":"{ \"defaultMode\": \"lite\" }"},{"language":"bash","snippet":"export PONYTAIL_DEFAULT_MODE=ultra"},{"language":"json","snippet":"{ \"defaultMode\": \"lite\" }"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: ponytail-help\ndescription: \"Quick reference for ponytail's modes, skills, and commands. One-shot display.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\n# Ponytail Help\n\nDisplay this reference card when invoked. One-shot, do NOT change mode,\nwrite flag files, or persist anything.\n\n## Levels\n\n| Level | Trigger | What change |\n|-------|---------|-------------|\n| **Lite** | `/ponytail lite` | Build what was asked, name the smaller option in one line. |\n| **Full** | `/ponytail` | The smallest complete change, a check where the logic needs one, and a reply that names what was skipped and any risk. Default. |\n| **Ultra** | `/ponytail ultra` | Also questions the request and pushes back before building. |\n\nLevel sticks until changed or session end.\n\n## Skills\n\n| Skill | Trigger | What it does |\n|-------|---------|--------------|\n| **ponytail** | `/ponytail` | Lazy mode itself: least new code, clear replies that name skipped work and risks. |\n| **ponytail-review** | `/ponytail-review` | Quality review of a diff: bugs, security, load, missing tests, speed, what to cut. Each finding says what goes wrong and how to fix it. |\n| **ponytail-audit** | `/ponytail-audit` | The same quality review for the whole repo, ranked. |\n| **ponytail-debt** | `/ponytail-debt` | Harvest `shortcut:` comments into a tracked ledger. |\n| **ponytail-gain** | `/ponytail-gain` | Measured-impact scoreboard: less code, less cost, more speed. |\n| **ponytail-help** | `/ponytail-help` | This card. |\n\nIn Codex CLI and the IDE extension, invoke skills with `$ponytail:ponytail`,\n`$ponytail:ponytail-review`, or `$ponytail:ponytail-help`. Claude Code and OpenCode use the\nslash-command forms above (OpenCode ships all six as slash commands).\n\n## Deactivate\n\nSay \"stop ponytail\" or \"normal mode\". Resume anytime with `/ponytail`.\n`/ponytail off` also works.\n\n## Configure Default Mode\n\nDefault mode = `full`, auto-active every session. Change it:\n\n**Environment variable** (highest priority):\n```bash\nexport PONYTAIL_DEFAULT_MODE=ultra\n```\n\n**Config file** (`~/.config/ponytail/config.json`, Windows: `%APPDATA%\\ponytail\\config.json`):\n```json\n{ \"defaultMode\": \"lite\" }\n```\n\nSet `\"off\"` to disable auto-activation on session start, activate manually\nwith `/ponytail` when wanted.\n\nResolution: env var > config file > `full`.\n\n## Update\n\nEnable auto-update once: open `/plugin`, go to Marketplaces, pick ponytail, Enable auto-update. Claude Code then pulls new versions at startup (run `/reload-plugins` when it prompts). Manual refresh: `/plugin marketplace update ponytail` then `/reload-plugins`.\n\nIf `/plugin` is not recognized, your Claude Code is out of date. Update it (`npm install -g @anthropic-ai/claude-code@latest`, or `brew upgrade claude-code`) and restart. Other hosts use their own update flow.\n\n## More\n\nFull docs + examples: https://github.com/DietrichGebert/ponytail"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-help\",\n  \"version\": \"5.1.0\",\n  \"publishedAt\": 1791476481522\n}"},{"path":"skill-card.md","content":"## Description:\n\nQuick reference for ponytail's modes, skills, and commands. One-shot display.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dietrichgebert](https://clawhub.ai/user/dietrichgebert)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and other Ponytail users can display a quick reference to its modes, available skills, configuration options, and update commands.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Running the documented update or configuration commands may change local tooling or defaults.\n\nMitigation: Review the commands and settings before applying them; displaying this help card does not execute them.\n\n## Reference(s):\n\n- [Ponytail documentation and examples](https://github.com/DietrichGebert/ponytail)\n- [Ponytail Help on ClawHub](https://clawhub.ai/dietrichgebert/skills/ponytail-help)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Guidance, Shell commands, Configuration instructions]\n\n**Output Format:** [Markdown reference card with example commands and configuration]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [One-shot display; does not change settings or run commands.]\n\n## Skill Version(s):\n\n5.1.0 (source: ClawHub 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":"Quick reference for ponytail's modes, skills, and commands. One-shot display. Skill: ponytail-help Owner: dietrichgebert Summary: Quick reference for ponytail's modes, skills, and commands. One-shot display. Tags: latest:5.1.0 Version history: v5.1.0 | 2026-10-08T16:21:21.522Z | auto - Updated SKILL.md to clarify level and skill descriptions for greater accuracy and detail. - Improved the definitions for each mode (\"lite\", \"full\", \"ultra\") and their triggers. - Expanded skill explanations, esp","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1157,"uniquenessScore":49,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-10T08:24:58.682Z","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":"2026-10-10T08:24:58.682Z","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":"2026-10-10T10:43:48.449Z","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"}]}}}