{"owner":"TEN-framework","repo":"ten-framework","hasSkills":true,"totalSkillsCount":5,"totalTokensCount":1697,"categories":["root-instruction","claude-rule","mcp-config","marketplace","plugin-manifest"],"hasMcp":true,"mcpConfig":{"mcpServers":{"ten-framework":{"command":"npx","args":["-y","@modelcontextprotocol/server-ten-framework"]}}},"found":["AGENTS.md","CLAUDE.md",".cursor/mcp.json",".claude-plugin/marketplace.json",".claude-plugin/plugin.json"],"skills":{"AGENTS.md":"# AI Agent Instructions\n\nThis repository uses progressive disclosure documentation to help AI coding\nagents work efficiently. Documentation is structured in three levels under\n`docs/ai/`.\n\n## How to Load\n\n1. Read [docs/ai/L0_repo_card.md](docs/ai/L0_repo_card.md) to identify the repo.\n2. Load ALL 8 files in `docs/ai/L1/`. They are small — load all of them upfront.\n   This gives you setup, architecture, code map, conventions, workflows,\n   interfaces, gotchas, and security.\n3. If a task needs more detail than L1 provides, follow links to L2 deep dives\n   in `docs/ai/L1/deep_dives/`. Load only the specific L2 file you need.\n\n## Levels\n\n- **L0 (Repo Card):** Identity and L1 index. Table of contents.\n- **L1 (Summaries):** Eight structured summaries. Load all at session start.\n- **L2 (Deep Dives):** Full specifications. Load only when L1 isn't detailed enough.\n\n## Git Conventions\n\n### Commit messages — conventional commits\n\n- **Format:** `type: description` or `type(scope): description`\n- **Types:** `feat:` (new feature), `fix:` (bug fix), `chore:` (maintenance, version bumps), `test:` (test additions/changes), `docs:` (documentation)\n- **Scoped variant:** `feat(scope):`, `fix(scope):` — e.g. `feat(auth): add token refresh`\n- **Lowercase after prefix** — `feat: add feature`, not `feat: Add feature`\n- **Present tense** — \"add feature\", not \"added feature\"\n- **PR number appended** — `feat: add feature (#123)`\n\n### Branch names\n\n- **Format:** `type/short-description` — lowercase, hyphen-separated\n- **Types match commit types:** `feat/`, `fix/`, `chore/`, `test/`, `docs/`\n- **Examples:** `feat/token-refresh`, `fix/null-pointer`, `docs/progressive-disclosure`\n\n### General rules\n\n- **No AI tool names** — never mention claude, cursor, copilot, cody, aider, gemini, codex, chatgpt, or gpt-3/4\n- **No Co-Authored-By trailers** — omit AI attribution lines\n- **No --no-verify** — let git hooks run normally\n- **No git config changes** — do not modify user.name or user.email\n\n## Doc Commands\n\n| Command       | When to use                                   |\n| ------------- | --------------------------------------------- |\n| generate docs | no `docs/ai/` directory exists yet            |\n| update docs   | code changed since last `last_reviewed` date  |\n| test docs     | verify docs give agents the right context     |\n\nFor detailed procedures, read\n[progressive-disclosure-standard.md](docs/progressive-disclosure-standard.md)\nsections 6 (generate) and 7 (bootstrap).\n\n## Working Areas\n\n- `ai_agents/` — primary area for agents, examples, server, integrations\n- `core/`, `packages/`, `build/` — framework internals\n\n## Domain Skills\n\n- For pull-request or diff reviews of implementation, configuration, dependency,\n  or test changes inside `ai_agents/agents/ten_packages/extension/<tts-extension>/`,\n  load and follow\n  [ten-tts-review](.agents/skills/ten-tts-review/SKILL.md).\n- Do not apply that skill to `ten_ai_base`, `tts_guarder`, examples, graphs, or\n  paths outside the TTS extension directory.\n","CLAUDE.md":"Read @AGENTS.md for AI agent instructions, git conventions, and progressive disclosure docs.\n",".cursor/mcp.json":"# Model Context Protocol (MCP) Configuration\n\nPath: `.cursor/mcp.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/TEN-framework/ten-framework/HEAD/.cursor/mcp.json)",".claude-plugin/marketplace.json":"# Claude Plugin Marketplace Catalog\n\nPath: `.claude-plugin/marketplace.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/TEN-framework/ten-framework/HEAD/.claude-plugin/marketplace.json)",".claude-plugin/plugin.json":"# claude-plugin Plugin Manifest\n\nPath: `.claude-plugin/plugin.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/TEN-framework/ten-framework/HEAD/.claude-plugin/plugin.json)"},"files":{"AGENTS.md":"# AI Agent Instructions\n\nThis repository uses progressive disclosure documentation to help AI coding\nagents work efficiently. Documentation is structured in three levels under\n`docs/ai/`.\n\n## How to Load\n\n1. Read [docs/ai/L0_repo_card.md](docs/ai/L0_repo_card.md) to identify the repo.\n2. Load ALL 8 files in `docs/ai/L1/`. They are small — load all of them upfront.\n   This gives you setup, architecture, code map, conventions, workflows,\n   interfaces, gotchas, and security.\n3. If a task needs more detail than L1 provides, follow links to L2 deep dives\n   in `docs/ai/L1/deep_dives/`. Load only the specific L2 file you need.\n\n## Levels\n\n- **L0 (Repo Card):** Identity and L1 index. Table of contents.\n- **L1 (Summaries):** Eight structured summaries. Load all at session start.\n- **L2 (Deep Dives):** Full specifications. Load only when L1 isn't detailed enough.\n\n## Git Conventions\n\n### Commit messages — conventional commits\n\n- **Format:** `type: description` or `type(scope): description`\n- **Types:** `feat:` (new feature), `fix:` (bug fix), `chore:` (maintenance, version bumps), `test:` (test additions/changes), `docs:` (documentation)\n- **Scoped variant:** `feat(scope):`, `fix(scope):` — e.g. `feat(auth): add token refresh`\n- **Lowercase after prefix** — `feat: add feature`, not `feat: Add feature`\n- **Present tense** — \"add feature\", not \"added feature\"\n- **PR number appended** — `feat: add feature (#123)`\n\n### Branch names\n\n- **Format:** `type/short-description` — lowercase, hyphen-separated\n- **Types match commit types:** `feat/`, `fix/`, `chore/`, `test/`, `docs/`\n- **Examples:** `feat/token-refresh`, `fix/null-pointer`, `docs/progressive-disclosure`\n\n### General rules\n\n- **No AI tool names** — never mention claude, cursor, copilot, cody, aider, gemini, codex, chatgpt, or gpt-3/4\n- **No Co-Authored-By trailers** — omit AI attribution lines\n- **No --no-verify** — let git hooks run normally\n- **No git config changes** — do not modify user.name or user.email\n\n## Doc Commands\n\n| Command       | When to use                                   |\n| ------------- | --------------------------------------------- |\n| generate docs | no `docs/ai/` directory exists yet            |\n| update docs   | code changed since last `last_reviewed` date  |\n| test docs     | verify docs give agents the right context     |\n\nFor detailed procedures, read\n[progressive-disclosure-standard.md](docs/progressive-disclosure-standard.md)\nsections 6 (generate) and 7 (bootstrap).\n\n## Working Areas\n\n- `ai_agents/` — primary area for agents, examples, server, integrations\n- `core/`, `packages/`, `build/` — framework internals\n\n## Domain Skills\n\n- For pull-request or diff reviews of implementation, configuration, dependency,\n  or test changes inside `ai_agents/agents/ten_packages/extension/<tts-extension>/`,\n  load and follow\n  [ten-tts-review](.agents/skills/ten-tts-review/SKILL.md).\n- Do not apply that skill to `ten_ai_base`, `tts_guarder`, examples, graphs, or\n  paths outside the TTS extension directory.\n","CLAUDE.md":"Read @AGENTS.md for AI agent instructions, git conventions, and progressive disclosure docs.\n",".cursor/mcp.json":"# Model Context Protocol (MCP) Configuration\n\nPath: `.cursor/mcp.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/TEN-framework/ten-framework/HEAD/.cursor/mcp.json)",".claude-plugin/marketplace.json":"# Claude Plugin Marketplace Catalog\n\nPath: `.claude-plugin/marketplace.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/TEN-framework/ten-framework/HEAD/.claude-plugin/marketplace.json)",".claude-plugin/plugin.json":"# claude-plugin Plugin Manifest\n\nPath: `.claude-plugin/plugin.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/TEN-framework/ten-framework/HEAD/.claude-plugin/plugin.json)"},"items":[{"name":"AGENTS.md","path":"AGENTS.md","rawUrl":"https://raw.githubusercontent.com/TEN-framework/ten-framework/HEAD/AGENTS.md","title":"AI Agent Protocol & Instructions","category":"root-instruction","format":"markdown","content":"# AI Agent Instructions\n\nThis repository uses progressive disclosure documentation to help AI coding\nagents work efficiently. Documentation is structured in three levels under\n`docs/ai/`.\n\n## How to Load\n\n1. Read [docs/ai/L0_repo_card.md](docs/ai/L0_repo_card.md) to identify the repo.\n2. Load ALL 8 files in `docs/ai/L1/`. They are small — load all of them upfront.\n   This gives you setup, architecture, code map, conventions, workflows,\n   interfaces, gotchas, and security.\n3. If a task needs more detail than L1 provides, follow links to L2 deep dives\n   in `docs/ai/L1/deep_dives/`. Load only the specific L2 file you need.\n\n## Levels\n\n- **L0 (Repo Card):** Identity and L1 index. Table of contents.\n- **L1 (Summaries):** Eight structured summaries. Load all at session start.\n- **L2 (Deep Dives):** Full specifications. Load only when L1 isn't detailed enough.\n\n## Git Conventions\n\n### Commit messages — conventional commits\n\n- **Format:** `type: description` or `type(scope): description`\n- **Types:** `feat:` (new feature), `fix:` (bug fix), `chore:` (maintenance, version bumps), `test:` (test additions/changes), `docs:` (documentation)\n- **Scoped variant:** `feat(scope):`, `fix(scope):` — e.g. `feat(auth): add token refresh`\n- **Lowercase after prefix** — `feat: add feature`, not `feat: Add feature`\n- **Present tense** — \"add feature\", not \"added feature\"\n- **PR number appended** — `feat: add feature (#123)`\n\n### Branch names\n\n- **Format:** `type/short-description` — lowercase, hyphen-separated\n- **Types match commit types:** `feat/`, `fix/`, `chore/`, `test/`, `docs/`\n- **Examples:** `feat/token-refresh`, `fix/null-pointer`, `docs/progressive-disclosure`\n\n### General rules\n\n- **No AI tool names** — never mention claude, cursor, copilot, cody, aider, gemini, codex, chatgpt, or gpt-3/4\n- **No Co-Authored-By trailers** — omit AI attribution lines\n- **No --no-verify** — let git hooks run normally\n- **No git config changes** — do not modify user.name or user.email\n\n## Doc Commands\n\n| Command       | When to use                                   |\n| ------------- | --------------------------------------------- |\n| generate docs | no `docs/ai/` directory exists yet            |\n| update docs   | code changed since last `last_reviewed` date  |\n| test docs     | verify docs give agents the right context     |\n\nFor detailed procedures, read\n[progressive-disclosure-standard.md](docs/progressive-disclosure-standard.md)\nsections 6 (generate) and 7 (bootstrap).\n\n## Working Areas\n\n- `ai_agents/` — primary area for agents, examples, server, integrations\n- `core/`, `packages/`, `build/` — framework internals\n\n## Domain Skills\n\n- For pull-request or diff reviews of implementation, configuration, dependency,\n  or test changes inside `ai_agents/agents/ten_packages/extension/<tts-extension>/`,\n  load and follow\n  [ten-tts-review](.agents/skills/ten-tts-review/SKILL.md).\n- Do not apply that skill to `ten_ai_base`, `tts_guarder`, examples, graphs, or\n  paths outside the TTS extension directory.\n","isInternal":false,"tokens":779,"sizeBytes":3048},{"name":"CLAUDE.md","path":"CLAUDE.md","rawUrl":"https://raw.githubusercontent.com/TEN-framework/ten-framework/HEAD/CLAUDE.md","title":"Claude Agent Guidelines & System Prompt","category":"claude-rule","format":"markdown","content":"Read @AGENTS.md for AI agent instructions, git conventions, and progressive disclosure docs.\n","isInternal":false,"tokens":18,"sizeBytes":93},{"name":"marketplace.json","path":".claude-plugin/marketplace.json","rawUrl":"https://raw.githubusercontent.com/TEN-framework/ten-framework/HEAD/.claude-plugin/marketplace.json","title":"Claude Plugin Marketplace Catalog","category":"marketplace","format":"json","content":"# Claude Plugin Marketplace Catalog\n\nPath: `.claude-plugin/marketplace.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/TEN-framework/ten-framework/HEAD/.claude-plugin/marketplace.json)","tokens":300,"sizeBytes":206},{"name":"plugin.json","path":".claude-plugin/plugin.json","rawUrl":"https://raw.githubusercontent.com/TEN-framework/ten-framework/HEAD/.claude-plugin/plugin.json","title":"claude-plugin Plugin Manifest","category":"plugin-manifest","format":"json","content":"# claude-plugin Plugin Manifest\n\nPath: `.claude-plugin/plugin.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/TEN-framework/ten-framework/HEAD/.claude-plugin/plugin.json)","tokens":300,"sizeBytes":192},{"name":"mcp.json","path":".cursor/mcp.json","rawUrl":"https://raw.githubusercontent.com/TEN-framework/ten-framework/HEAD/.cursor/mcp.json","title":"Model Context Protocol (MCP) Configuration","category":"mcp-config","format":"json","content":"# Model Context Protocol (MCP) Configuration\n\nPath: `.cursor/mcp.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/TEN-framework/ten-framework/HEAD/.cursor/mcp.json)","tokens":300,"sizeBytes":185}],"systemPromptSnippet":"<yakaai_skills repo=\"TEN-framework/ten-framework\">\n<!-- File: AGENTS.md (Tokens: ~779 | Category: root-instruction) -->\n# AI Agent Instructions\n\nThis repository uses progressive disclosure documentation to help AI coding\nagents work efficiently. Documentation is structured in three levels under\n`docs/ai/`.\n\n## How to Load\n\n1. Read [docs/ai/L0_repo_card.md](docs/ai/L0_repo_card.md) to identify the repo.\n2. Load ALL 8 files in `docs/ai/L1/`. They are small — load all of them upfront.\n   This gives you setup, architecture, code map, conventions, workflows,\n   interfaces, gotchas, and security.\n3. If a task needs more detail than L1 provides, follow links to L2 deep dives\n   in `docs/ai/L1/deep_dives/`. Load only the specific L2 file you need.\n\n## Levels\n\n- **L0 (Repo Card):** Identity and L1 index. Table of contents.\n- **L1 (Summaries):** Eight structured summaries. Load all at session start.\n- **L2 (Deep Dives):** Full specifications. Load only when L1 isn't detailed enough.\n\n## Git Conventions\n\n### Commit messages — conventional commits\n\n- **Format:** `type: description` or `type(scope): description`\n- **Types:** `feat:` (new feature), `fix:` (bug fix), `chore:` (maintenance, version bumps), `test:` (test additions/changes), `docs:` (documentation)\n- **Scoped variant:** `feat(scope):`, `fix(scope):` — e.g. `feat(auth): add token refresh`\n- **Lowercase after prefix** — `feat: add feature`, not `feat: Add feature`\n- **Present tense** — \"add feature\", not \"added feature\"\n- **PR number appended** — `feat: add feature (#123)`\n\n### Branch names\n\n- **Format:** `type/short-description` — lowercase, hyphen-separated\n- **Types match commit types:** `feat/`, `fix/`, `chore/`, `test/`, `docs/`\n- **Examples:** `feat/token-refresh`, `fix/null-pointer`, `docs/progressive-disclosure`\n\n### General rules\n\n- **No AI tool names** — never mention claude, cursor, copilot, cody, aider, gemini, codex, chatgpt, or gpt-3/4\n- **No Co-Authored-By trailers** — omit AI attribution lines\n- **No --no-verify** — let git hooks run normally\n- **No git config changes** — do not modify user.name or user.email\n\n## Doc Commands\n\n| Command       | When to use                                   |\n| ------------- | --------------------------------------------- |\n| generate docs | no `docs/ai/` directory exists yet            |\n| update docs   | code changed since last `last_reviewed` date  |\n| test docs     | verify docs give agents the right context     |\n\nFor detailed procedures, read\n[progressive-disclosure-standard.md](docs/progressive-disclosure-standard.md)\nsections 6 (generate) and 7 (bootstrap).\n\n## Working Areas\n\n- `ai_agents/` — primary area for agents, examples, server, integrations\n- `core/`, `packages/`, `build/` — framework internals\n\n## Domain Skills\n\n- For pull-request or diff reviews of implementation, configuration, dependency,\n  or test changes inside `ai_agents/agents/ten_packages/extension/<tts-extension>/`,\n  load and follow\n  [ten-tts-review](.agents/skills/ten-tts-review/SKILL.md).\n- Do not apply that skill to `ten_ai_base`, `tts_guarder`, examples, graphs, or\n  paths outside the TTS extension directory.\n\n<!-- File: CLAUDE.md (Tokens: ~18 | Category: claude-rule) -->\nRead @AGENTS.md for AI agent instructions, git conventions, and progressive disclosure docs.\n\n<!-- File: .claude-plugin/marketplace.json (Tokens: ~300 | Category: marketplace) -->\n# Claude Plugin Marketplace Catalog\n\nPath: `.claude-plugin/marketplace.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/TEN-framework/ten-framework/HEAD/.claude-plugin/marketplace.json)\n\n<!-- File: .claude-plugin/plugin.json (Tokens: ~300 | Category: plugin-manifest) -->\n# claude-plugin Plugin Manifest\n\nPath: `.claude-plugin/plugin.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/TEN-framework/ten-framework/HEAD/.claude-plugin/plugin.json)\n\n<!-- File: .cursor/mcp.json (Tokens: ~300 | Category: mcp-config) -->\n# Model Context Protocol (MCP) Configuration\n\nPath: `.cursor/mcp.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/TEN-framework/ten-framework/HEAD/.cursor/mcp.json)\n</yakaai_skills>"}