{"id":47172652,"url":"https://github.com/sehoon787/my-claude","last_synced_at":"2026-05-15T03:03:52.238Z","repository":{"id":344102134,"uuid":"1179935285","full_name":"sehoon787/my-claude","owner":"sehoon787","description":"All-in-one agent harness for Claude Code — Boss meta-orchestrator, 200+ agents, 200+ skills, 87 rules, 3 MCP servers, 7 hooks. One plugin install.","archived":false,"fork":false,"pushed_at":"2026-05-13T09:58:21.000Z","size":3097,"stargazers_count":8,"open_issues_count":0,"forks_count":4,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-13T11:38:56.162Z","etag":null,"topics":["agent-harness","agent-teams","agentic-coding","ai-agents","anthropic","claude","claude-code","claude-code-plugin","developer-tools","llm-agent","mcp","mcp-server","multi-agent","orchestration","subagents"],"latest_commit_sha":null,"homepage":"https://sehoon787.github.io/my-claude/","language":"Shell","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/sehoon787.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":"CLA.md"}},"created_at":"2026-03-12T14:30:23.000Z","updated_at":"2026-05-13T09:58:24.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/sehoon787/my-claude","commit_stats":null,"previous_names":["sehoon787/my-claude"],"tags_count":143,"template":false,"template_full_name":null,"purl":"pkg:github/sehoon787/my-claude","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sehoon787%2Fmy-claude","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sehoon787%2Fmy-claude/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sehoon787%2Fmy-claude/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sehoon787%2Fmy-claude/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sehoon787","download_url":"https://codeload.github.com/sehoon787/my-claude/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sehoon787%2Fmy-claude/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33051875,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-13T13:14:54.681Z","status":"online","status_checked_at":"2026-05-15T02:00:06.351Z","response_time":103,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent-harness","agent-teams","agentic-coding","ai-agents","anthropic","claude","claude-code","claude-code-plugin","developer-tools","llm-agent","mcp","mcp-server","multi-agent","orchestration","subagents"],"created_at":"2026-03-13T06:05:32.590Z","updated_at":"2026-05-15T03:03:52.231Z","avatar_url":"https://github.com/sehoon787.png","language":"Shell","funding_links":[],"categories":["Source Catalog"],"sub_categories":[],"readme":"[English](./README.md) | [한국어](./docs/i18n/README.ko.md) | [日本語](./docs/i18n/README.ja.md) | [中文](./docs/i18n/README.zh.md) | [Deutsch](./docs/i18n/README.de.md) | [Français](./docs/i18n/README.fr.md)\n\n\u003e [![Codex CLI](https://img.shields.io/badge/Codex_CLI-my--codex-10b981?style=flat-square\u0026logo=openai\u0026logoColor=white)](https://github.com/sehoon787/my-codex) Looking for Codex CLI? → **my-codex** — same orchestration in native TOML format\n\n---\n\n\u003cdiv align=\"center\"\u003e\n\n# my-claude\n\n![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)\n![Agents](https://img.shields.io/badge/agents-200%2B-blue)\n![Skills](https://img.shields.io/badge/skills-200%2B-purple)\n![Rules](https://img.shields.io/badge/rules-87-orange)\n![MCP Servers](https://img.shields.io/badge/MCP-3-green)\n![Hooks](https://img.shields.io/badge/hooks-7-red)\n\n**All-in-one agent harness for Claude Code.**\n**One plugin, 200+ agents ready.**\n\nBoss auto-discovers every agent, skill, and MCP tool at runtime,\u003cbr\u003e\nthen routes your task to the right specialist. No config files. No boilerplate.\n\n\u003cimg src=\"./assets/owl-claude-social.svg\" alt=\"The Maestro Owl — my-claude\" width=\"700\"\u003e\n\n\u003c/div\u003e\n\n---\n\n## Installation\n\n### For Humans\n\n```bash\ngit clone --depth 1 https://github.com/sehoon787/my-claude.git /tmp/my-claude\nbash /tmp/my-claude/install.sh\nrm -rf /tmp/my-claude\n```\n\nOr install as a Claude Code plugin first, then run the companion installer:\n\n```bash\n# Inside a Claude Code session:\n/plugin marketplace add sehoon787/my-claude\n/plugin install my-claude@my-claude\n\n# Then install companion tools:\ngit clone --depth 1 https://github.com/sehoon787/my-claude.git /tmp/my-claude\nbash /tmp/my-claude/install.sh\nrm -rf /tmp/my-claude\n```\n\n### For AI Agents\n\n```\nRead https://raw.githubusercontent.com/sehoon787/my-claude/main/AI-INSTALL.md and follow every step.\n```\n\n---\n\n## Open-Source Tools Used\n\n### 1. [Oh My Claude Code (OMC)](https://github.com/Yeachan-Heo/oh-my-claudecode)\n\nAn agent harness dedicated to Claude Code. 18 specialist agents (architect, debugger, code reviewer, security reviewer, etc.) divide work by role, and magic keywords like `autopilot:` activate automatic parallel execution.\n\n### 2. [Oh My OpenAgent (omo)](https://github.com/code-yeongyu/oh-my-openagent)\n\nA multi-platform agent harness. Bridges to the Claude Code ecosystem via `claude-code-agent-loader` and `claude-code-plugin-loader`. Automatically routes across 8 providers (Claude, GPT, Gemini, etc.) by category. The 9 agents in this repository are adaptations of omo agents in Claude Code standalone `.md` format.\n\n### 3. [Andrej Karpathy Skills](https://github.com/forrestchang/andrej-karpathy-skills)\n\nThe 4 AI coding behavioral guidelines proposed by Andrej Karpathy (Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution). Included in CLAUDE.md and always active across all sessions.\n\n### 4. [Everything Claude Code (ECC)](https://github.com/affaan-m/everything-claude-code)\n\nA comprehensive framework providing 67 skills + 17 agents + 45 commands + language-specific rules. Automates repetitive development patterns with slash commands like `/tdd`, `/plan`, `/code-review`, and `/build-fix`.\n\n### 5. [Anthropic Official Skills](https://github.com/anthropics/skills)\n\nThe official agent skills repository provided directly by Anthropic. Enables specialist tasks such as PDF parsing, Word/Excel/PowerPoint document manipulation, and MCP server creation.\n\n### 6. [Agency Agents](https://github.com/msitarzewski/agency-agents)\n\nA library of 164 business specialist agent personas. Provides specialist perspectives in business contexts beyond technical roles — UX architects, data engineers, security auditors, QA managers, and more.\n\n### 7. [gstack](https://github.com/garrytan/gstack)\n\nA sprint-process harness by Garry Tan with 27 skills. Provides browser-based QA testing (`/qa`), code review with scope-drift detection (`/review`), security auditing (`/cso`), and a full Plan→Review→QA→Ship deployment workflow. Includes a compiled Playwright browser daemon for real-browser testing.\n\n### 8. [VibeProxy](https://github.com/automazeio/vibeproxy)\n\nOAuth-based API proxy that uses existing AI subscriptions (ChatGPT Plus, Gemini, Claude) to access GPT/Gemini/Claude models without separate API keys. Supports both Anthropic and OpenAI API formats. Integrated via optional `vibeproxy-setup.sh` during installation. Model routing maps Claude model tiers (opus/sonnet/haiku) to equivalent vendor models.\n\n---\n\n## How Boss Works\n\nBoss is the meta-orchestrator at the core of my-claude. It never writes code — it discovers, classifies, matches, delegates, and verifies.\n\n```\nUser Request\n     │\n     ▼\n┌─────────────────────────────────────────────┐\n│  Phase 0 · DISCOVERY                        │\n│  Scan agents, skills, MCP, hooks at runtime │\n│  → Build live capability registry           │\n└──────────────────────┬──────────────────────┘\n                       ▼\n┌─────────────────────────────────────────────┐\n│  Phase 1 · INTENT GATE                      │\n│  Classify: trivial | build | refactor |     │\n│  mid-sized | architecture | research | ...  │\n│  → Counter-propose skill if better fit      │\n└──────────────────────┬──────────────────────┘\n                       ▼\n┌─────────────────────────────────────────────┐\n│  Phase 2 · CAPABILITY MATCHING              │\n│  P0: gstack skill (if installed)            │\n│  P1: Exact skill match                      │\n│  P2: Specialist agent (200+)               │\n│  P3: Multi-agent orchestration              │\n│  P4: General-purpose fallback               │\n└──────────────────────┬──────────────────────┘\n                       ▼\n┌─────────────────────────────────────────────┐\n│  Phase 3 · DELEGATION                       │\n│  6-section structured prompt to specialist  │\n│  TASK / OUTCOME / TOOLS / DO / DON'T / CTX  │\n└──────────────────────┬──────────────────────┘\n                       ▼\n┌─────────────────────────────────────────────┐\n│  Phase 4 · VERIFICATION                     │\n│  Read changed files independently           │\n│  Run tests, lint, build                     │\n│  Cross-reference with original intent       │\n│  → Retry up to 3× on failure               │\n└─────────────────────────────────────────────┘\n```\n\n### Priority Routing\n\nBoss cascades every request through a priority chain until the best match is found:\n\n| Priority | Match Type | When | Example |\n|:--------:|-----------|------|---------|\n| **P1** | Skill match | Task maps to a self-contained skill | `\"merge PDFs\"` → pdf skill |\n| **P2** | Specialist agent | Domain-specific agent exists | `\"security audit\"` → Security Engineer |\n| **P3a** | Boss direct | 2-4 independent agents | `\"fix 3 bugs\"` → parallel spawn |\n| **P3b** | Sub-orchestrator | Complex multi-step workflow | `\"refactor + test\"` → Sisyphus |\n| **P3c** | Agent Teams | Peer-to-peer communication needed | `\"implement + review\"` → Review Chain |\n| **P4** | Fallback | No specialist matches | `\"explain this\"` → general agent |\n\n### Model Routing\n\n| Complexity | Model | Used For |\n|-----------|-------|----------|\n| Deep analysis, architecture | Opus | Boss, Oracle, Sisyphus |\n| Standard implementation | Sonnet | executor, debugger, security-reviewer |\n| Quick lookup, exploration | Haiku | explore, simple advisory |\n\n### 3-Phase Sprint Workflow\n\nFor end-to-end feature implementation, Boss orchestrates a structured sprint:\n\n```\nPhase 1: DESIGN         Phase 2: EXECUTE        Phase 3: REVIEW\n(interactive)            (autonomous)             (interactive)\n─────────────────────   ─────────────────────   ─────────────────────\nUser decides scope      ralph runs execution    Compare vs design doc\nEngineering review      Auto code review        Present comparison table\nConfirm \"design done\"   Architect verification  User: approve / improve\n```\n\n---\n\n## Architecture\n\n```\n┌─────────────────────────────────────────────────────┐\n│                    User Request                       │\n└───────────────────────┬─────────────────────────────┘\n                        ▼\n┌─────────────────────────────────────────────────────┐\n│  Boss · Meta-Orchestrator (Opus)                      │\n│  Discovery → Classification → Matching → Delegation  │\n└──┬──────────┬──────────┬──────────┬─────────────────┘\n   │          │          │          │\n   ▼          ▼          ▼          ▼\n┌──────┐ ┌────────┐ ┌────────┐ ┌────────┐\n│ P3a  │ │  P3b   │ │  P3c   │ │  P1/P2 │\n│Direct│ │Sub-orch│ │ Agent  │ │ Skill/ │\n│2-4   │ │Sisyphus│ │ Teams  │ │ Agent  │\n│agents│ │Atlas   │ │  P2P   │ │ Direct │\n└──────┘ │Hephaes│ └────────┘ └────────┘\n         └────────┘\n┌─────────────────────────────────────────────────────┐\n│  Behavioral Layer                                     │\n│  Karpathy Guidelines · ECC Rules (87) · Hooks (7)    │\n├─────────────────────────────────────────────────────┤\n│  Specialist Agents (200+)                             │\n│  OMO 9 · OMC 19 · Agency Eng. 26 · Superpowers 1    │\n│  + 136 domain packs (on-demand)                       │\n├─────────────────────────────────────────────────────┤\n│  Skills (200+)                                        │\n│  ECC 180+ · OMC 36 · gstack 40 · Superpowers 14     │\n│  + Core 3 · Anthropic 14+                             │\n├─────────────────────────────────────────────────────┤\n│  MCP Layer                                            │\n│  Context7 · Exa · grep.app                            │\n└─────────────────────────────────────────────────────┘\n```\n\n---\n\n## What's Inside\n\n| Category | Count | Source |\n|----------|------:|--------|\n| **Core agents** (always loaded) | 56 | Boss 1 + OMO 9 + OMC 19 + Agency Engineering 26 + Superpowers 1 |\n| **Agent packs** (on-demand) | 136 | 12 domain categories from agency-agents |\n| **Skills** | 200+ | ECC 180+ · OMC 36 · gstack 40 · Superpowers 14 · Core 3 |\n| **Anthropic Skills** | 14+ | PDF, DOCX, PPTX, XLSX, MCP builder |\n| **Rules** | 87 | ECC common + 14 language directories |\n| **MCP Servers** | 3 | Context7, Exa, grep.app |\n| **Hooks** | 7 | Delegation guard, telemetry, verification |\n| **CLI Tools** | 3 | omc, omo, ast-grep |\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eCore Agent — Boss meta-orchestrator (1)\u003c/strong\u003e\u003c/summary\u003e\n\n| Agent | Model | Role | Source |\n|-------|-------|------|--------|\n| Boss | Opus | Dynamic runtime discovery → capability matching → optimal routing. Never writes code. | my-claude |\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eOMO Agents — Sub-orchestrators and specialists (9)\u003c/strong\u003e\u003c/summary\u003e\n\n| Agent | Model | Role | Source |\n|-------|-------|------|--------|\n| Sisyphus | Opus | Intent classification → specialist delegation → verification | [oh-my-openagent](https://github.com/code-yeongyu/oh-my-openagent) |\n| Hephaestus | Opus | Autonomous explore → plan → execute → verify | oh-my-openagent |\n| Atlas | Opus | Task decomposition + 4-stage QA verification | oh-my-openagent |\n| Oracle | Opus | Strategic technical consulting (read-only) | oh-my-openagent |\n| Metis | Opus | Intent analysis, ambiguity detection | oh-my-openagent |\n| Momus | Opus | Plan feasibility review | oh-my-openagent |\n| Prometheus | Opus | Interview-based detailed planning | oh-my-openagent |\n| Librarian | Sonnet | Open-source documentation search via MCP | oh-my-openagent |\n| Multimodal-Looker | Sonnet | Image/screenshot/diagram analysis | oh-my-openagent |\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eOMC Agents — Specialist workers (19)\u003c/strong\u003e\u003c/summary\u003e\n\n| Agent | Role | Source |\n|-------|------|--------|\n| analyst | Pre-analysis before planning | [oh-my-claudecode](https://github.com/Yeachan-Heo/oh-my-claudecode) |\n| architect | System design and architecture | oh-my-claudecode |\n| code-reviewer | Focused code review | oh-my-claudecode |\n| code-simplifier | Code simplification and cleanup | oh-my-claudecode |\n| critic | Critical analysis, alternative proposals | oh-my-claudecode |\n| debugger | Focused debugging | oh-my-claudecode |\n| designer | UI/UX design guidance | oh-my-claudecode |\n| document-specialist | Documentation writing | oh-my-claudecode |\n| executor | Task execution | oh-my-claudecode |\n| explore | Codebase exploration | oh-my-claudecode |\n| git-master | Git workflow management | oh-my-claudecode |\n| planner | Rapid planning | oh-my-claudecode |\n| qa-tester | Quality assurance testing | oh-my-claudecode |\n| scientist | Research and experimentation | oh-my-claudecode |\n| security-reviewer | Security review | oh-my-claudecode |\n| test-engineer | Test writing and maintenance | oh-my-claudecode |\n| tracer | Execution tracing and analysis | oh-my-claudecode |\n| verifier | Final verification | oh-my-claudecode |\n| writer | Content and documentation | oh-my-claudecode |\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eAgency Engineering — Always-loaded specialists (26)\u003c/strong\u003e\u003c/summary\u003e\n\n| Agent | Role | Source |\n|-------|------|--------|\n| AI Engineer | AI/ML engineering | [agency-agents](https://github.com/msitarzewski/agency-agents) |\n| Backend Architect | Backend architecture | agency-agents |\n| CMS Developer | CMS development | agency-agents |\n| Code Reviewer | Code review | agency-agents |\n| Data Engineer | Data engineering | agency-agents |\n| Database Optimizer | Database optimization | agency-agents |\n| DevOps Automator | DevOps automation | agency-agents |\n| Embedded Firmware Engineer | Embedded firmware | agency-agents |\n| Frontend Developer | Frontend development | agency-agents |\n| Git Workflow Master | Git workflow | agency-agents |\n| Incident Response Commander | Incident response | agency-agents |\n| Mobile App Builder | Mobile apps | agency-agents |\n| Rapid Prototyper | Rapid prototyping | agency-agents |\n| Security Engineer | Security engineering | agency-agents |\n| Senior Developer | Senior development | agency-agents |\n| Software Architect | Software architecture | agency-agents |\n| SRE | Site reliability | agency-agents |\n| Technical Writer | Technical docs | agency-agents |\n| AI Data Remediation Engineer | Self-healing data pipelines | agency-agents |\n| Autonomous Optimization Architect | API performance governance | agency-agents |\n| Email Intelligence Engineer | Email data extraction | agency-agents |\n| Feishu Integration Developer | Feishu/Lark platform | agency-agents |\n| Filament Optimization Specialist | Filament PHP optimization | agency-agents |\n| Solidity Smart Contract Engineer | EVM smart contracts | agency-agents |\n| Threat Detection Engineer | SIEM \u0026 threat hunting | agency-agents |\n| WeChat Mini Program Developer | WeChat 小程序 | agency-agents |\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eAgent Packs — On-demand domain specialists (136)\u003c/strong\u003e\u003c/summary\u003e\n\nInstalled to `~/.claude/agent-packs/`. Activate by symlinking:\n\n```bash\nln -s ~/.claude/agent-packs/marketing/*.md ~/.claude/agents/\n```\n\n| Pack | Count | Examples | Source |\n|------|------:|---------|--------|\n| marketing | 29 | Douyin, Xiaohongshu, TikTok, SEO | [agency-agents](https://github.com/msitarzewski/agency-agents) |\n| specialized | 28 | Legal, Finance, Healthcare, MCP Builder | agency-agents |\n| game-development | 20 | Unity, Unreal, Godot, Roblox | agency-agents |\n| design | 8 | Brand, UI, UX, Visual Storytelling | agency-agents |\n| testing | 8 | API, Accessibility, Performance | agency-agents |\n| sales | 8 | Deal Strategy, Pipeline Analysis | agency-agents |\n| paid-media | 7 | Google Ads, Meta Ads, Programmatic | agency-agents |\n| project-management | 6 | Scrum, Kanban, Risk Management | agency-agents |\n| spatial-computing | 6 | visionOS, WebXR, Metal | agency-agents |\n| support | 6 | Analytics, Infrastructure, Legal | agency-agents |\n| academic | 5 | Anthropologist, Historian, Psychologist | agency-agents |\n| product | 5 | Product Manager, Sprint, Feedback | agency-agents |\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eSkills — 200+ from 6 sources\u003c/strong\u003e\u003c/summary\u003e\n\n| Source | Count | Key Skills |\n|--------|------:|------------|\n| [everything-claude-code](https://github.com/affaan-m/everything-claude-code) | 180+ | tdd-workflow, autopilot, ralph, security-review, coding-standards |\n| [oh-my-claudecode](https://github.com/Yeachan-Heo/oh-my-claudecode) | 36 | plan, team, trace, deep-dive, blueprint, ultrawork |\n| [gstack](https://github.com/garrytan/gstack) | 40 | /qa, /review, /ship, /cso, /investigate, /office-hours |\n| [superpowers](https://github.com/obra/superpowers) | 14 | brainstorming, systematic-debugging, TDD, parallel-agents |\n| [my-claude Core](https://github.com/sehoon787/my-claude) | 3 | boss-advanced, gstack-sprint, briefing-vault |\n| [Anthropic Official](https://github.com/anthropics/skills) | 14+ | pdf, docx, pptx, xlsx, canvas-design, mcp-builder |\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eMCP Servers (3) + Hooks (7)\u003c/strong\u003e\u003c/summary\u003e\n\n**MCP Servers**\n\n| Server | Purpose | Cost |\n|--------|---------|------|\n| \u003cimg src=\"https://context7.com/favicon.ico\" width=\"16\" height=\"16\" align=\"center\"/\u003e [Context7](https://mcp.context7.com) | Real-time library documentation | Free |\n| \u003cimg src=\"https://exa.ai/images/favicon-32x32.png\" width=\"16\" height=\"16\" align=\"center\"/\u003e [Exa](https://mcp.exa.ai) | Semantic web search | Free 1k req/month |\n| \u003cimg src=\"https://www.google.com/s2/favicons?domain=grep.app\u0026sz=32\" width=\"16\" height=\"16\" align=\"center\"/\u003e [grep.app](https://mcp.grep.app) | GitHub code search | Free |\n\n**Behavioral Hooks**\n\n| Hook | Event | Behavior |\n|------|-------|----------|\n| Session Setup | SessionStart | Auto-detects missing tools + injects Briefing Vault context |\n| Delegation Guard | PreToolUse | Blocks Boss from directly modifying files |\n| Agent Telemetry | PostToolUse | Logs agent usage to `agent-usage.jsonl` |\n| Subagent Verifier | SubagentStop | Forces independent verification + logs to Briefing Vault |\n| Completion Check | Stop | Runs profile fallback + guards /boss-briefing execution |\n| Teammate Idle Guide | TeammateIdle | Prompts leader on idle teammates |\n| Task Quality Gate | TaskCompleted | Verifies deliverable quality |\n| Vault Reminder | UserPromptSubmit | Suggests /boss-briefing after 5+ messages |\n\n\u003c/details\u003e\n\n---\n\n## \u003cimg src=\"https://obsidian.md/images/obsidian-logo-gradient.svg\" width=\"24\" height=\"24\" align=\"center\"/\u003e Briefing Vault\n\nObsidian-compatible persistent memory. Every project maintains a `.briefing/` directory that auto-populates across sessions.\n\n```\n.briefing/\n├── INDEX.md                          ← Project context (auto-created once)\n├── state.json                        ← Session metadata, counters, lastVaultSync (auto-managed)\n├── sessions/\n│   ├── YYYY-MM-DD-\u003ctopic\u003e.md        ← AI-written session summary (enforced)\n│   └── YYYY-MM-DD-auto.md           ← Auto-generated scaffold (git diff, agent stats)\n├── decisions/\n│   └── YYYY-MM-DD-\u003cdecision\u003e.md     ← AI-written decision record (enforced)\n├── learnings/\n│   ├── YYYY-MM-DD-\u003cpattern\u003e.md      ← AI-written learning note\n│   └── YYYY-MM-DD-auto-session.md   ← Auto-generated scaffold (agents, files)\n├── references/\n│   └── auto-links.md                ← Auto-collected URLs from web searches\n├── archives/                         ← PARA: completed/inactive notes (flat)\n├── wiki/                             ← LLM-wiki: concept pages\n│   └── _schema.md\n├── agents/\n│   ├── agent-log.jsonl              ← Subagent execution telemetry\n│   └── YYYY-MM-DD-summary.md        ← Daily agent usage breakdown\n└── persona/\n    ├── profile.md                   ← Agent affinity stats (auto-updated)\n    ├── suggestions.jsonl            ← Routing suggestions (auto-generated)\n    └── rules/                       ← Workflow pattern rules (workflow-*.md)\n```\n\n### Sub-Vaults\n\n| Path | Description |\n|------|-------------|\n| `INDEX.md` | Project overview with links to recent decisions and learnings. Auto-created on first session, refreshed by /boss-briefing or Stop hook fallback. |\n| `state.json` | Session metadata: counters (workCounter, messageCount), lastVaultSync timestamp, sessionStartHead. Auto-managed by hooks. |\n| `sessions/` | **Session summaries.** `*-auto.md` — scaffold with git diff stats and agent counts. `\u003ctopic\u003e.md` — AI-written summary enforced by Stop hook guard. |\n| `decisions/` | **Architecture and design decisions** with rationale. AI-written, enforced during active work. |\n| `learnings/` | **Patterns, gotchas, non-obvious solutions.** `*-auto-session.md` — scaffold with file lists. `\u003ctopic\u003e.md` — AI-written. |\n| `references/` | **Web research URLs.** `auto-links.md` — auto-collected from WebSearch/WebFetch calls. |\n| `agents/` | **Agent telemetry.** `agent-log.jsonl` — per-call log with enriched fields `{ts, agent_type, phase, seq, task_hint}`. `YYYY-MM-DD-summary.md` — daily usage breakdown. |\n| `persona/` | **User work style profile.** `profile.md` — tool affinity stats. `suggestions.jsonl` — routing recommendations. Workflow sequence patterns in `rules/workflow-*.md`. Run /boss-briefing to analyze. |\n| `archives/` | PARA Archives — completed sessions (30+ days), superseded decisions, inactive learnings |\n| `wiki/` | LLM-wiki concept pages — distilled knowledge from multiple sessions |\n\n### Knowledge Management (v2)\n\nBriefingVault v2 integrates three knowledge management methodologies:\n\n| Methodology | Applied As |\n|------------|-----------|\n| **PARA** (Tiago Forte) | Directory structure: sessions=Projects, decisions=Areas, references=Resources, archives=Archives |\n| **Zettelkasten** (Luhmann) | Atomic notes in `learnings/`, unique IDs (`YYYYMMDDHHMMSS`), enforced `[[wiki-links]]` |\n| **LLM-wiki** (Karpathy) | Concept pages in `wiki/` — auto-suggested when keywords appear 3+ times |\n\nClaude Code session-end hooks automatically:\n- Suggest archiving notes older than 30 days\n- Propose wiki pages for frequently mentioned concepts\n- Generate unique Zettelkasten IDs for new notes\n\n### Session-Specific Diffs\n\nAt session start, the current git HEAD is saved to `state.json` (`sessionStartHead` field). For non-git projects, a `YYYY-MM-DD:cwd` identifier is used instead. At session end, diffs are calculated relative to this saved point — showing only changes from the current session, not accumulated uncommitted changes from previous sessions.\n\n### Using with Obsidian\n\n1. Open Obsidian → **Open folder as vault** → select `.briefing/`\n2. Notes appear in graph view, linked by `[[wiki-links]]`\n3. YAML frontmatter (`date`, `type`, `tags`) enables structured search\n4. Timeline of decisions and learnings builds automatically over sessions\n\n### /boss-briefing\n\nRun `/boss-briefing` during or at the end of a session to:\n- **Sync vault**: Update profile.md, INDEX.md, and agent summaries\n- **Detect workflow patterns**: Analyze temporal agent call sequences across sessions\n- **Recover from gaps**: Generate recovery summaries if days have passed since the last session\n- **Propose persona rules**: Suggest workflow-based routing preferences (not just frequency)\n- **Validate session notes**: Check that today's session has a proper summary\n\nThe Stop hook checks whether `/boss-briefing` has run today. If not, it blocks session end with a reminder. The existing `stop-profile-update.js` continues to run as a fallback.\n\n---\n\n## Upstream Open-Source Sources\n\nmy-claude bundles content from 5 MIT-licensed upstream repositories via git submodules:\n\n| # | Source | What It Provides |\n|---|--------|-----------------|\n| 1 | \u003cimg src=\"https://github.com/Yeachan-Heo.png?size=32\" width=\"20\" height=\"20\" align=\"center\"/\u003e **[oh-my-claudecode](https://github.com/Yeachan-Heo/oh-my-claudecode)** — Yeachan Heo | 19 specialist agents + 36 skills. Claude Code multi-agent harness with autopilot, ralph, team orchestration. |\n| 2 | \u003cimg src=\"https://github.com/code-yeongyu.png?size=32\" width=\"20\" height=\"20\" align=\"center\"/\u003e **[oh-my-openagent](https://github.com/code-yeongyu/oh-my-openagent)** — code-yeongyu | 9 OMO agents (Sisyphus, Atlas, Oracle, etc.). Multi-platform agent harness bridging Claude, GPT, Gemini. |\n| 3 | \u003cimg src=\"https://github.com/affaan-m.png?size=32\" width=\"20\" height=\"20\" align=\"center\"/\u003e **[everything-claude-code](https://github.com/affaan-m/everything-claude-code)** — affaan-m | 180+ skills + 87 rules across 14 languages. Comprehensive dev framework with TDD, security, and coding standards. |\n| 4 | \u003cimg src=\"https://github.com/msitarzewski.png?size=32\" width=\"20\" height=\"20\" align=\"center\"/\u003e **[agency-agents](https://github.com/msitarzewski/agency-agents)** — msitarzewski | 26 engineering agents (always loaded) + 136 domain agent-packs across 12 categories. |\n| 5 | \u003cimg src=\"https://github.com/garrytan.png?size=32\" width=\"20\" height=\"20\" align=\"center\"/\u003e **[gstack](https://github.com/garrytan/gstack)** — garrytan | 40 skills for code review, QA, security audit, deployment. Includes Playwright browser daemon. |\n| 6 | \u003cimg src=\"https://github.com/obra.png?size=32\" width=\"20\" height=\"20\" align=\"center\"/\u003e **[superpowers](https://github.com/obra/superpowers)** — Jesse Vincent | 14 skills + 1 agent covering brainstorming, TDD, parallel agents, and code review. |\n| 7 | \u003cimg src=\"https://www.anthropic.com/favicon.ico\" width=\"20\" height=\"20\" align=\"center\"/\u003e **[anthropic/skills](https://github.com/anthropics/skills)** — Anthropic | 14+ official skills for PDF, DOCX, PPTX, XLSX, and MCP builder. |\n| 8 | \u003cimg src=\"https://github.com/forrestchang.png?size=32\" width=\"20\" height=\"20\" align=\"center\"/\u003e **[andrej-karpathy-skills](https://github.com/forrestchang/andrej-karpathy-skills)** — forrestchang | 4 AI coding behavioral guidelines (Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution). |\n\n---\n\n## GitHub Actions\n\n| Workflow | Trigger | Purpose |\n|----------|---------|---------|\n| **CI** | push, PR | Validates JSON configs, agent frontmatter, skill existence, upstream file counts |\n| **Update Upstream** | weekly / manual | Runs `git submodule update --remote` and creates auto-merge PR |\n| **Auto Tag** | push to main | Reads `plugin.json` version and creates git tag if new |\n| **Pages** | push to main | Deploys `docs/index.html` to GitHub Pages |\n| **CLA** | PR | Contributor License Agreement check |\n| **Lint Workflows** | push, PR | Validates GitHub Actions workflow YAML syntax |\n\n---\n\n## my-claude Originals\n\nFeatures built specifically for this project, beyond what upstream sources provide:\n\n| Feature | Description |\n|---------|-------------|\n| **Boss Meta-Orchestrator** | Dynamic capability discovery → intent classification → 5-priority routing → delegation → verification |\n| **3-Phase Sprint** | Design (interactive) → Execute (autonomous via ralph) → Review (interactive vs design doc) |\n| **Agent Tier Priority** | core \u003e omo \u003e omc \u003e agency deduplication. Most specialized agent wins. |\n| **Agency Cost Optimization** | Haiku for advisory, Sonnet for implementation — automatic model routing for 172 domain agents |\n| **Briefing Vault** | Obsidian-compatible `.briefing/` directory with sessions, decisions, learnings, references |\n| **Agent Telemetry** | PostToolUse hook logs agent usage to `agent-usage.jsonl` |\n| **Smart Packs** | Project-type detection recommends relevant agent packs at session start |\n| **CI SHA Pre-check** | Upstream sync skips unchanged sources via `git ls-remote` SHA comparison |\n| **Agent Dedup Detection** | Normalized name comparison catches duplicates across upstream sources |\n\n---\n\n## Bundled Upstream Versions\n\nLinked via git submodules. Pinned commits tracked natively by `.gitmodules`.\n\n| Source | SHA | Date | Diff |\n|--------|-----|------|------|\n| [agency-agents](https://github.com/msitarzewski/agency-agents) | `4feb0cd` | 2026-04-07 | [compare](https://github.com/msitarzewski/agency-agents/compare/4feb0cd...HEAD) |\n| [everything-claude-code](https://github.com/affaan-m/everything-claude-code) | `7dfdbe0` | 2026-04-07 | [compare](https://github.com/affaan-m/everything-claude-code/compare/7dfdbe0...HEAD) |\n| [oh-my-claudecode](https://github.com/Yeachan-Heo/oh-my-claudecode) | `2487d38` | 2026-04-07 | [compare](https://github.com/Yeachan-Heo/oh-my-claudecode/compare/2487d38...HEAD) |\n| [gstack](https://github.com/garrytan/gstack) | `03973c2` | 2026-04-07 | [compare](https://github.com/garrytan/gstack/compare/03973c2...HEAD) |\n| [superpowers](https://github.com/obra/superpowers) | `b7a8f76` | 2026-04-06 | [compare](https://github.com/obra/superpowers/compare/b7a8f76...HEAD) |\n\n---\n\n## Contributing\n\nIssues and PRs are welcome. When adding a new agent, add a `.md` file to `agents/core/` or `agents/omo/` and update `SETUP.md`.\n\n## Credits\n\nBuilt on the work of: [oh-my-claudecode](https://github.com/Yeachan-Heo/oh-my-claudecode) (Yeachan Heo), [oh-my-openagent](https://github.com/code-yeongyu/oh-my-openagent) (code-yeongyu), [everything-claude-code](https://github.com/affaan-m/everything-claude-code) (affaan-m), [agency-agents](https://github.com/msitarzewski/agency-agents) (msitarzewski), [gstack](https://github.com/garrytan/gstack) (garrytan), [superpowers](https://github.com/obra/superpowers) (Jesse Vincent), [anthropic/skills](https://github.com/anthropics/skills) (Anthropic), [andrej-karpathy-skills](https://github.com/forrestchang/andrej-karpathy-skills) (forrestchang).\n\n## License\n\nMIT License. See the [LICENSE](./LICENSE) file for details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsehoon787%2Fmy-claude","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsehoon787%2Fmy-claude","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsehoon787%2Fmy-claude/lists"}