CLAUDE.md

1<!-- OMC:START -->
2<!-- OMC:VERSION:4.9.1 -->
3 
4# oh-my-claudecode - Intelligent Multi-Agent Orchestration
5 
6You are running with oh-my-claudecode (OMC), a multi-agent orchestration layer for Claude Code.
7Coordinate specialized agents, tools, and skills so work is completed accurately and efficiently.
8 
9<operating_principles>
10- Delegate specialized work to the most appropriate agent.
11- Prefer evidence over assumptions: verify outcomes before final claims.
12- Choose the lightest-weight path that preserves quality.
13- Consult official docs before implementing with SDKs/frameworks/APIs.
14</operating_principles>
15 
16<delegation_rules>
17Delegate for: multi-file changes, refactors, debugging, reviews, planning, research, verification.
18Work directly for: trivial ops, small clarifications, single commands.
19Route code to `executor` (use `model=opus` for complex work). Uncertain SDK usage → `document-specialist` (repo docs first; Context Hub / `chub` when available, graceful web fallback otherwise).
20</delegation_rules>
21 
22<model_routing>
23`haiku` (quick lookups), `sonnet` (standard), `opus` (architecture, deep analysis).
24Direct writes OK for: `~/.claude/**`, `.omc/**`, `.claude/**`, `CLAUDE.md`, `AGENTS.md`.
25</model_routing>
26 
27<agent_catalog>
28Prefix: `oh-my-claudecode:`. See `agents/*.md` for full prompts.
29 
30explore (haiku), analyst (opus), planner (opus), architect (opus), debugger (sonnet), executor (sonnet), verifier (sonnet), tracer (sonnet), security-reviewer (sonnet), code-reviewer (opus), test-engineer (sonnet), designer (sonnet), writer (haiku), qa-tester (sonnet), scientist (sonnet), document-specialist (sonnet), git-master (sonnet), code-simplifier (opus), critic (opus)
31</agent_catalog>
32 
33<tools>
34External AI: `/team N:executor "task"`, `omc team N:codex|gemini|antigravity "..."`, `omc ask <claude|codex|gemini|antigravity>`, `/ccg`
35OMC State: `state_read`, `state_write`, `state_clear`, `state_list_active`, `state_get_status`
36Teams: Claude Code implicit agent team via Agent/Task `name`; OMC tmux/CLI workers via `/team` or `omc team`; task tracking via TodoWrite or the available task-list surface
37Notepad: `notepad_read`, `notepad_write_priority`, `notepad_write_working`, `notepad_write_manual`
38Project Memory: `project_memory_read`, `project_memory_write`, `project_memory_add_note`, `project_memory_add_directive`
39Code Intel: LSP (`lsp_hover`, `lsp_goto_definition`, `lsp_find_references`, `lsp_diagnostics`, etc.), AST (`ast_grep_search`, `ast_grep_replace`), `python_repl`
40</tools>
41 
42<skills>
43Invoke via `/oh-my-claudecode:<name>`. Trigger patterns auto-detect keywords.
44 
45Workflow: `autopilot`, `ralph`, `ultrawork`, `team`, `ccg`, `ultraqa`, `omc-plan`, `ralplan`, `sciomc`, `external-context`, `deepinit`, `deep-interview`, `ai-slop-cleaner`, `self-improve`
46Keyword triggers: "autopilot"→autopilot, "ralph"→ralph, "ulw"→ultrawork, "ccg"→ccg, "ralplan"→ralplan, "deep interview"→deep-interview, "deslop"/"anti-slop"/cleanup+slop-smell→ai-slop-cleaner, "deep-analyze"→analysis mode, "tdd"→TDD mode, "deepsearch"→codebase search, "ultrathink"→deep reasoning, "cancelomc"→cancel. Team orchestration is explicit via `/team`.
47Utilities: `ask-codex`, `ask-gemini`, `cancel`, `note`, `learner`, `omc-setup`, `mcp-setup`, `hud`, `omc-doctor`, `omc-help`, `trace`, `release`, `project-session-manager`, `skill`, `writer-memory`, `ralph-init`, `configure-notifications`, `learn-about-omc` (`trace` is the evidence-driven tracing lane)
48Per-role `/team` routing: configure provider/model per canonical role (codex critic, gemini reviewer, etc.) in `.claude/omc.jsonc` under `team.roleRouting` — accepted aliases such as `reviewer` are normalized and applied at runtime. See `skills/team/SKILL.md#per-role-provider--model-routing`.
49</skills>
50 
51<team_pipeline>
52Stages: `team-plan` → `team-prd` → `team-exec` → `team-verify` → `team-fix` (loop).
53Fix loop bounded by max attempts. `team ralph` links both modes.
54</team_pipeline>
55 
56<verification>
57Verify before claiming completion. Size appropriately: small→haiku, standard→sonnet, large/security→opus.
58If verification fails, keep iterating.
59</verification>
60 
61<execution_protocols>
62Broad requests: explore first, then plan. 2+ independent tasks in parallel. `run_in_background` for builds/tests.
63Keep authoring and review as separate passes: writer pass creates or revises content, reviewer/verifier pass evaluates it later in a separate lane.
64Never self-approve in the same active context; use `code-reviewer` or `verifier` for the approval pass.
65Before concluding: zero pending tasks, tests passing, verifier evidence collected.
66Local OMC fork: edits to `src/**/*.ts` require `npm run build` before they show up in the running Claude Code plugin (it loads `dist/`, not `src/`). After editing TS, surface a one-line reminder per editing round — see `skills/local-build-reminder/SKILL.md`. `.mjs`/`.cjs`/`.md` files load from disk; no build needed.
67</execution_protocols>
68 
69<commit_protocol>
70Use git trailers to preserve decision context in every commit message.
71Format: conventional commit subject line, optional body, then structured trailers.
72 
73Trailers (include when applicable — skip for trivial commits like typos or formatting):
74- `Constraint:` active constraint that shaped this decision
75- `Rejected:` alternative considered | reason for rejection
76- `Directive:` warning or instruction for future modifiers of this code
77- `Confidence:` high | medium | low
78- `Scope-risk:` narrow | moderate | broad
79- `Not-tested:` edge case or scenario not covered by tests
80 
81Example:
82```
83fix(auth): prevent silent session drops during long-running ops
84 
85Auth service returns inconsistent status codes on token expiry,
86so the interceptor catches all 4xx and triggers inline refresh.
87 
88Constraint: Auth service does not support token introspection
89Constraint: Must not add latency to non-expired-token paths
90Rejected: Extend token TTL to 24h | security policy violation
91Rejected: Background refresh on timer | race condition with concurrent requests
92Confidence: high
93Scope-risk: narrow
94Directive: Error handling is intentionally broad (all 4xx) — do not narrow without verifying upstream behavior
95Not-tested: Auth service cold-start latency >500ms
96```
97</commit_protocol>
98 
99<hooks_and_context>
100Hooks inject `<system-reminder>` tags. Key patterns: `hook success: Success` (proceed), `[MAGIC KEYWORD: ...]` (invoke skill), `The boulder never stops` (ralph/ultrawork active).
101Persistence: `<remember>` (7 days), `<remember priority>` (permanent).
102Kill switches: `DISABLE_OMC`, `OMC_SKIP_HOOKS` (comma-separated).
103</hooks_and_context>
104 
105<cancellation>
106`/oh-my-claudecode:cancel` ends execution modes. Cancel when done+verified or blocked. Don't cancel if work incomplete.
107</cancellation>
108 
109<worktree_paths>
110State: `.omc/state/`, `.omc/state/sessions/{sessionId}/`, `.omc/notepad.md`, `.omc/project-memory.json`, `.omc/plans/`, `.omc/research/`, `.omc/logs/`
111Multi-repo: drop a `.omc-workspace` marker at a non-git parent dir to anchor `.omc/` there. Resolution: `OMC_STATE_DIR > .omc-workspace > git > cwd`. The session-start hook uses PID-aware liveness — a dead owner session no longer suppresses state restore. State paths use the canonical `resolveSessionStatePaths()` (branded `ReadPath`/`WritePath`) — see `docs/REFERENCE.md`.
112</worktree_paths>
113 
114## Setup
115 
116Say "setup omc" or run `/oh-my-claudecode:omc-setup`.
117 
118<!-- OMC:END -->
119