OMC agent catalog, available tools, team pipeline routing, commit protocol, and skills registry. Auto-loads when delegating to agents, using OMC tools, orchestrating teams, making commits, or invoking skills.
Use this built-in reference when you need detailed OMC catalog information that does not need to live in every CLAUDE.md session.
Prefix: oh-my-claudecode:. See agents/*.md for full prompts.
explore (haiku) — fast codebase search and mappinganalyst (opus) — requirements clarity and hidden constraintsplanner (opus) — sequencing and execution plansarchitect (opus) — system design, boundaries, and long-horizon tradeoffsdebugger (sonnet) — root-cause analysis and failure diagnosisexecutor (sonnet) — implementation and refactoringverifier (sonnet) — completion evidence and validationtracer (sonnet) — trace gathering and evidence capturesecurity-reviewer (sonnet) — trust boundaries and vulnerabilitiescode-reviewer (opus) — comprehensive code reviewtest-engineer (sonnet) — testing strategy and regression coveragedesigner (sonnet) — UX and interaction designwriter (haiku) — documentation and concise content workqa-tester (sonnet) — runtime/manual validationscientist (sonnet) — data analysis and statistical reasoningdocument-specialist (sonnet) — SDK/API/framework documentation lookupgit-master (sonnet) — commit strategy and history hygienecode-simplifier (opus) — behavior-preserving simplificationcritic (opus) — plan/design challenge and reviewhaiku — quick lookups, lightweight inspection, narrow docs worksonnet — standard implementation, debugging, and reviewopus — architecture, deep analysis, consensus planning, and high-risk review/team N:executor "task"omc team N:codex|gemini "..."omc ask <claude|codex|gemini>/ccgstate_read, state_write, state_clear, state_list_active, state_get_statusTeamCreate, TeamDelete, SendMessage, TaskCreate, TaskList, TaskGet, TaskUpdatenotepad_read, notepad_write_priority, notepad_write_working, notepad_write_manualproject_memory_read, project_memory_write, project_memory_add_note, project_memory_add_directivelsp_hover, lsp_goto_definition, lsp_find_references, lsp_diagnostics, and related helpersast_grep_search, ast_grep_replacepython_replInvoke built-in workflows via /oh-my-claudecode:<name>.
autopilot — full autonomous execution from idea to working coderalph — persistence loop until completion with verificationultrawork — high-throughput parallel executionvisual-verdict — structured visual QA verdictsteam — coordinated team orchestrationccg — Codex + Gemini + Claude synthesis laneultraqa — QA cycle: test, verify, fix, repeatomc-plan — planning workflow and /plan-safe aliasralplan — consensus planning workflowsciomc — science/research workflowexternal-context — external docs/research workflowdeepinit — hierarchical AGENTS.md generationdeep-interview — Socratic ambiguity-gated requirements workflowai-slop-cleaner — regression-safe cleanup workflowask, cancel, note, learner, omc-setup, mcp-setup, hud, omc-doctor, trace, release, project-session-manager, skill, writer-memory, configure-notifications"autopilot"→autopilot"ralph"→ralph"ulw"→ultrawork"ccg"→ccg"ralplan"→ralplan"deep interview"→deep-interview"deslop" / "anti-slop"→ai-slop-cleaner"deep-analyze"→analysis mode"tdd"→TDD mode"deepsearch"→codebase search"ultrathink"→deep reasoning"cancelomc"→cancel/team.Stages: team-plan → team-prd → team-exec → team-verify → team-fix (loop).
team-fix for bounded remediation loops.team ralph links the team pipeline with Ralph-style sequential verification.Use git trailers to preserve decision context in every commit message.
Constraint: active constraint shaping the decisionRejected: alternative considered | reason for rejectionDirective: forward-looking warning or instructionConfidence: high | medium | lowScope-risk: narrow | moderate | broadNot-tested: known verification gapfeat(docs): reduce always-loaded OMC instruction footprint
Move reference-only orchestration content into a native Claude skill so
session-start guidance stays small while detailed OMC reference remains available.
Constraint: Preserve CLAUDE.md marker-based installation flow
Rejected: Sync all built-in skills in legacy install | broader behavior change than issue requires
Confidence: high
Scope-risk: narrow
Not-tested: End-to-end plugin marketplace install in a fresh Claude profile