curl -fsSL https://api.cheatcodehq.com/install.sh | sh -s -- oh-my-claudecode --to allCopies 43 skills into each app's skills folder (Claude Code: ~/.claude/skills), after checking every file against Yeachan-Heo/oh-my-claudecode at commit 9fd35ec. Nothing else on your computer changes. To undo it, run the terminal command with --uninstall at the end; that also removes what the app added.
Then start a new session in your AI app and ask for the work in plain words; it picks the skill from its description. In Claude Code you can also type /oh-my-claudecode:agent-doc-discipline.
See it in use
After installing, start a new session and say: Use the omc-review skill to check whether the change in feature.py does what ticket.md asks, explain any problems in plain words, and save the review as review.md.
What else it can do, and its limits
- 43 skills for running Claude Code as a team of agents: planning with interviews, autonomous build loops (autopilot, ralph, team, ultragoal) and review, verify and tracing lanes
- Review lanes: finished work checked for defects, risk and simplification, cleanup of AI written code, and screenshot comparisons against a reference
- Project upkeep: codebase docs, a markdown wiki that carries across sessions, release help and worktree sessions; most of these run commands and need a terminal
- Setup, the status display and Telegram, Discord or Slack notifications need the oh-my-claudecode npm package and those accounts; web research needs web access
- Five Shipyard skills (intake, launch, harbor, navigator, architecture survey) start only when you type them, so they are not shown here
- This review was made by reading the files; the code was not run and came with no tests
Sample input Recorded Oct 24, 2026 in Claude Code 2.1.308 with Sonnet 5.5. The video replays that session; nothing in it was acted or edited.
What's inside 43 skills
agent-doc-disciplineWriting-time discipline for documents agents consume (the five surfaces, specs, tickets, .omc/skills/) — every rule checkable and carrying a why, steps before reference, one meaning in one home, no restating what the environment already says. Mandatory at drydock seed generation and the launch C5 sediment pass; opt-in for any other agent-facing doc edit. The companion of minimal-code-discipline: that one disciplines code, this one disciplines papers.
Writing-time discipline for documents agents consume (the five surfaces, specs, tickets, .omc/skills/) — every rule checkable and carrying a why, steps before reference, one meaning in one home, no restating what the environment already says. Mandatory at drydock seed generation and the launch C5 sediment pass; opt-in for any other agent-facing doc edit. The companion of minimal-code-discipline: that one disciplines code, this one disciplines papers.
ai-slop-cleanerClean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode
Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode
architecture-surveyPeriodic architecture survey — walks the module graph and reports ranked deepening candidates (shallow modules, hypothetical seams, logic behind the wrong seam). Survey, not rescue: it finds candidates and hands them to the captain; it never refactors on its own.
Periodic architecture survey — walks the module graph and reports ranked deepening candidates (shallow modules, hypothetical seams, logic behind the wrong seam). Survey, not rescue: it finds candidates and hands them to the captain; it never refactors on its own.
askProcess-first advisor routing for Claude, Codex, Gemini, Antigravity, Grok, or Cursor via `omc ask`, with artifact capture and no raw CLI assembly
Process-first advisor routing for Claude, Codex, Gemini, Antigravity, Grok, or Cursor via `omc ask`, with artifact capture and no raw CLI assembly
ask-navigatorShipyard's navigator — chart a foggy effort (destination unclear, questions not yet stateable) into a map of decision tickets on the repo's issue tracker, then work the frontier one ticket per session until the way is clear, and hand the collapsed decisions to /launch as a mission brief. Wayfinding, not building: it produces decisions, never deliverables.
Shipyard's navigator — chart a foggy effort (destination unclear, questions not yet stateable) into a map of decision tickets on the repo's issue tracker, then work the frontier one ticket per session until the way is clear, and hand the collapsed decisions to /launch as a mission brief. Wayfinding, not building: it produces decisions, never deliverables.
autopilotFull autonomous execution from idea to working code
Full autonomous execution from idea to working code
autoresearchStateful single-mission improvement loop with strict evaluator contract, markdown decision logs, and max-runtime stop behavior
Stateful single-mission improvement loop with strict evaluator contract, markdown decision logs, and max-runtime stop behavior
cancelCancel any active OMC mode (autopilot, ralph, ultragoal, swarm, ultrapilot, pipeline, team) and clean up retired legacy state
Cancel any active OMC mode (autopilot, ralph, ultragoal, swarm, ultrapilot, pipeline, team) and clean up retired legacy state
Show all 43 skills
configure-notificationsConfigure notification integrations (Telegram, Discord, Slack) via natural language
Configure notification integrations (Telegram, Discord, Slack) via natural language
debugDiagnose the current OMC session or repo state using logs, traces, state, and focused reproduction
Diagnose the current OMC session or repo state using logs, traces, state, and focused reproduction
deep-interviewSocratic deep interview with mathematical ambiguity gating before explicit execution approval
Socratic deep interview with mathematical ambiguity gating before explicit execution approval
deepinitDeep codebase initialization with hierarchical AGENTS.md documentation
Deep codebase initialization with hierarchical AGENTS.md documentation
diagramUse the smallest visual when prose must carry structure—control flow, call depth, module ownership, or change shape: pseudocode, call tree, component/file tree, Mermaid diagram, or diff. Skip it when prose already answers the question.
Use the smallest visual when prose must carry structure—control flow, call depth, module ownership, or change shape: pseudocode, call tree, component/file tree, Mermaid diagram, or diff. Skip it when prose already answers the question.
drydockLay the keel of the shipyard harness in any repo — the 4-pillar shared environment (Context, Rules, Tools, Standards) across 5 surfaces (CLAUDE.md, skills, design-system, mcp/cli, shared context) so that every human and agent inherits the same design language and anyone can ship. Run once per repo; re-run with --check to audit drift.
Lay the keel of the shipyard harness in any repo — the 4-pillar shared environment (Context, Rules, Tools, Standards) across 5 surfaces (CLAUDE.md, skills, design-system, mcp/cli, shared context) so that every human and agent inherits the same design language and anyone can ship. Run once per repo; re-run with --check to audit drift.
executeCarry an approved task through to working, verified code
Carry an approved task through to working, verified code
external-contextInvoke parallel document-specialist agents for external web searches and documentation lookup
Invoke parallel document-specialist agents for external web searches and documentation lookup
graphDeterministic orchestration graph runtime - declarative DAG pipelines with journal-based crash recovery
Deterministic orchestration graph runtime - declarative DAG pipelines with journal-based crash recovery
harborHarbor intake for external work — the captain only handles unresolved decisions. Sweeps incoming issues and PRs, verifies every claim before disposition, reuses every decision already made, and hands the maintainer a docket whose pending items each carry one question with options, recommendation, impact and evidence. Agent-autonomous for facts and for actions covered by standing authorization; signed for every new judgment. Never merges.
Harbor intake for external work — the captain only handles unresolved decisions. Sweeps incoming issues and PRs, verifies every claim before disposition, reuses every decision already made, and hands the maintainer a docket whose pending items each carry one question with options, recommendation, impact and evidence. Agent-autonomous for facts and for actions covered by standing authorization; signed for every new judgment. Never merges.
hudConfigure HUD display options (layout, presets, display elements)
Configure HUD display options (layout, presets, display elements)
intentShipyard's internal requirements intake for non-engineer contributors (support/ops) — turn a pasted chat log or verbal problem report into a five-section intent.md through numbered batch questioning with a completion gate, walk it through tracker review with harbor's four records, and hand the accepted intent to /launch as its mission brief. Produces decisions, not code.
Shipyard's internal requirements intake for non-engineer contributors (support/ops) — turn a pasted chat log or verbal problem report into a five-section intent.md through numbered batch questioning with a completion gate, walk it through tracker review with harbor's four records, and hand the accepted intent to /launch as its mission brief. Produces decisions, not code.
launchShipyard's governed delivery pipeline — converge the mission, synthesize a durable spec, decompose vertical-slice tickets with blocking edges, run the frontier in parallel via team, close with verification, and report with a full decision log. Two entry gates — the yard gate (drydock audit) and the fog gate (an effort whose destination is unclear is routed to /ask-navigator before this pipeline starts). Humans own the checkpoints where there is no unique answer or the error cost is severe; agents continuously run everything repeatable and acceptable-by-evidence.
Shipyard's governed delivery pipeline — converge the mission, synthesize a durable spec, decompose vertical-slice tickets with blocking edges, run the frontier in parallel via team, close with verification, and report with a full decision log. Two entry gates — the yard gate (drydock audit) and the fog gate (an effort whose destination is unclear is routed to /ask-navigator before this pipeline starts). Humans own the checkpoints where there is no unique answer or the error cost is severe; agents continuously run everything repeatable and acceptable-by-evidence.
loftLoft the shape before cutting steel — answer a design question that prose cannot settle by building a throwaway artifact: a pure logic module in a clickable shell, or structurally different UI variants behind one route. The captain reacts to the artifact; the answer folds into the decision; the artifact never docks. Use when a design question stalls in words, when a navigator map carries a loft ticket, or when a spec discussion reaches "we would have to see it".
Loft the shape before cutting steel — answer a design question that prose cannot settle by building a throwaway artifact: a pure logic module in a clickable shell, or structurally different UI variants behind one route. The captain reacts to the artifact; the answer folds into the decision; the artifact never docks. Use when a design question stalls in words, when a navigator map carries a loft ticket, or when a spec discussion reaches "we would have to see it".
minimal-code-disciplineYAGNI-ladder coding discipline for writing changes — existence-first, reuse before writing, dependency ladder, shortest correct diff, with non-negotiables that must never be minimized away
YAGNI-ladder coding discipline for writing changes — existence-first, reuse before writing, dependency ladder, shortest correct diff, with non-negotiables that must never be minimized away
minimal-prose-disciplineWriting-time discipline for the prose an agent speaks to a human (replies, reports, pointers): a protected core never rewritten (code, commands, paths, errors, negators, numbers), filler dies, no narration, auto-clarity where terse misleads
Writing-time discipline for the prose an agent speaks to a human (replies, reports, pointers): a protected core never rewritten (code, commands, paths, errors, negators, numbers), filler dies, no narration, auto-clarity where terse misleads
omc-doctorDiagnose and fix oh-my-claudecode installation issues
Diagnose and fix oh-my-claudecode installation issues
omc-planStrategic planning with optional interview workflow
Strategic planning with optional interview workflow
omc-reviewEvaluate finished work for defects, risk, and simplification before it ships
Evaluate finished work for defects, risk, and simplification before it ships
omc-setupInstall or refresh oh-my-claudecode for plugin, npm, and local-dev setups from the canonical setup flow
Install or refresh oh-my-claudecode for plugin, npm, and local-dev setups from the canonical setup flow
project-session-managerWorktree-first dev environment manager for issues, PRs, and features with optional tmux sessions
Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions
ralphSelf-referential loop until task completion with configurable verification reviewer
Self-referential loop until task completion with configurable verification reviewer
ralplanConsensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution
releaseGeneric release assistant — analyzes repo release rules, caches them in .omc/RELEASE_RULE.md, then guides the release
Generic release assistant — analyzes repo release rules, caches them in .omc/RELEASE_RULE.md, then guides the release
rememberReview reusable project knowledge and decide what belongs in project memory, notepad, or durable docs
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs
researchInvestigate an open question and return grounded, sourced findings
Investigate an open question and return grounded, sourced findings
self-improveAutonomous evolutionary code improvement engine with tournament selection
Autonomous evolutionary code improvement engine with tournament selection
skillManage local skills - list, add, remove, search, edit, setup wizard
Manage local skills - list, add, remove, search, edit, setup wizard
skillifyTurn a repeatable workflow from the current session into a reusable OMC skill draft
Turn a repeatable workflow from the current session into a reusable OMC skill draft
teamN coordinated agents on shared task list using Claude Code implicit agent teams
N coordinated agents on shared task list using Claude Code implicit agent teams
traceEvidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team mode
Evidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team mode
ultragoalDurable multi-goal workflow that persists plan/ledger artifacts under .omc/ultragoal and prints Claude /goal handoff text for the active session
Durable multi-goal workflow that persists plan/ledger artifacts under .omc/ultragoal and prints Claude /goal handoff text for the active session
verifyVerify that a change really works before you claim completion
Verify that a change really works before you claim completion
visual-verdictStructured visual QA verdict for screenshot-to-reference comparisons
Structured visual QA verdict for screenshot-to-reference comparisons
wikiLLM Wiki — persistent markdown knowledge base that compounds across sessions (Karpathy model)
LLM Wiki — persistent markdown knowledge base that compounds across sessions (Karpathy model)
About
Something wrong with this listing, or it did not install? Tell us