cc-settings

Lock file edits to one directory for the session — Edit/Write outside it are blocked, not just warned. Use when debugging to stop accidental edits to unrelated code, or to fence a parallel agent to one module. Triggers "freeze edits", "lock editing scope", "restrict edits to", "only edit this folder", "unfreeze", "lift the freeze".

Lighthouse audit + improvement loop until targets met. Triggers "lighthouse", "performance audit", "page speed", "improve scores", "LCP", "CLS", "INP", "core web vitals".

Extremely strict whole-codebase maintainability audit — checks structural quality, 1k-line file sprawl, thin wrappers, leaked logic, spaghetti growth, and dependency freshness + usage quality via context7. Pushes "code-judo" moves that delete whole branches instead of rearranging them. When fixes land, the same pass updates CHANGELOG, MANUAL, and derived schemas so the docs don't drift. Triggers "nuclear review", "thermonuclear review", "thermo-nuclear code quality review", "code judo", "deep code quality audit", "harsh maintainability review", "whole codebase review". Sibling to `/review` (per-diff Darkroom checklist) and `/zero-tech-debt` (rework patch to end-state).

Adversarial whole-repo audits in three goal-spec modes — hunt defects, drift, and dead ends rather than validate. Triggers "adversarial audit", "fable audit", "audit the codebase", "expectation gaps" (codebase mode - correctness, incoherences, affordance mismatches); "audit the docs", "docs audit", "documentation audit", "doc drift" (docs mode - accuracy vs code, inverted pyramid, doc sizing, diagram backlog); "process audit", "audit the workflows", "walk the journeys", "end-to-end audit" (process mode - empirical journey walking, state-machine map, dead ends, re-run semantics). Sibling to /nuclear-review (maintainability + code-judo deletion) - this skill audits whether the system does what it promises, not whether it should exist.

CEO/founder-mode plan review. Stress-tests plans through a product lens. Use when: - User says "ceo review", "founder review", "product review" - User wants to challenge whether they're solving the right problem - User asks "is this the right approach?", "should we even build this?" - Before committing to a large feature or architectural change - User wants to evaluate a plan from a product/business perspective

Local pre-commit review of unstaged/staged diff against the Darkroom quality checklist (TypeScript, React, a11y, perf, security). Also summarizes inbound PR review comments on the active PR. Distinct from native /review which inspects open PRs. Triggers "review my changes", "check this diff", "feedback on this code", "PR comments", "what did reviewers say", "summarize PR feedback", post-implementation self-review before commit.

Product strategy advisor for vision, positioning, and architecture decisions. Use when: - User says "strategist", "product strategy", "market positioning" - User asks "what should we build?", "who is this for?", "how should we position?" - User wants to discuss vision, market, competitive landscape - User needs help connecting architecture/code decisions to product strategy - User mentions "market analysis", "competitive advantage", "product direction"

Verify and publish changes — push, open PR, watch CI until green; land mode merges an existing PR and cleans up. Triggers "ship it", "create PR", "open PR", "ready to merge", "/pr", "/ship", "push and PR", "watch the PR", "babysit CI", "loop until green"; land mode "land it", "/ship land", "fix CI and merge", "merge it then clean the branches", "merge and clean up".

First-pass review of a client or unfamiliar repo — pull latest, sweep for glaring issues, report ranked findings. READ-ONLY on external repos. Triggers "triage this repo", "point out glaring issues", "review the codebase and tell me what needs fixing", "first pass on this client repo".

Mid-task rollback points — save/restore state before risky ops (refactors, migrations, destructive edits). For end-of-session save use `/handoff`. Triggers "checkpoint", "snapshot", "before this risky op", "rollback to", "list checkpoints", pre-refactor save.

End-of-session save and next-session resume. Triggers "ending session", "wrapping up", "context window", "running out of context", "done for today" (save mode); "continue where we left off", "pick up where", "last session", "previous work", "resume" (resume mode).

Expert opinions from the oracle agent — freeform advice, risk analysis, or weighted comparison of approaches. Triggers "what should I", "how should I", "advice on" (advice mode); "what could go wrong", "risks", "potential issues", "premortem" (risks mode); "compare approaches", "which is better", "evaluate options", "trade-off analysis", "tech selection", "decide between" (compare mode).

Visual + a11y QA — screenshot-first critique, contrast, touch targets, mockup-vs-impl diff. For adversarial logic checks use `/verify`. Triggers "visual QA", "QA check", "does this look right", "a11y check", "contrast check", post-component changes.

Autonomous skill-prompt optimization — Karpathy-style mutate/score/keep loop on SKILL.md. Triggers "autoresearch", "optimize skill", "tune", "evolve" a skill, "prompt optimization".

Capture an unusually good workflow into a durable, reviewed artifact — a skill, rule, profile, AGENTS.md diff, or team learning — with measured evidence and an explicit contract. Runs a witnessed-behavior census (multi-witness vs single-witness), fills a harvest contract, validates with blind trap prompts, and emits a PASS / FAIL / INCONCLUSIVE verdict before promotion; seeds /autoresearch when the artifact is a skill. Use when a stronger or temporary model, a one-off session, or a teammate's transcript produced behavior worth preserving before it's lost. Triggers "harvest this workflow", "capture what the model did", "turn this session into a skill", "preserve this behavior", "model handoff", "before we lose access to this model".

Debug and fix bugs/errors/failures, including merge conflicts and failing PR CI checks. Triggers "fix", "broken", "not working", "bug", "error", "failing", "merge conflict", "fix CI", "checks failing", console errors, build/test failures, regression.

Multi-agent coordination across plan/implement/test/review; fan-out for 3+ independent workstreams. Triggers "coordinate", "orchestrate", "complex task", "parallel agents", "split work", "fan out", "multi-instance", large refactor, "overnight", "long running", "autonomous task", "extended task", "marathon", "multi-hour task".

GitHub Issues as PLAN.md replacement — agents read/update them. Auto-invoke on issue-linked branches. Triggers "what's the plan", "project status", "sync with github", "close the issue".

Batch-review the diffs from several agents in one sitting with per-change re-entry cards, instead of cold-reloading one agent at a time. Triggers "review batch", "review all the agents", "what's pending review", "batch review", "catch up on agent work", or after fanning out several agents.

Claude x Codex bridge — delegate mechanical or bulk implementation to the OpenAI Codex CLI, get an independent cross-model review of the current uncommitted diff, or ask Codex a read-only second-opinion question. Triggers "use codex", "have codex do", "have codex review", "have codex check", "codex exec", "second opinion from codex", "cross-check with codex", "delegate to codex", "ask codex". Use when you want a different model family to verify your own diff, parallelize bulk work, or get a fast read-only opinion without spending Claude turns.

Pre-implementation planning — interview to clarify scope, then compile into a PRD. Triggers "help me figure out", "vague scope", "define requirements" (discovery phase); "PRD", "requirements document", "product spec", "feature spec", "write requirements" (PRD phase).

Write/run tests, check coverage, or TDD discipline. Triggers "test", "write tests", "add tests", "run tests", "coverage", "unit test", "integration test", "TDD", "test-first", "red-green-refactor", "bugs-that-must-not-recur"; post-implementation, pre-merge.

Sync cc-settings with upstream Claude Code (maintainer) or pull the latest cc-settings (user). Triggers "sync with claude code", "changelog sync", "upstream sync" (sync mode); "update cc-settings", "refresh my install" (update mode).

Generate OR consolidate design tokens — type scales, color palettes, spacing systems, dark-mode derivations with WCAG checks (generate); or audit-and-reduce an over-grown Tailwind v4 token set with identical render (consolidate). Outputs CSS/Tailwind. Triggers "design tokens", "type scale", "color palette", "theme setup", "reduce tokens", "dedupe tokens", "too many tokens", "consolidate tokens".

TLDR code analysis — call graphs, semantic search, impact, dataflow; ~95% token savings vs raw reads. Use for "who calls X", "what affects X", before large file reads or refactors.

Audit and prune rules/skills/learnings to prevent context bloat. Triggers "consolidate", "clean up rules", "spa day", "what's redundant", degraded agent perf.

Behavior-preserving restructuring of code that is NOT in your current diff — extract modules, rename across files, untangle abstractions, pay down tech debt. For tightening just-changed code use `/zero-tech-debt` instead. Triggers "refactor X", "reorganize this module", "restructure", "extract Y from Z", "pay down tech debt".

Weekly engineering retrospective with persistent metrics. Use when: - User says "retro", "retrospective", "weekly review" - User asks "how was my week?", "engineering metrics", "velocity" - User wants to analyze commit patterns, work sessions, or code quality trends - User says "what did I ship?", "show me my stats"

Run the machine-verifiable gate (typecheck/test/lint, plus a screenshot for UI) so an agent's diff is "review-ready" before it reaches a human. Triggers "proof of work", "is this review-ready", "verify before review", "prove it is green", or after an agent finishes a diff-producing task.

Adversarial verification — three competing agents (issue-finder, disprover, judge). Triggers "verify", "double check", "are you sure", "poke holes"; pre-prod, post-critical-fix.

Promote a team-relevant learning to the shared team-knowledge repo, deduping against existing notes first. Triggers "share this", "promote to the team repo", "add to the knowledge base", or after a gotcha/decision/convention worth team-wide awareness.

Rework a patch from its intended end-state, not from the historical path that produced it — delete compat cruft, mode flags, fallbacks, and wrappers no one calls anymore. Triggers "zero tech debt", "rewrite as if from scratch", "delete the compat layer", "kill the legacy path", "this has too many flags", or when a feature has accreted mode props and shims over multiple iterations and you want the shape it should have shipped with.

Initialize new Darkroom project from a satus or novus starter (NOT the same as native /init which writes CLAUDE.md). Triggers "new darkroom project", "satus", "novus", "scaffold from starter".

Build feature/page/integration end-to-end with GO/NO-GO gate. For components use `/component`, hooks `/hook`. Triggers "build a feature/page", "implement feature", "add feature", "build integration".

Create UI component / widget / reusable piece. Triggers "create component", "new component", "add component", or naming a component (Button, Header, Card).

Create reusable React hook (useX pattern). Triggers "create hook", "new hook", "custom hook", "useAuth"/"useScroll"-style names, extracting logic from a component.

Build CONTEXT.md (domain glossary) + docs/adr/ via interview; keeps agent vocab aligned. Triggers "domain language", "glossary", "ADR", inconsistent terminology.

Read-only codebase investigation via Explore agent; also handles upward-zoom for unfamiliar code regions. Triggers "how does X work", "where is X", "find X", "understand X", "navigate codebase", "zoom out", "bigger picture", "where does this fit".