darkroom

Plugin darkroom from marketplace cc-settings in darkroomengineering/cc-settings. Commands read from the repo's manifest — today.

Skills (22)

• audit

  Repo audits, one mode or all (codebase, docs, process, perf, tests, state, threat-model, motion, SEO, debt). Triggers "audit the codebase", "full audit", "perf audit", "audit the tests", "find the implicit state machines", "threat model", "motion audit", "seo audit", "debt ledger".

• autoresearch

  Autonomous mutate/score/keep optimization of a SKILL.md prompt. Triggers "autoresearch", "optimize skill", "tune this skill", "evolve this skill".

• case-study

  Turn any web project (WebGL, three.js, React Three Fiber, Theatre.js, GSAP or Lenis scroll sites, plain DOM sites, and browser games or app-like flows) into case-study material for the studio website. Produces frame-perfect 16:9 clips of every chapter and transition (games are played through by a sc

• cc

  Sync cc-settings with Claude Code and Codex upstreams, update a local install, or migrate a project's CLAUDE.md to AGENTS.md. Triggers "sync with claude code", "update cc-settings", "migrate to agents.md".

• codex

  Claude-to-Codex bridge to delegate bulk mechanical work, get an independent cross-model diff review, or ask a read-only question. Triggers only when the user names Codex, as in "use codex", "have codex review", "cross-check with codex", "ask codex".

• component

  Create a UI component. Triggers "create component", "new component", "add component", or naming a component to build (Button, Header, Card).

• context-doc

  Build CONTEXT.md (domain glossary) and docs/adr/ through an interview. Triggers "domain language", "glossary", "ADR", or inconsistent terminology across the codebase.

• dr-init

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

• dr-review

  Review the local diff against Darkroom's checklist, or address feedback on the active PR. Triggers "review my changes", "check this diff", "address PR feedback", "review these tickets". Native /code-review handles a diff or PR without the checklist.

• fix

  Debug and fix a reported defect, such as a failing build or tests, runtime or console errors, regressions, merge conflicts, red PR checks. Triggers "fix", "broken", "not working", "merge conflict", "fix CI".

• freeze

  Block Edit and Write outside one directory for the session to contain debugging or parallel agents. Triggers "freeze edits", "restrict edits to", "only edit this folder", "unfreeze".

• handoff

  Save state at the end of a session or before unrelated work, or resume from the last one. Triggers "wrapping up", "running out of context", "done for today", "switching to unrelated work", "new topic", "continue where we left off", "resume".

• harvest

  Turn proven session behavior into a skill, rule, profile, AGENTS.md diff, or team learning; artifacts seed /autoresearch evals. Triggers "harvest this workflow", "turn this session into a skill", "preserve this behavior".

• orchestrate

  Coordinate agents across plan, implement, test, and review, or fan out 3+ independent workstreams. Triggers "orchestrate", "parallel agents", "fan out", "split work", "overnight", "autonomous task".

• poke-holes

  Adversarial verification with three competing agents (issue-finder, disprover, judge). Triggers "double check", "are you sure", "poke holes", or a critical fix before production.

• proof-of-work

  Run the machine-verifiable gate (typecheck, test, lint, plus a screenshot for UI) so a diff is review-ready. Triggers "proof of work", "is this review-ready", "prove it is green".

• retro

  Weekly engineering retrospective with persistent metrics, or a PR friction retro of where fix effort went. Triggers "retro", "weekly review", "how was my week", "what did I ship", "PR retro", "friction retro", "where did our fixes go".

• review-batch

  Batch-review diffs from several agents with per-change re-entry cards and abridged reading diffs. Triggers "review batch", "what's pending review", "reading diff", or after fanning out several agents.

• share-learning

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

• ship

  Push, open a PR, and watch CI; land mode merges and cleans branches. Triggers "ship it", "create PR", "babysit CI", "land it", "fix CI and merge".

• stories

  Turn a client build's scope into approved user stories, then tickets, kickoff, QA checklist and closing comments in one shared format. Triggers "user stories", "write the tickets", "break this scope into tickets".

• triage

  First-pass, read-only review of a client or unfamiliar repo with ranked glaring issues. Triggers "triage this repo", "point out glaring issues", "first pass on this client repo".

Subagents (11)

• browser

  Reads signed-in or third-party web pages (dashboards, Search Console, analytics, production sites) in its own Chrome and reports what it read. Spawn it without the Agent tool's `name`: a named spawn runs as a teammate, and teammates do not get this agent's Chrome server. RETURNS: pages read, finding

• codex-verifier

  Independent cross-model verification of the current diff via the OpenAI Codex CLI, to catch what Claude self-review misses. Delegate after a risky change when you want a non-Claude opinion. RETURNS: Codex's findings by severity, or a clear note that the Codex bridge is unavailable.

• deslopper

  Code cleanup: auto-removes only dead code and slop comments, and reports duplication and consolidation opportunities for approval. Delegate after an implementer finishes and before a push, or to find dead or duplicated code. Supports team mode for large codebases. RETURNS: dead code removed, and con

• explore

  Read-only codebase research: where things live, how they work, what a change would touch, plus library docs lookup. Delegate before making changes, for blast-radius questions, or when the answer needs file:line evidence. RETURNS: file locations, architecture and dependency maps, and evidence-based a

• implementer

  Executes code changes and tests. Delegate for implementation, builds, fixes, updates, or a planner roadmap. Prompts must inline the ask, exact paths/ranges, concrete change, verification plus expected result, boundaries, escape hatches, any port source contract, and rejected attempts; incomplete pro

• linear

  Linear bookkeeping for one unit of work in a repo with a Linear mapping: find or create its issue, move the status with the work, keep its checklist and progress comments current, and file follow-up issues. Spawn at each milestone: kickoff, plan or scope change, PR opened, CI result, ready for revie

• maestro

  Multi-agent orchestrator for work spanning 3+ agents or parallel workstreams: full features, large refactors, multi-perspective debugging. Delegate when coordination, not a single specialist, is the bottleneck. RETURNS: orchestration status, synthesized sub-agent results, and progress tracking.

• planner

  Task breakdown and architecture planning without implementation. Delegate before any multi-file change or complex feature, or to compare approaches. RETURNS: a Functional DAG, numbered phased tasks, ADRs, and risk assessments.

• reviewer

  Read-only code review against Darkroom standards. Delegate after a change lands or for a PR review. RETURNS: review summary, issues by severity (Critical/Warning/Suggestion) with confidence and origin, approval status.

• security-reviewer

  Static security audit: OWASP Top 10, secrets, dependencies, auth flows. Delegate before deploying or merging sensitive changes (auth, payments, crypto, input validation). RETURNS: security report by severity (Critical/High/Medium), secret-scan results, remediation steps. Run the Workflow step 1 scan

• tester

  Writes and runs tests, and reports coverage gaps. Delegate for new test files, test runs, or verification after implementation. RETURNS: test results (pass/fail/skip), test files, failure analysis, coverage gaps. - chrome-devtools: type: stdio command: bunx args: ["-y", "[email protected]",

MCP servers (3)

• figma

  connects to: https://mcp.figma.com/mcp

• context7

  connects to: https://mcp.context7.com/mcp/oauth

• chrome-devtools

  runs: bunx -y [email protected] --no-usage-statistics

Hooks (4)

• PreToolUse

  bun "$PLUGIN_ROOT/src/scripts/codex-hook.ts" "src/hooks/safety-net.ts"

• UserPromptSubmit

  bun "$PLUGIN_ROOT/src/scripts/codex-hook.ts" "src/hooks/delegation-detector.ts"

• PreCompact

  bun "$PLUGIN_ROOT/src/scripts/codex-hook.ts" "src/scripts/handoff.ts" create --from-hook

• SessionEnd

  bun "$PLUGIN_ROOT/src/scripts/codex-hook.ts" "src/scripts/handoff.ts" create --from-hook

Similar plugins