duart-555/claude-code-setup
Claude Code setup: agents, skills, hooks, rules, commands, memory system, plugins, MCP servers. Clone and run install.sh.
field: unknown workflow: Planning & specsFrontend & designSecurity reviewPR / code reviewTesting & TDD
ARCHETYPE
Fort Knox
Deny lists, pre-tool hooks, sandboxing. Nothing touches prod without a signature.
GUARDRAILS
4/5
Blocks destructive commands · Protects secrets · Pre-tool screening hook · No YOLO mode · details
Quality 17/100 Guardrails v2
Copy this rig
# review before running: this installs third-party code $ npx degit duart-555/claude-code-setup/agents ./rig-claude-code-setup/agents $ npx degit duart-555/claude-code-setup/commands ./rig-claude-code-setup/commands $ npx degit duart-555/claude-code-setup/skills ./rig-claude-code-setup/skills $ npx degit duart-555/claude-code-setup/hooks ./rig-claude-code-setup/hooks
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit duart-555/claude-code-setup/skills/accessibility .claude/skills/accessibility $ npx degit duart-555/claude-code-setup/skills/agent-reach .claude/skills/agent-reach $ npx degit duart-555/claude-code-setup/skills/agentic-engineering .claude/skills/agentic-engineering $ npx degit duart-555/claude-code-setup/skills/api-design .claude/skills/api-design $ npx degit duart-555/claude-code-setup/skills/apple-design-hig .claude/skills/apple-design-hig $ npx degit duart-555/claude-code-setup/skills/apple-design .claude/skills/apple-design $ npx degit duart-555/claude-code-setup/skills/architecture-decision-records .claude/skills/architecture-decision-records $ npx degit duart-555/claude-code-setup/skills/autonomous-loops .claude/skills/autonomous-loops $ npx degit duart-555/claude-code-setup/skills/backend-patterns .claude/skills/backend-patterns $ npx degit duart-555/claude-code-setup/skills/best-practices .claude/skills/best-practices $ npx degit duart-555/claude-code-setup/skills/brainstorming .claude/skills/brainstorming $ npx degit duart-555/claude-code-setup/skills/brandkit .claude/skills/brandkit $ npx degit duart-555/claude-code-setup/skills/coding-standards .claude/skills/coding-standards $ npx degit duart-555/claude-code-setup/skills/content-hash-cache-pattern .claude/skills/content-hash-cache-pattern $ npx degit duart-555/claude-code-setup/skills/context-budget .claude/skills/context-budget $ npx degit duart-555/claude-code-setup/skills/continuous-learning-v2 .claude/skills/continuous-learning-v2 $ npx degit duart-555/claude-code-setup/skills/core-web-vitals .claude/skills/core-web-vitals $ npx degit duart-555/claude-code-setup/skills/cost-aware-llm-pipeline .claude/skills/cost-aware-llm-pipeline $ npx degit duart-555/claude-code-setup/skills/cpp-coding-standards .claude/skills/cpp-coding-standards $ npx degit duart-555/claude-code-setup/skills/cpp-testing .claude/skills/cpp-testing $ npx degit duart-555/claude-code-setup/skills/database-migrations .claude/skills/database-migrations $ npx degit duart-555/claude-code-setup/skills/deep-research .claude/skills/deep-research $ npx degit duart-555/claude-code-setup/skills/deployment-patterns .claude/skills/deployment-patterns $ npx degit duart-555/claude-code-setup/skills/design-taste-frontend-v1 .claude/skills/design-taste-frontend-v1 $ npx degit duart-555/claude-code-setup/skills/design-taste-frontend .claude/skills/design-taste-frontend $ npx degit duart-555/claude-code-setup/skills/django-patterns .claude/skills/django-patterns $ npx degit duart-555/claude-code-setup/skills/django-security .claude/skills/django-security $ npx degit duart-555/claude-code-setup/skills/django-tdd .claude/skills/django-tdd $ npx degit duart-555/claude-code-setup/skills/docker-patterns .claude/skills/docker-patterns $ npx degit duart-555/claude-code-setup/skills/e2e-testing .claude/skills/e2e-testing $ npx degit duart-555/claude-code-setup/skills/error-handling .claude/skills/error-handling $ npx degit duart-555/claude-code-setup/skills/eval-harness .claude/skills/eval-harness $ npx degit duart-555/claude-code-setup/skills/evaluate-skill .claude/skills/evaluate-skill $ npx degit duart-555/claude-code-setup/skills/fastapi-patterns .claude/skills/fastapi-patterns $ npx degit duart-555/claude-code-setup/skills/frontend-a11y .claude/skills/frontend-a11y $ npx degit duart-555/claude-code-setup/skills/frontend-patterns .claude/skills/frontend-patterns $ npx degit duart-555/claude-code-setup/skills/full-output-enforcement .claude/skills/full-output-enforcement $ npx degit duart-555/claude-code-setup/skills/git-workflow .claude/skills/git-workflow $ npx degit duart-555/claude-code-setup/skills/github-ops .claude/skills/github-ops $ npx degit duart-555/claude-code-setup/skills/gpt-taste .claude/skills/gpt-taste
$ curl -fsSL --create-dirs -o .claude/agents/a11y-architect.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/a11y-architect.md $ curl -fsSL --create-dirs -o .claude/agents/agent-evaluator.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/agent-evaluator.md $ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/build-error-resolver.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/build-error-resolver.md $ curl -fsSL --create-dirs -o .claude/agents/code-architect.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/code-architect.md $ curl -fsSL --create-dirs -o .claude/agents/code-explorer.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/code-explorer.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/code-simplifier.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/code-simplifier.md $ curl -fsSL --create-dirs -o .claude/agents/database-reviewer.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/database-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/doc-updater.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/doc-updater.md $ curl -fsSL --create-dirs -o .claude/agents/docs-lookup.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/docs-lookup.md $ curl -fsSL --create-dirs -o .claude/agents/e2e-runner.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/e2e-runner.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-advisor-researcher.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-advisor-researcher.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-ai-researcher.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-ai-researcher.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-assumptions-analyzer.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-assumptions-analyzer.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-code-fixer.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-code-fixer.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-code-reviewer.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-codebase-mapper.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-codebase-mapper.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-debug-session-manager.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-debug-session-manager.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-debugger.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-debugger.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-doc-classifier.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-doc-classifier.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-doc-synthesizer.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-doc-synthesizer.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-doc-verifier.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-doc-verifier.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-doc-writer.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-doc-writer.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-domain-researcher.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-domain-researcher.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-eval-auditor.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-eval-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-eval-planner.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-eval-planner.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-executor.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-executor.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-framework-selector.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-framework-selector.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-integration-checker.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-integration-checker.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-intel-updater.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-intel-updater.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-mempalace-curator.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-mempalace-curator.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-nyquist-auditor.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-nyquist-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-pattern-mapper.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-pattern-mapper.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-phase-researcher.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-phase-researcher.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-plan-checker.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-plan-checker.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-planner.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-planner.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-project-researcher.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-project-researcher.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-research-synthesizer.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-research-synthesizer.md $ curl -fsSL --create-dirs -o .claude/agents/gsd-roadmapper.md https://raw.githubusercontent.com/duart-555/claude-code-setup/main/agents/gsd-roadmapper.md
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"permissions": {
"deny": [
"Bash(awk * .env*)",
"Bash(cat ~/.env*)",
"Bash(cat */.env*)",
"Bash(cat ~/.env*)",
"Bash(grep * .env*)",
"Bash(head */.env*)",
"Bash(less */.env*)",
"Bash(more */.env*)",
"Bash(sed * .env*)",
"Bash(tail */.env*)",
"Read(**/.env)",
"Read(**/.env.*)",
"Read(.env)",
"Read(.env.*)",
"Read(.secrets)",
"Read(~/.env)"
]
},
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "node -e \"const p=require('path');const r=(function(){var p=require('path'),f=require('fs'),o=require('os');var e=process.env.CLAUDE_PLUGIN_ROOT;if(e&&e.trim())return e.trim();var d=p.join(o.homedir(),'.claude');function L(x){try{return requ"
},
{
"type": "command",
"command": "bash \"$HOME/.claude/hooks/gsd-validate-commit.sh\""
},
{
"type": "command",
"command": "node \"$HOME/.claude/hooks/dash-path-guard.mjs\""
}
]
},
{
"matcher": "Write",
"hooks": [
{
"type": "command",
"command": "node -e \"const p=require('path');const r=(function(){var p=require('path'),f=require('fs'),o=require('os');var e=process.env.CLAUDE_PLUGIN_ROOT;if(e&&e.trim())return e.trim();var d=p.join(o.homedir(),'.claude');function L(x){try{return requ"
}
]
},
{
"matcher": "Edit|Write",
"hooks": [
{
"type": "command",
"command": "node -e \"const p=require('path');const r=(function(){var p=require('path'),f=require('fs'),o=require('os');var e=process.env.CLAUDE_PLUGIN_ROOT;if(e&&e.trim())return e.trim();var d=p.join(o.homedir(),'.claude');function L(x){try{return requ"
}
]
},
{
"matcher": "*",
"hooks": [
{
"type": "command",
"command": "node -e \"const p=require('path');const r=(function(){var p=require('path'),f=require('fs'),o=require('os');var e=process.env.CLAUDE_PLUGIN_ROOT;if(e&&e.trim())return e.trim();var d=p.join(o.homedir(),'.claude');function L(x){try{return requ"
},
{
"type": "command",
"command": "node -e \"const p=require('path');const r=(function(){var p=require('path'),f=require('fs'),o=require('os');var e=process.env.CLAUDE_PLUGIN_ROOT;if(e&&e.trim())return e.trim();var d=p.join(o.homedir(),'.claude');function L(x){try{return requ"
},
{
"type": "command",
"command": "if [ -z \"${HOME-}\" ]; then case \"${OSTYPE-}\" in msys*|cygwin*|win32*) printf '{}\\n'; if [ -z \"${ORCA_AGENT_HOOK_PORT-}\" ] || [ -z \"${ORCA_AGENT_HOOK_TOKEN-}\" ] || [ -z \"${ORCA_PANE_KEY-}\" ]; then exit 0; fi; { command -p cat 2>/dev/null || "
}
]
},
{
"matcher": "Bash|Write|Edit|MultiEdit",
"hooks": [
{
"type": "command",
"command": "node -e \"const p=require('path');const r=(function(){var p=require('path'),f=require('fs'),o=require('os');var e=process.env.CLAUDE_PLUGIN_ROOT;if(e&&e.trim())return e.trim();var d=p.join(o.homedir(),'.claude');function L(x){try{return requ"
}
]
},
{
"matcher": "Write|Edit|MultiEdit",
"hooks": [
{
"type": "command",
"command": "node -e \"const p=require('path');const r=(function(){var p=require('path'),f=require('fs'),o=require('os');var e=process.env.CLAUDE_PLUGIN_ROOT;if(e&&e.trim())return e.trim();var d=p.join(o.homedir(),'.claude');function L(x){try{return requ"
},
{
"type": "command",
"command": "node \"$HOME/.claude/hooks/gsd-worktree-path-guard.js\""
}
]
},
{
"matcher": "Edit|Write|MultiEdit",
"hooks": [
{
"type": "command",
"command": "node -e \"const p=require('path');const r=(function(){var p=require('path'),f=require('fs'),o=require('os');var e=process.env.CLAUDE_PLUGIN_ROOT;if(e&&e.trim())return e.trim();var d=p.join(o.homedir(),'.claude');function L(x){try{return requ"
}
]
},
{
"matcher": "Write|Edit",
"hooks": [
{
"type": "command",
"command": "node \"$HOME/.claude/hooks/gsd-prompt-guard.js\""
},
{
"type": "command",
"command": "node \"$HOME/.claude/hooks/gsd-read-guard.js\""
}
]
},
{
"matcher": "Bash|Edit|Write|MultiEdit",
"hooks": [
{
"type": "command",
"command": "node \"$HOME/.claude/hooks/gsd-workflow-guard.js\""
}
]
}
]
}
} Skills (150)
accessibilityagent-reachagentic-engineeringapi-designapple-design-higapple-designarchitecture-decision-recordsautonomous-loopsbackend-patternsbest-practicesbrainstormingbrandkitcoding-standardscontent-hash-cache-patterncontext-budgetcontinuous-learning-v2core-web-vitalscost-aware-llm-pipelinecpp-coding-standardscpp-testingdatabase-migrationsdeep-researchdeployment-patternsdesign-taste-frontend-v1design-taste-frontenddjango-patternsdjango-securitydjango-tdddocker-patternse2e-testingerror-handlingeval-harnessevaluate-skillfastapi-patternsfrontend-a11yfrontend-patternsfull-output-enforcementgit-workflowgithub-opsgpt-tastegrill-skillgsd-add-testsgsd-ai-integration-phasegsd-audit-fixgsd-audit-milestonegsd-audit-uatgsd-autonomousgsd-capturegsd-cleanupgsd-code-reviewgsd-complete-milestonegsd-configgsd-debuggsd-discuss-phasegsd-docs-updategsd-eval-reviewgsd-execute-phasegsd-exploregsd-extract-learningsgsd-fastgsd-forensicsgsd-graphifygsd-healthgsd-helpgsd-importgsd-inboxgsd-ingest-docsgsd-managergsd-map-codebasegsd-mempalace-capturegsd-mempalace-recallgsd-milestone-summarygsd-mvp-phasegsd-new-milestonegsd-new-projectgsd-nextgsd-ns-contextgsd-ns-ideategsd-ns-managegsd-ns-projectgsd-ns-reviewgsd-ns-workflowgsd-onboardgsd-pause-workgsd-phasegsd-plan-phasegsd-plan-review-convergencegsd-pr-branchgsd-profile-usergsd-progressgsd-quickgsd-resume-workgsd-review-backloggsd-reviewgsd-secure-phasegsd-settingsgsd-shipgsd-sketchgsd-spec-phasegsd-spikegsd-statsgsd-surfacegsd-threadgsd-ui-phasegsd-ui-reviewgsd-ultraplan-phasegsd-undogsd-updategsd-validate-phasegsd-verify-workgsd-workspacegsd-workstreamshexagonal-architecturehigh-end-visual-designhumanizerimage-to-codeimagegen-frontend-mobileimagegen-frontend-webindustrial-brutalist-uiinstall-anti-slopinvestor-materialsiterative-retrievallast30daysmarket-researchmcp-server-patternsmemory-auditminimalist-uimle-workflownextjs-turbopackperformancepostgres-patternspython-patternspython-testingreact-patternsreact-performancereact-testingreceiving-code-reviewredesign-existing-projectsredis-patternsregex-vs-llm-structured-textsearch-firstsecurity-bounty-huntersecurity-reviewsecurity-scanseoskill-stocktakesmoke-harnessstitch-design-tastestop-slopsystematic-debugging
Subagents (61)
| a11y-architect model: sonnet | Accessibility Architect specializing in WCAG 2.2 compliance for Web and Native platforms. Use PROACTIVELY when designing UI components, establishing design systems, or auditing code for inclusive user |
| agent-evaluator model: sonnet | Evaluates agent output against 5-axis quality rubric (accuracy, completeness, clarity, actionability, conciseness). Use after any non-trivial task when the user wants a quality assessment, or when the |
| architect model: opus | Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new features, refactoring large systems, or making architectural decisions |
| build-error-resolver model: sonnet | Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting the |
| code-architect model: sonnet | Designs feature architectures by analyzing existing codebase patterns and conventions, then providing implementation blueprints with concrete files, interfaces, data flow, and build order. |
| code-explorer model: sonnet | Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, and documenting dependencies to inform new development. |
| code-reviewer model: sonnet | Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes. |
| code-simplifier model: sonnet | Simplifies and refines code for clarity, consistency, and maintainability while preserving behavior. Focus on recently modified code unless instructed otherwise. |
| database-reviewer model: sonnet | PostgreSQL database specialist for query optimization, schema design, security, and performance. Use PROACTIVELY when writing SQL, creating migrations, designing schemas, or troubleshooting database p |
| doc-updater model: haiku | Documentation and codemap specialist. Use PROACTIVELY for updating codemaps and documentation. Runs /update-codemaps and /update-docs, generates docs/CODEMAPS/*, updates READMEs and guides. |
| docs-lookup model: haiku | When the user asks how to use a library, framework, or API or needs up-to-date code examples, use Context7 MCP to fetch current documentation and return answers with examples. Invoke for docs/API/setu |
| e2e-runner model: sonnet | End-to-end testing specialist using Vercel Agent Browser (preferred) with Playwright fallback. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines fl |
| gsd-advisor-researcher | Researches a single gray area decision and returns a structured comparison table with rationale. Spawned by discuss-phase advisor mode. |
| gsd-ai-researcher | Researches a chosen AI framework's official docs to produce implementation-ready guidance — best practices, syntax, core patterns, and pitfalls distilled for the specific use case. Writes the Framewor |
| gsd-assumptions-analyzer | Deeply analyzes codebase for a phase and returns structured assumptions with evidence. Spawned by discuss-phase assumptions mode. |
| gsd-code-fixer | Applies fixes to code review findings from REVIEW.md. Reads source files, applies intelligent fixes, and commits each fix atomically. Spawned by /gsd-code-review --fix. |
| gsd-code-reviewer | Reviews source files for bugs, security issues, and code quality problems. Produces structured REVIEW.md with severity-classified findings. Spawned by /gsd-code-review. |
| gsd-codebase-mapper | Explores codebase and writes structured analysis documents. Spawned by map-codebase with a focus area (tech, arch, quality, concerns). Writes documents directly to reduce orchestrator context load. |
| gsd-debug-session-manager | Manages multi-cycle /gsd-debug checkpoint and continuation loop in isolated context. Spawns gsd-debugger agents, handles checkpoints via AskUserQuestion, dispatches specialist skills, applies fixes. R |
| gsd-debugger | Investigates bugs using scientific method, manages debug sessions, handles checkpoints. Spawned by /gsd-debug orchestrator. |
| gsd-doc-classifier | Classifies a single planning document as ADR, PRD, SPEC, DOC, or UNKNOWN. Extracts title, scope summary, and cross-references. Spawned in parallel by /gsd-ingest-docs. Writes a JSON classification fil |
| gsd-doc-synthesizer | Synthesizes classified planning docs into a single consolidated context. Applies precedence rules, detects cross-ref cycles, enforces LOCKED-vs-LOCKED hard-blocks, and writes INGEST-CONFLICTS.md with |
| gsd-doc-verifier | Verifies factual claims in generated docs against the live codebase. Returns structured JSON per doc. |
| gsd-doc-writer | Writes and updates project documentation. Spawned with a doc_assignment block specifying doc type, mode (create/update/supplement), and project context. |
| gsd-domain-researcher | Researches the business domain and real-world application context of the AI system being built. Surfaces domain expert evaluation criteria, industry-specific failure modes, regulatory context, and wha |
| gsd-eval-auditor | Retroactive audit of an implemented AI phase's evaluation coverage. Checks implementation against the AI-SPEC.md evaluation plan. Scores each eval dimension as COVERED/PARTIAL/MISSING. Produces a scor |
| gsd-eval-planner | Designs a structured evaluation strategy for an AI phase. Identifies critical failure modes, selects eval dimensions with rubrics, recommends tooling, and specifies the reference dataset. Writes the E |
| gsd-executor | Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command. |
| gsd-framework-selector | Presents an interactive decision matrix to surface the right AI/LLM framework for the user's specific use case. Produces a scored recommendation with rationale. Spawned by /gsd-ai-integration-phase an |
| gsd-integration-checker | Verifies cross-phase integration and E2E flows. Checks that phases connect properly and user workflows complete end-to-end. |
| gsd-intel-updater | Analyzes codebase and writes structured intel files to .planning/intel/. |
| gsd-mempalace-curator model: sonnet | Ship-time MemPalace curation — writes the session diary, proposes/creates cross-project tunnels, mirrors extract-learnings into the temporal KG, and runs wing-scoped drawer pruning. Spawned at ship:po |
| gsd-nyquist-auditor | Fills Nyquist validation gaps by generating tests and verifying coverage for phase requirements |
| gsd-pattern-mapper | Analyzes codebase for existing patterns and produces PATTERNS.md mapping new files to closest analogs. Read-only codebase analysis spawned by /gsd-plan-phase orchestrator before planning. |
| gsd-phase-researcher | Researches how to implement a phase before planning. Produces RESEARCH.md consumed by gsd-planner. Spawned by /gsd-plan-phase orchestrator. |
| gsd-plan-checker | Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality. Spawned by /gsd-plan-phase orchestrator. |
| gsd-planner | Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification. Spawned by /gsd-plan-phase orchestrator. |
| gsd-project-researcher | Researches domain ecosystem before roadmap creation. Produces files in .planning/research/ consumed during roadmap creation. Spawned by /gsd-new-project or /gsd-new-milestone orchestrators. |
| gsd-research-synthesizer | Synthesizes research outputs from parallel researcher agents into SUMMARY.md. Spawned by /gsd-new-project after 4 researcher agents complete. |
| gsd-roadmapper | Creates project roadmaps with phase breakdown, requirement mapping, success criteria derivation, and coverage validation. Spawned by /gsd-new-project orchestrator. |
Hooks (57)
| event | matcher | runs |
|---|---|---|
| SessionStart | * | node "$HOME/.claude/hooks/memory-check.mjs" |
| SessionStart | * | "$HOME/.claude/hooks/context-mode-cache-heal.mjs" |
| SessionStart | * | node "$HOME/.claude/scripts/context-mode-patch.mjs" --quiet |
| SessionStart | * | node -e "const p=require('path');const r=(function(){var p=require('path'),f=require('fs'),o=require('os');var e=process.env.CLAUDE_PLUGIN_ROOT;if(e&&e.trim())return e.trim();var d=p.join(o.homedir(),'.claude');function L(x){try{return requ |
| SessionStart | * | node -e "const p=require('path');const r=(function(){var p=require('path'),f=require('fs'),o=require('os');var e=process.env.CLAUDE_PLUGIN_ROOT;if(e&&e.trim())return e.trim();var d=p.join(o.homedir(),'.claude');function L(x){try{return requ |
| SessionStart | * | node "$HOME/.claude/hooks/gsd-check-update.js" |
| SessionStart | * | bash "$HOME/.claude/hooks/gsd-session-state.sh" |
| SessionStart | * | if [ -z "${HOME-}" ]; then case "${OSTYPE-}" in msys*|cygwin*|win32*) printf '{}\n'; if [ -z "${ORCA_AGENT_HOOK_PORT-}" ] || [ -z "${ORCA_AGENT_HOOK_TOKEN-}" ] || [ -z "${ORCA_PANE_KEY-}" ]; then exit 0; fi; { command -p cat 2>/dev/null || |
| PostToolUse | * | node -e "const p=require('path');const r=(function(){var p=require('path'),f=require('fs'),o=require('os');var e=process.env.CLAUDE_PLUGIN_ROOT;if(e&&e.trim())return e.trim();var d=p.join(o.homedir(),'.claude');function L(x){try{return requ |
| PostToolUse | * | node -e "const p=require('path');const r=(function(){var p=require('path'),f=require('fs'),o=require('os');var e=process.env.CLAUDE_PLUGIN_ROOT;if(e&&e.trim())return e.trim();var d=p.join(o.homedir(),'.claude');function L(x){try{return requ |
| PostToolUse | Bash|Edit|Write|MultiEdit|Agent|Task | node "$HOME/.claude/hooks/gsd-context-monitor.js" |
| PostToolUse | Read | node "$HOME/.claude/hooks/gsd-read-injection-scanner.js" |
| PostToolUse | Bash | bash "$HOME/.claude/hooks/gsd-graphify-update.sh" |
| PostToolUse | Write|Edit | bash "$HOME/.claude/hooks/gsd-phase-boundary.sh" |
| PostToolUse | * | if [ -z "${HOME-}" ]; then case "${OSTYPE-}" in msys*|cygwin*|win32*) printf '{}\n'; if [ -z "${ORCA_AGENT_HOOK_PORT-}" ] || [ -z "${ORCA_AGENT_HOOK_TOKEN-}" ] || [ -z "${ORCA_PANE_KEY-}" ]; then exit 0; fi; { command -p cat 2>/dev/null || |
| PreToolUse | Bash | node -e "const p=require('path');const r=(function(){var p=require('path'),f=require('fs'),o=require('os');var e=process.env.CLAUDE_PLUGIN_ROOT;if(e&&e.trim())return e.trim();var d=p.join(o.homedir(),'.claude');function L(x){try{return requ |
| PreToolUse | Write | node -e "const p=require('path');const r=(function(){var p=require('path'),f=require('fs'),o=require('os');var e=process.env.CLAUDE_PLUGIN_ROOT;if(e&&e.trim())return e.trim();var d=p.join(o.homedir(),'.claude');function L(x){try{return requ |
| PreToolUse | Edit|Write | node -e "const p=require('path');const r=(function(){var p=require('path'),f=require('fs'),o=require('os');var e=process.env.CLAUDE_PLUGIN_ROOT;if(e&&e.trim())return e.trim();var d=p.join(o.homedir(),'.claude');function L(x){try{return requ |
| PreToolUse | * | node -e "const p=require('path');const r=(function(){var p=require('path'),f=require('fs'),o=require('os');var e=process.env.CLAUDE_PLUGIN_ROOT;if(e&&e.trim())return e.trim();var d=p.join(o.homedir(),'.claude');function L(x){try{return requ |
| PreToolUse | Bash|Write|Edit|MultiEdit | node -e "const p=require('path');const r=(function(){var p=require('path'),f=require('fs'),o=require('os');var e=process.env.CLAUDE_PLUGIN_ROOT;if(e&&e.trim())return e.trim();var d=p.join(o.homedir(),'.claude');function L(x){try{return requ |
| PreToolUse | Write|Edit|MultiEdit | node -e "const p=require('path');const r=(function(){var p=require('path'),f=require('fs'),o=require('os');var e=process.env.CLAUDE_PLUGIN_ROOT;if(e&&e.trim())return e.trim();var d=p.join(o.homedir(),'.claude');function L(x){try{return requ |
| PreToolUse | * | node -e "const p=require('path');const r=(function(){var p=require('path'),f=require('fs'),o=require('os');var e=process.env.CLAUDE_PLUGIN_ROOT;if(e&&e.trim())return e.trim();var d=p.join(o.homedir(),'.claude');function L(x){try{return requ |
| PreToolUse | Edit|Write|MultiEdit | node -e "const p=require('path');const r=(function(){var p=require('path'),f=require('fs'),o=require('os');var e=process.env.CLAUDE_PLUGIN_ROOT;if(e&&e.trim())return e.trim();var d=p.join(o.homedir(),'.claude');function L(x){try{return requ |
| PreToolUse | Write|Edit | node "$HOME/.claude/hooks/gsd-prompt-guard.js" |
| PreToolUse | Write|Edit | node "$HOME/.claude/hooks/gsd-read-guard.js" |
| PreToolUse | Bash|Edit|Write|MultiEdit | node "$HOME/.claude/hooks/gsd-workflow-guard.js" |
| PreToolUse | Write|Edit|MultiEdit | node "$HOME/.claude/hooks/gsd-worktree-path-guard.js" |
| PreToolUse | Bash | bash "$HOME/.claude/hooks/gsd-validate-commit.sh" |
| PreToolUse | Bash | node "$HOME/.claude/hooks/dash-path-guard.mjs" |
| PreToolUse | * | if [ -z "${HOME-}" ]; then case "${OSTYPE-}" in msys*|cygwin*|win32*) printf '{}\n'; if [ -z "${ORCA_AGENT_HOOK_PORT-}" ] || [ -z "${ORCA_AGENT_HOOK_TOKEN-}" ] || [ -z "${ORCA_PANE_KEY-}" ]; then exit 0; fi; { command -p cat 2>/dev/null || |
Slash commands (23)
/build-fix/checkpoint/code-review/evolve/instinct-export/instinct-import/instinct-status/learn-eval/learn/multi-backend/multi-execute/multi-plan/multi-workflow/plan/pm2/prune/python-review/quality-gate/refactor-clean/sessions/skill-create/test-coverage/update-docs
Plugins (28)
skill-creator@claude-plugins-officialsuperpowers@claude-plugins-officialcode-review@claude-plugins-officialvercel@claude-plugins-officialfrontend-design@claude-plugins-officialui-ux-pro-max@ui-ux-pro-max-skillcaveman@cavemanclaude-mem@thedotmackcontext-mode@context-modestripe@claude-plugins-officialchisle@chislereticle@reticlehqproductivity@knowledge-work-pluginsproduct-management@knowledge-work-pluginsengineering@knowledge-work-pluginsdata@knowledge-work-pluginsdesign@knowledge-work-pluginsmarketing@knowledge-work-pluginssales@knowledge-work-pluginslegal@knowledge-work-pluginssmall-business@knowledge-work-pluginsmarketing-skills@marketingskillsfrontend-slides@frontend-slidesfinance@knowledge-work-pluginsoperations@knowledge-work-pluginsenterprise-search@knowledge-work-pluginscustomer-support@knowledge-work-pluginsproduct-tracking-skills@knowledge-work-plugins
Permissions
deny (16)
Bash(awk * .env*)
Bash(cat ~/.env*)
Bash(cat */.env*)
Bash(cat ~/.env*)
Bash(grep * .env*)
Bash(head */.env*)
Bash(less */.env*)
Bash(more */.env*)
Bash(sed * .env*)
Bash(tail */.env*)
Read(**/.env)
Read(**/.env.*)
Read(.env)
Read(.env.*)
Read(.secrets)
Read(~/.env)
ask (0)
—
allow (15)
Bash(git diff:*)
Bash(pip list:*)
Bash(pip show:*)
Bash(pip3 list:*)
Bash(pip3 show:*)
Bash(systemctl is-active:*)
Bash(systemctl is-enabled:*)
Bash(systemctl list-units:*)
Bash(systemctl status:*)
Edit(.planning/*)
Edit(STATE.md)
Read(.planning/*)
Read(STATE.md)
WebFetch(domain:gist.github.com)
WebFetch(domain:gitlab.com)
Similar rigs
open-gsd/gsd-core
Git. Ship. Done - Core
Skill Collector 19.6k tok · · Q3
FacundoECornet/Habitat
Restaurá tu entorno de OpenCode (GSD, agentes, skills, plugins y herramientas) en cualquier máquina, con backups y verificación.
Skill Collector 2.6k tok · · Q0
tomascortereal/claude-code-setup
My full Claude Code configuration — agents, skills, hooks, plugins, and global instructions
Orchestrator 7.2k tok · · Q0
ysyecust/everything-claude-code
Complete collection of Claude Code configs for C++20 HPC development - agents, skills, hooks, commands, and rules
YOLO Cowboy 58.8k tok · · Q5