planning-suite

Plugin planning-suite from marketplace claude-craft in whichguy/claude-craft. Commands read from the repo's manifest — 14 days ago.

Skills (2)

• node-plan

  Dual-perspective Node.js/TypeScript plan review (TypeScript/API + Node runtime) with iterative convergence loop. 36 Node/TS-specific questions (N20/N21 naming+docs deferred to L1's Q-G6/Q-G7 which cover these universally). **AUTOMATICALLY INVOKE** when: - Any plan exists for Node.js or TypeScript ch

• test-prompt-harness

  Headless `claude -p` test harness V2 — runs a fixture's literal prompt through real Claude sessions (k replicas in parallel), grades each replica on five string views plus structured tool-call / tool-result / run-health / LLM-judge condition families, then quorum-aggregates row verdicts. Use when an

Slash commands (6)

• /planning-suite:alias

  Create slash command aliases or list existing aliases

• /planning-suite:knowledge

  Discover and integrate knowledge files from project and user directories

• /planning-suite:performance

  Performance analysis and optimization recommendations

• /planning-suite:red-team-v2

  Multi-phase question-driven red team review (A/B test - Approach B)

• /planning-suite:red-team

  Expert-driven iterative red team review with Opus orchestration (--fast for Haiku, --deep for Opus throughout)

• /planning-suite:unalias

  Remove slash command aliases

Subagents (12)

• deployment-orchestrator

  Deploys code through the deployment pipeline. **AUTOMATICALLY INVOKE** when user mentions: - "deploy", "release", "ship", "launch", "go live", "push to prod" - "promote to staging", "promote to production" - After feature merge to main branch **STRONGLY RECOMMENDED** for: - Feature releases - Hotfix

• environment-analyst

  Analyzes existing systems, integrations, and environment before making changes. **AUTOMATICALLY INVOKE** when user asks: - "what's the current setup", "how does it work now", "what exists" - "dependencies", "integrations", "what will this affect" - "environment", "infrastructure", "existing code" -

• file-output-executor

  Execute instructions and write ALL output to specified file. Prevents conversation truncation for large outputs. Returns only completion message: 'COMPLETE: filepath bytes seconds' **AUTOMATICALLY INVOKE** when: - Output will be very large (code generation, reports, data exports) - User mentions "sa

• knowledge-aggregator

  Captures patterns, learnings, and discoveries for future reference. **AUTOMATICALLY INVOKE** when user mentions: - "save this pattern", "document learning", "remember this" - "capture this", "note this down", "save for later" - After significant debugging or implementation discoveries **STRONGLY REC

• qa-analyst

  Creates test plans and specifications for specific implementation files/components using existing test infrastructure. Should be invoked by feature-developer with specific file/component target and dryrun flag. **AUTOMATICALLY INVOKE** this agent when user mentions "test", "coverage", "QA", or after

• recommend-tech

  Researches and compares technology options with structured analysis. **AUTOMATICALLY INVOKE** when user mentions: - "which tech", "compare options", "technology stack", "what should I use" - "framework comparison", "library choice", "tech recommendation" - Choosing between multiple technologies or f

• requirements-generator

  Generates detailed requirements from feature descriptions or use cases. **AUTOMATICALLY INVOKE** when user mentions: - "requirements", "what do I need", "define specs", "specification" - "what should it do", "functional requirements", "acceptance criteria" - Vague feature requests that need clarific

• synthesis-coordinator

  Synthesizes findings from multiple sources and coordinates cross-cutting concerns. **AUTOMATICALLY INVOKE** when user mentions: - "coordinate", "synthesize", "integrate findings" - "cross-cutting", "pull together", "combine results" - Multiple streams of work that need integration **STRONGLY RECOMME

• system-architect

  Adaptive system architect that makes intelligent technology decisions leveraging existing environment. Uses prompt-as-code methodology with runtime decision-making for optimal KISS/YAGNI outcomes. **AUTOMATICALLY INVOKE** this agent when user mentions "architecture", "design system", "technology sta

• tech-research-analyst

  Conducts deep technical research and evaluation of technology options. **AUTOMATICALLY INVOKE** when user mentions: - "research technology", "evaluate options", "tech comparison" - "deep dive on", "investigate", "analyze technology" - Technical questions requiring extensive research **STRONGLY RECOM

• ui-designer

  Creates UI/UX design specifications for specific interface components and views. Should be invoked by feature-developer when implementing UI/frontend files that require interface design and user experience considerations. **AUTOMATICALLY INVOKE** this agent when user mentions "UI", "UX", "design", "

• verify-transformation

  Analyzes prose transformations to detect unintended functionality loss — distinguishes intentional transformation and enhancement from accidental omission or meaning drift. Use when rewriting agent files, documentation, or instructional content to verify the new version preserves all critical rules

Hooks (4)

• PreToolUse

  ${CLAUDE_PLUGIN_ROOT}/handlers/plan-unknowns-gate.py

• PreToolUse

  ${CLAUDE_PLUGIN_ROOT}/handlers/plan-worktree-gate.py

• PostToolUse

  ${CLAUDE_PLUGIN_ROOT}/handlers/plan-review-cleanup.py

• PostToolUse

  ${CLAUDE_PLUGIN_ROOT}/handlers/exit-plan-mode-schedule-nudge.sh

Similar plugins