scan-analyst
25Agent
Reverse-engineer requirements from existing code and tests. Tags each requirement as CONFIRMED (test-backed) or INFERRED (code-only).
11 15d ago A 34 tokens
original MIT
Agent
Analyze existing codebase architecture from scan context. Documents as-is architecture rather than designing to-be.
11 15d ago A 23 tokens
original MIT
Agent
Extract data models from existing ORM definitions, migration files, and schema declarations. Only invoked when database usage is detected.
11 15d ago A 28 tokens
original MIT
scan-planner
28Agent
Generate improvement issues from codebase scan observations — test gaps, tech debt, schema problems, and risk items.
11 15d ago A 26 tokens
original MIT
Agent
Assess existing test coverage, identify gaps, and produce a test plan based on actual codebase analysis rather than PRD requirements.
11 15d ago A 31 tokens
original MIT
Agent
Separate-context auditor for the kit's synthesis layer. Verifies that a /deep-research report's claims survive into the kit's rendered output without being dropped, distorted, or scope-changed. Refute-first prompt — defaults claims to suspect until proven faithful.
11 15d ago A 60 tokens
original MIT
team-lead
31Agent
Sprint phase executor — receives a specific phase (IMPLEMENT/REVIEW/SHIP) and target issues, executes that phase, updates sprint state.
11 15d ago A 32 tokens
original MIT
Agent
Scan codebase for test gaps and generate unit/integration/E2E tests that actually pass — no hollow tests, no false coverage.
11 15d ago A 30 tokens
original MIT
ui-reviewer
33Agent
Audit the design IMPLEMENTATION (rendered state coverage, copy usage, token usage in code, interaction fidelity, accessibility in code, component existence) — implementation-level only. System-level checks belong to design-auditor.
11 15d ago A 48 tokens
original MIT
Agent
UI/UX development expert who establishes design philosophy based on PRD and UX specs, and generates design systems, wireframes, and HTML prototypes.
11 15d ago A 34 tokens
original MIT
ux-designer
35Agent
Create UX spec (IA, flows, screen states, copy, a11y) from PRD. v0 scope — spec only, no visual design.
11 15d ago A 36 tokens
original MIT
SessionEnd
36Hook
Runs when a session ends, executing run_cleanup.py via bash. From pillip/claude-dev-kit.
11 15d ago A
tokens not measured
original MIT
Stop
37Hook
Runs when the agent finishes a response, executing run_cleanup.py via bash. From pillip/claude-dev-kit.
11 15d ago A
tokens not measured
copy · 89% MIT
Hook
Runs when a subagent starts, executing agent_state.py via bash. From pillip/claude-dev-kit.
11 15d ago A
tokens not measured
original MIT
SubagentStop
39Hook
Runs when a subagent finishes, executing agent_state.py via bash. From pillip/claude-dev-kit.
11 15d ago A
tokens not measured
copy · 98% MIT
PreToolUse
40Hook
Runs before the agent uses a tool for Write, Edit and Bash tool calls, executing agent_state.py, secret_guard.py and dangerous_command_guard.py via bash (3 commands). From pillip/claude-dev-kit.
11 15d ago A
tokens not measured
copy · 80% MIT
PostToolUse
41Hook
Runs after a tool call finishes for Write and Edit tool calls, executing agent_state.py and autotest.py via bash (2 commands). From pillip/claude-dev-kit.
11 15d ago A
tokens not measured
copy · 84% MIT
Hook
Runs when a tool call fails, executing agent_state.py via bash. From pillip/claude-dev-kit.
11 15d ago A
tokens not measured
copy · 97% MIT
Hook
Runs when you submit a prompt, before the agent sees it, executing agent_state.py via bash. From pillip/claude-dev-kit.
11 15d ago A
tokens not measured
copy · 97% MIT
SessionStart
44Hook
Runs when a session starts, executing session_start.py via bash. From pillip/claude-dev-kit.
11 15d ago A
tokens not measured
original MIT
bizanalysis
45Skill Claude CodeCodex
Analyzes and critiques business viability. Use after /brainstorm and before /prd.
11 15d ago A 20 tokens
original MIT
brainstorm
46Skill Claude CodeCodex
Explores ideas and defines problems through free-form conversation. Use before /prd when direction is unclear.
11 15d ago A 23 tokens
original MIT
careful
47Skill Claude CodeCodex
Activates destructive command warnings for the current session. Use when working in sensitive environments.
11 15d ago C 20 tokens
original MIT
desktop-uiux
48Skill Claude CodeCodex
Establishes a desktop design philosophy based on kickoff outputs, and generates a desktop design system/wireframes/Electron prototype. Recommended flow — /prd → /kickoff → /desktop-uiux.
11 15d ago A 43 tokens
original MIT