prove
01Plugin Claude Code
Plan, Research, Orchestrate, Validate, Execute — a complete lifecycle plugin for Claude Code.
2 22d ago A
tokens not measured
original MIT
prove
02Plugin Claude Code
Plan, Research, Orchestrate, Validate, Execute — a complete lifecycle plugin for Claude Code, for any tech stack.
2 22d ago A
tokens not measured
original MIT
Agent Claude Code
You are the Requirements Analyst seat. You turn discovery findings into testable requirements.
2 22d ago A 41 tokens
original MIT
Agent Claude Code
You are the Technical Writer seat. You produce the PRDs, charters, and user-facing documents the other seats rely on.
2 22d ago A 43 tokens
original MIT
Agent Claude Code
You are the Product Manager seat for claude-prove. You own discovery, requirements, and milestone shaping — not code.
2 22d ago A 44 tokens
original MIT
Agent Claude Code
You implement claude-prove engine features in TypeScript on Bun (packages/, scripts/).
2 22d ago A 40 tokens
original MIT
Agent Claude Code
You execute leaf implementation tasks on the claude-prove engine (packages/, scripts/).
2 22d ago A 42 tokens
original MIT
Agent Claude Code
You are the architecture owner for the claude-prove engine (packages/, scripts/).
2 22d ago A 43 tokens
original MIT
Agent Claude Code
You author and revise skills, agent definitions, commands, and references.
2 22d ago A 42 tokens
original MIT
Agent Claude Code
You apply leaf edits to the prose layer: reference updates, doc fixes, frontmatter corrections.
2 22d ago A 44 tokens
original MIT
Agent Claude Code
You own the model-facing prose layer (skills/, agents/, commands/, references/).
2 22d ago A 45 tokens
original MIT
triage
12Command Claude Code
Triage open GitHub issues — review, label, prioritize, and plan fixes.
2 22d ago A 16 tokens
original MIT
PostToolUse
13Hook Claude Code
Runs after a tool call finishes for Write, Edit and MultiEdit tool calls, executing run.ts via bun (2 commands). From mjmorales/claude-prove.
2 22d ago A
tokens not measured
original MIT
PreToolUse
14Hook Claude Code
Runs before the agent uses a tool for Glob, Grep, Write, Edit, MultiEdit, Read, Write, Edit, MultiEdit and Bash tool calls, executing run.ts via bun (3 commands). From mjmorales/claude-prove.
2 22d ago A
tokens not measured
copy · 89% MIT
SessionStart
15Hook Claude Code
Runs when a session starts on resume, compact, startup, resume and compact, executing run.ts via bun (2 commands). From mjmorales/claude-prove.
2 22d ago A
tokens not measured
original MIT
Stop
16Hook Claude Code
Runs when the agent finishes a response, executing run.ts via bun (2 commands). From mjmorales/claude-prove.
2 22d ago A
tokens not measured
original MIT
SubagentStop
17Hook Claude Code
Runs when a subagent finishes for general-purpose tool calls, executing run.ts via bun (2 commands). From mjmorales/claude-prove.
2 22d ago A
tokens not measured
copy · 91% MIT
settings
18Settings file Claude Code
Agent settings declaring 5 hook events (PostToolUse, PreToolUse, SessionStart, Stop).
2 22d ago A
tokens not measured
original MIT
playwright
19MCP server Claude CodeCodexCursor
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
2 22d ago A
tokens not measured
copy · 100% MIT
Instructions file
Claude Code instructions for mjmorales/claude-prove, covering claude-prove, structure, conventions, validation and discovery protocol.
2 22d ago A 2,588 tokens
original MIT
brief-judge
21Agent
Stage-2 prose-quality judge for the reasoning-log Review Brief. Judges whether a synthesized brief's narrative is accurate, risk-forward, and coherent against the run's reasoning log. Read-only, advisory, non-blocking — preservation is proven mechanically by acb brief validate (Stage-1), so this judges prose only.…
2 22d ago A 82 tokens
original MIT
code-steward
22Agent
Post-agent code quality auditor. Deep codebase audit with surgical refactoring after parallel agent workflows.
2 22d ago A 24 tokens
original MIT
Agent
Prompt optimization specialist. Audits and rewrites prompts, agent definitions, system instructions, and CLAUDE.md files for LLM efficiency. Use when writing, reviewing, or improving any prompt or agent definition. Triggers on prompt optimization, token efficiency, instruction tuning, or LLM best practices.
2 22d ago A 67 tokens
original MIT
Agent
Memory-layer curator for prove teams. Reads one team's full memory (Lore, annotations, contributor artifacts) or the project Codex (scrum decisions) and returns a keep/consolidate/promote/supersede plan that maximizes future accuracy per token. Read-only and plan-only — the janitor skill executes every write through…
2 22d ago A 96 tokens
original MIT