Plugin Claude Code
Deterministic quality gates for AI-written code.
5 22d ago A
tokens not measured
original MIT
Agent Claude Code
Quality Loop context mapper. Use during EXPLORE to map the smallest relevant code surface before editing.
5 22d ago A 26 tokens
original MIT
Agent Claude Code
Quality Loop planner. Use during MINIMALITYGATE and PLAN to design the smallest correct change with strong reasoning.
5 22d ago A 27 tokens
original MIT
Agent Claude Code
Fresh-context Quality Loop reviewer. Use after implementation and before package/done.
5 22d ago A 20 tokens
original MIT
Agent Claude Code
Fresh-context security reviewer for auth, payments, secrets, PII, migrations, upload/download, network, shell, and dependency changes.
5 22d ago A 33 tokens
original MIT
SessionStart
06Hook Claude Code
Runs when a session starts on startup and resume, running python3. From zaingz/coding-quality-loop.
5 22d ago A
tokens not measured
original MIT
PreToolUse
07Hook Claude Code
Runs before the agent uses a tool for Bash, Edit and Write tool calls, running python3. From zaingz/coding-quality-loop.
5 22d ago A
tokens not measured
original MIT
Stop
08Hook Claude Code
Runs when the agent finishes a response, running python3. From zaingz/coding-quality-loop.
5 22d ago A
tokens not measured
original MIT
Settings file Claude Code
Agent settings declaring 3 hook events (SessionStart, PreToolUse, Stop).
5 22d ago A
tokens not measured
original MIT
Skill Claude CodeCodex
Use when a coding agent must turn a software goal, bug, issue, or refactor into a small, verified, independently reviewed code change.
5 22d ago A 33 tokens
original MIT
Cursor rule Cursor
Apply to non-trivial coding work — implementing, fixing, refactoring, testing, or migrating a change. Produce the smallest correct, verified change with fresh-context review. Skip for trivial one-line edits.
5 22d ago A 41 tokens
original MIT
Plugin Claude Code
Prove a new test fails against the old code before trusting green.
5 22d ago A
tokens not measured
copy · 86% MIT
Skill Claude CodeCodex
Use when AI-written code or tests claim green and you need deterministic proof that the new test catches the old bug.
5 22d ago A 29 tokens
original MIT