plumpslabs

plumpslabs/matcha

Agent Codex

Stack audit. Finds overlaps, waste, security risks. Read-only.

plumpslabs/matcha

Agent Codex

Cleanup. Removes temp, debug, unused code. Confirm before delete. May edit after confirmation.

plumpslabs/matcha

Agent Codex

Systematic debugger. One hypothesis at a time. Evidence required. May apply minimal fixes.

plumpslabs/matcha

Agent Codex

Reuse decision engine. Finds existing code before writing new — classifies REUSE/EXTEND/COMPOSE/REFERENCE/NEW. Never duplicate. Read-only.

plumpslabs/matcha

Agent Codex

Engineering planning. Intent Discovery → context → constraints → reuse → alternatives → roadmap. Read-only — never implements, never edits source code.

plumpslabs/matcha

Agent Codex

Review gate with risk-based routing. L0=output check, L1=lint, L2=full review, L3=expert+threat model. Blocks merge if critical issues found. Read-only.

plumpslabs/matcha

Command Codex

🍵 Stack health check — find overlaps, waste, and risks before they become problems.

plumpslabs/matcha

Command Codex

🍵 Technical debt & marker ledger — harvest all // matcha: comments into an actionable report.

plumpslabs/matcha

Command Codex

🍵 Set matcha intensity level: observe, enforce, or audit.

plumpslabs/matcha

Command Codex

🍵 Scan for // matcha: markers in the codebase and group by severity.

plumpslabs/matcha

Command Codex

🍵 Review gate — risk-based code review (L0-L3). Nothing ships until this passes.

plumpslabs/matcha

Command Codex

🍵 Master session health dashboard — intensity, git diff stats, test status, and marker ledger.

plumpslabs/matcha

Command Codex

🍵 Intent Discovery — problem, goals, success criteria, What → Why → How before touching code.

plumpslabs/matcha

Skill Claude CodeCodex

../../../skills/matcha/SKILL.md.

plumpslabs/matcha

Plugin Claude Code

Engineering philosophy ruleset for AI coding agents — simple, efficient, deliberate.

plumpslabs/matcha

Plugin Claude Code

Engineering philosophy ruleset — simple, efficient, deliberate. Enforces Intent Discovery thinking, stack audits, mid-task efficiency checks, and cleanup protocols.

plumpslabs/matcha

Hook Claude Code

Runs before the agent uses a tool for Bash, Edit, Write and MultiEdit tool calls, executing matcha-shield.js via node. From plumpslabs/matcha.

plumpslabs/matcha

Hook Claude Code

Runs after a tool call finishes, executing matcha-post-write.js via node. From plumpslabs/matcha.

plumpslabs/matcha

Hook Claude Code

Runs when the agent finishes a response, executing matcha-stop.js via node. From plumpslabs/matcha.

plumpslabs/matcha

Settings file Claude Code

Agent settings declaring 3 hook events (PreToolUse, PostToolUse, Stop).

plumpslabs/matcha

Cursor rule Cursor

This project uses the matcha engineering convention. Read the AGENTS.md file at the project root and follow its philosophy.

plumpslabs/matcha

Instructions file GitHub Copilot

Copilot instructions for plumpslabs/matcha: This project uses the matcha engineering convention. Read the AGENTS.md file at the project root and follow its philosophy.

plumpslabs/matcha

Instructions file CodexOpenCode

AGENTS.md instructions for plumpslabs/matcha, covering 🍵 matcha — core ai directives, the 6-checkpoint filter, core principles, intensity levels and commands.

plumpslabs/matcha

Instructions file

Claude Code instructions for plumpslabs/matcha, covering 🍵 matcha — claude persona, core behavior, intensity (set via /matcha:intensity) and safety.