commit
01Command Claude Code
Create a conventional commit/s from current changes.
One config for every AI coding tool, plus lessons so your agents learn from their mistakes. Sync rules, skills, MCP servers and hooks to Claude Code, Cursor, Copilot, Codex and more.
This repository also configures its own agents. See what agentsmesh tells them →
Command Claude Code
Create a conventional commit/s from current changes.
Command Claude Code
Review current changes for code quality and best practices.
Command Claude Code
Run tests and report results.
Command Claude Code
Implement the next task incrementally — build, test, verify, commit.
Command Claude Code
Simplify code for clarity and maintainability — reduce complexity without changing behavior.
Command Claude Code
Break work into small verifiable tasks with acceptance criteria and dependency ordering.
Command Claude Code
Break work into small verifiable tasks with acceptance criteria and dependency ordering.
Command Claude Code
Run the pre-launch checklist via parallel fan-out to specialist personas, then synthesize a go/no-go decision.
Command Claude Code
Start spec-driven development — write a structured specification before writing code.
Command Claude Code
Audit the whole repo for over-engineering, what can be deleted.
Command Claude Code
Harvest ponytail: comments into a tracked debt ledger.
Command Claude Code
Show ponytail's measured impact scoreboard (less code, cost, time).
Command Claude Code
Quick reference for ponytail levels, skills, and commands.
Command Claude Code
Review changes for over-engineering, what can be deleted.
Command Claude Code
Switch ponytail intensity level (lite/full/ultra/off).
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: