Soda-null

Multi Agent Repo Protocol — AI skill for Claude Code

AI community

Rules, git hooks and scripts that let several AI coding agents (Claude Code, Codex, DeepSeek) share one git repo without overwriting each other, with every commit attributed.

How to install Multi Agent Repo Protocol

This entry records only its repository, not the path inside it, so there is no exact command to give. Open Soda-null/multi-agent-repo-protocol and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Multi Agent Repo Protocol does

Rules, git hooks and scripts that let several AI coding agents (Claude Code, Codex, DeepSeek) share one git repo without overwriting each other, with every commit attributed.

Alternatives in AI

BrowserSkill — Let AI agents use your real, logged-in browser without interrupting your work 9.1k ★
Commit Claude Config — Version the Solana AI Kit config in git (un-ignores .claude/, CLAUDE.md, .mcp.json, .gitmodules and commits th 98 ★
Sloppy — Static analysis for the debt AI agents leave in PHP: 25 rules, Claude Code hooks, git-diff review, a Rector an 84 ★

README

multi-agent-repo-protocol

Rules, git hooks and small scripts that let several AI coding agents — Claude Code, Codex, a cheap API model, a local model — work in **one git repository** without overwriting each other, and let you find out afterwards **which agent did what**.

[中文说明](README_zh.md)

The problem

When you use more than one agent on the same project, the same things go wrong again and again:

Agent B "cleans up" files that agent A had not committed yet. A's work is gone.
All agents commit under your one git identity. When something breaks, git blame says you.
An agent reads an old decision in a status file and follows it, because nobody removed it.
One agent calls another on its own and spends that agent's quota.
A cheap model is given a task that needs judgment, and its plausible-looking output is accepted.

The agents cannot talk to each other. **Files are the only channel.** So this protocol puts everything into files, and puts a machine check on every rule that a machine can check.

What is inside

Piece	What it does
`AGENTS.md` (+ `CLAUDE.md` symlink)	One constitution read by every agent
`docs/agent_board.md`	Claims table: who is working on which paths right now
`.githooks/commit-msg`	Rejects a commit without an `Agent:` trailer, so every commit is attributed
`scripts/agent_worktree.sh`	Gives each parallel agent its own working tree on `agent/`
`scripts/delegate.sh`	Sends a task to a cheaper agent — only if the task names a command that proves it correct
`docs/decisions.md` + `docs/glossary.md`	Append-only decision ledger with an index, and one line per code name
`scripts/check_current_docs.py`	Blocks a commit when an entry file cites a superseded decision without saying so
`scripts/check_doc_structure.py`	Every doc has a header card; indexes list every file; entry files stay small
`scripts/worklog.py`, `new_log.py`	Daily log, and hours derived