metagit-agent-coordination

metagit-agent-coordination is a skill for Claude Code, Codex from metagit-ai/metagit-cli. It costs 70 tokens per session (1,426 once invoked), scanned A, original, MIT.

A coordination system for multiple coding agents working in one Git repository. It assigns separate branches and worktrees, which are independent copies of the repository, and records which files an agent intends to use.

In plain words
What is it for?
Use it before dispatching parallel agents, creating isolated workspaces, claiming files, or coordinating branches and merges.
Why use it?
It reduces collisions when agents work at the same time by separating their checkouts and making file ownership visible.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents).

Good fit Use it before dispatching parallel agents, creating isolated workspaces, claiming files, or coordinating branches and merges.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/metagit-ai/metagit-cli/metagit-agent-coordination
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add metagit-ai/metagit-cli --skill metagit-agent-coordination
Clone the repo
git clone --depth 1 https://github.com/metagit-ai/metagit-cli

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for metagit-agent-coordination

README.md
[![agentmods](https://agentmods.dev/badge/skills/metagit-ai/metagit-cli/metagit-agent-coordination/github.svg)](https://agentmods.dev/skills/metagit-ai/metagit-cli/metagit-agent-coordination)
Your own site
<a href="https://agentmods.dev/skills/metagit-ai/metagit-cli/metagit-agent-coordination"><img src="https://agentmods.dev/badge/skills/metagit-ai/metagit-cli/metagit-agent-coordination/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for metagit-agent-coordination

Your own site · 80×15
<a href="https://agentmods.dev/skills/metagit-ai/metagit-cli/metagit-agent-coordination"><img src="https://agentmods.dev/badge/skills/metagit-ai/metagit-cli/metagit-agent-coordination.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,426 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.01426
Opus 5 $0.00035 $0.00713
Sonnet 5 $0.00014 $0.00285
Haiku 4.5 $0.00007 $0.00143

Measured 9d ago against content hash c4de96bc0b42, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

metagit-agent-coordination scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/metagit-agent-coordination/SKILL.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Metagit Agent Coordination Layer (ACL)

Use when more than one agent may edit the same repository, or when an orchestrator must give each agent an exclusive checkout.

Full reference: docs/reference/agent-coordination.md

Task graphs (metagit task …) can store ACL command hints on nodes via metagit task bind-acl without running git — see docs/reference/task-graph.md.

Merge orchestration (metagit merge …) records conflicts with ACL command hints only; it does not allocate branches or worktrees automatically.

The agent scheduler (metagit schedule next) scores ready task nodes and returns dispatch hints without launching models or mutating git — see docs/reference/agent-scheduler.md.

For a composed operator snapshot and next-work envelope across ACL + task graph + optional 0009–0012, use skill metagit-aos (metagit aos|coord status|doctor|next) — see docs/reference/aos.md.

When to use

  • Dispatching parallel subagents on the same repo
  • handoff.acl_commands appears in metagit agent dispatch-plan
  • Preventing two agents from sharing a working directory
  • Declaring intended file paths before coding (advisory claims)
  • Cleaning up expired leases / orphan worktrees

Do not confuse with handoff leases

Concept Command Owns
Handoff claim TTL metagit context handoff claim --ttl Task-queue row
ACL branch lease metagit lease acquire agent/* branch

Happy path

export METAGIT_AGENT_MODE=true

# 1. Allocate an exclusive agent branch
metagit branch allocate \
  --repository project/repo \
  --agent-id agent-1 \
  --task-id 412 \
  --description auth \
  --json

# 2. Lease it (default TTL 30m; renew while working)
metagit lease acquire \
  --repository project/repo \
  --agent-id agent-1 \
  --task-id 412 \
  --allocate \
  --ttl 30m \
  --json

# 3. Create an isolated worktree (requires active lease)
metagit worktree create \
  --repository project/repo \
  --agent-id agent-1 \
  --task-id 412 \
  --branch agent/412-auth \
  --json

# 4. Optional: advisory file claims before editing
metagit claim declare \
  --repository project/repo \
  --agent-id agent-1 \
  --pattern 'src/auth/*' \
  --json

# 5. Show execution manifest written on create
metagit worktree manifest agent-1

Read the full file on GitHub · 155 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 155 lines · 70 tokens per session scan A c4de96bc0b42

Subscribe to this mod's changes

metagit-agent-coordination is a skill published in the GitHub repository metagit-ai/metagit-cli (3 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 1,426 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories