mav-multi-instance-coordination

mav-multi-instance-coordination is a skill for Claude Code from thermiteau/maverick. It costs 50 tokens per session (1,657 once invoked), scanned A, original, Apache-2.0.

A coordination protocol for multiple coding-agent sessions working on the same GitHub issue or larger task. It uses GitHub labels and comments to record who owns the work and whether that ownership is still active.

In plain words
What is it for?
Claiming and releasing issues, renewing ownership with heartbeats, checking for blocking issues, detecting expired claims, and coordinating takeovers across machines.
Why use it?
It reduces the risk of two agents changing the same work at once. It also helps detect when an agent has stopped responding so another can safely take over.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions Claude Code.

Part of the maverick plugin — 41 skills, 5 agents, 5 hooks shipped together

Good fit Claiming and releasing issues, renewing ownership with heartbeats, checking for blocking issues, detecting expired claims, and coordinating takeovers across machines.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thermiteau/maverick/mav-multi-instance-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 thermiteau/maverick --skill mav-multi-instance-coordination
Clone the repo
git clone --depth 1 https://github.com/thermiteau/maverick

Made for: Claude Code.

Or install maverick, the plugin that ships this one along with the rest of its 41 skills, 5 agents, 5 hooks.

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 mav-multi-instance-coordination

README.md
[![agentmods](https://agentmods.dev/badge/skills/thermiteau/maverick/mav-multi-instance-coordination.svg)](https://agentmods.dev/skills/thermiteau/maverick/mav-multi-instance-coordination)
Your own site
<a href="https://agentmods.dev/skills/thermiteau/maverick/mav-multi-instance-coordination"><img src="https://agentmods.dev/badge/skills/thermiteau/maverick/mav-multi-instance-coordination.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,657 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 $0.00050 $0.01657
Opus 5 $0.00025 $0.00829
Sonnet 5 $0.00010 $0.00331
Haiku 4.5 $0.00005 $0.00166

Measured 7d ago against content hash b5d105a11452, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mav-multi-instance-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 7d 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.

skills/mav-multi-instance-coordination/SKILL.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Instance Coordination

Several Claude Code instances, on different machines, may be asked to act on the same issue or epic at the same time. This skill defines how they coordinate so that:

  • Two instances never silently step on the same story.
  • A machine dying without notice is detected within ~10 minutes.
  • No committed work is lost on takeover.

All coordination state is on GitHub. The local filesystem is a cache.

Entry check — before any work

Every workflow entry point must run the entry check before touching an issue. The CLI helper uv run maverick coord read <repo> <issue> returns a JSON snapshot; parse it and decide:

digraph entry {
    "Read claim state" [shape=box];
    "blocked-by:#N label?" [shape=diamond];
    "Abort — report block to user" [shape=box];
    "claude-in-progress label?" [shape=diamond];
    "lease live?" [shape=diamond];
    "Abort — report holder + expiry" [shape=box];
    "Stale lease — takeover or defer" [shape=diamond];
    "Claim scope" [shape=box];
    "Claim" [shape=box];

    "Read claim state" -> "blocked-by:#N label?";
    "blocked-by:#N label?" -> "Abort — report block to user" [label="yes"];
    "blocked-by:#N label?" -> "claude-in-progress label?" [label="no"];
    "claude-in-progress label?" -> "lease live?" [label="yes"];
    "claude-in-progress label?" -> "Claim scope" [label="no"];
    "lease live?" -> "Abort — report holder + expiry" [label="yes"];
    "lease live?" -> "Stale lease — takeover or defer" [label="no"];
    "Stale lease — takeover or defer" -> "Claim" [label="take over"];
    "Claim scope" -> "Claim";
}

The four exit points

Exit When Action
Blocked blocked-by:#N label present Report to user; do not claim, do not modify issue
Claimed with live lease Another instance is active Report holder id and expiry; do not modify issue
Claimed with stale lease Holder likely crashed Decide: take over now, or defer
Free No claim or stale/absent lease Claim and proceed

Read the full file on GitHub · 172 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. 7d ago First seen · 172 lines · 50 tokens per session scan A b5d105a11452

Subscribe to this mod's changes

mav-multi-instance-coordination is a skill published in the GitHub repository thermiteau/maverick (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 50 tokens to every session and 1,657 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 2026-08-30.

Related

Other skills, from other repositories

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

story-readiness

Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…

Donchitos/Claude-Code-Game-Studios · 77 tokens

autotask-creator

Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.

Orkas-AI/Orkas · 5 tokens

monorepo-management

Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.

wshobson/agents · 54 tokens