What is multi-agent-repo-handoff?

A toolkit for letting several coding agents share work on one GitHub repository. It records branch rules, onboarding instructions, work logs, scripts, and other handoff material so an agent can continue work without relying on chat history or local uncommitted files.

Use it to set up or update agent instructions, WIP branch conventions, GitHub templates, CI, handoff scripts, and repository documentation.

It reduces confusion when work moves between agents, computers, or temporary workers, especially when unfinished changes must be handed over safely.

multi-agent-repo-handoff — Skill for Claude Code and Codex by hojinlee

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 hojinlee/multi-agent-repo-handoff-skill --skill multi-agent-repo-handoff

Clone the repo

git clone --depth 1 https://github.com/hojinlee/multi-agent-repo-handoff-skill

Made for: Claude Code, Codex.

Or install multi-agent-repo-handoff, the plugin that ships this one along with the rest of its 1 skill.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/hojinlee/multi-agent-repo-handoff-skill/multi-agent-repo-handoff/github.svg)](https://agentmods.dev/skills/hojinlee/multi-agent-repo-handoff-skill/multi-agent-repo-handoff)

Your own site

<a href="https://agentmods.dev/skills/hojinlee/multi-agent-repo-handoff-skill/multi-agent-repo-handoff"><img src="https://agentmods.dev/badge/skills/hojinlee/multi-agent-repo-handoff-skill/multi-agent-repo-handoff/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/hojinlee/multi-agent-repo-handoff-skill/multi-agent-repo-handoff"><img src="https://agentmods.dev/badge/skills/hojinlee/multi-agent-repo-handoff-skill/multi-agent-repo-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,116 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.

Model	Per session	Once invoked
Fable 5.1	$0.00112	$0.01116
Opus 5	$0.00056	$0.00558
Sonnet 5	$0.00022	$0.00223
Haiku 4.5	$0.00011	$0.00112

Measured 12d ago against content hash d56681fca647, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

multi-agent-repo-handoff 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 12d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (assets/scripts/end_session.sh, assets/scripts/handoff_check.sh, assets/scripts/start_worker.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

multi-agent-repo-handoff/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Agent Repo Handoff

Use this skill to make a repository safe for multiple coding agents to share through GitHub without relying on chat history or local uncommitted state. It can scaffold Codex skills, Claude Code instructions, and instruction-only entrypoints for other agent tools.

Core Workflow

Inspect the repo state:
- git status --short --branch
- git remote -v
- existing docs such as AGENTS.md, CLAUDE.md, WORKLOG.md, TODO.md, .github/, and docs/.
Choose the branch model from references/branch-model.md.
Add or update worker onboarding docs using references/worker-onboarding.md.
Copy scripts from assets/scripts/ if equivalent scripts do not already exist.
Copy GitHub templates and CI from assets/github/ when the repo uses GitHub.
Copy starter docs from assets/docs/ only when the repo lacks equivalent docs; otherwise merge the relevant sections.
Update existing agent entrypoints instead of replacing project-specific instructions.
Validate with the repo test command and the generated handoff scripts.
Commit and push on the appropriate WIP branch when cross-agent continuity is required.

Multi-Agent Distribution Targets

When publishing or adapting this package, keep these entrypoints aligned:

multi-agent-repo-handoff/SKILL.md for Codex skill usage.
AGENTS.md for Codex and generic agent project instructions.
CLAUDE.md for Claude Code.
.github/copilot-instructions.md for GitHub Copilot.
.cursor/rules/*.mdc for Cursor.
.windsurf/rules/*.md for Windsurf.
.clinerules for Cline.
.opencode/AGENTS.md for OpenCode.
.agents/rules/*.md for generic agent-rule consumers.

Files To Prefer

For a generic repo, create or update these files:

AGENTS.md: primary Codex/agent instructions.
CLAUDE.md: Claude Code entrypoint when Claude Code may work on the repo.
WORKLOG.md: current context, decisions, failures, next steps.
TODO.md: task queue and completion state.
docs/OPERATING_MODEL.md: branch, commit, push, PR, CI, and safety rules.
docs/HANDOFF.md: start/end session commands.
docs/WORKERS.md: worker status board with branch, task, issue/PR, and next safe step.
docs/WORKER_ONBOARDING.md: instructions for new workers.
docs/CODEX_CONTINUITY.md: copy-paste prompt for Codex-like workers.
scripts/handoff_check.sh: safe local state inspection.
scripts/start_worker.sh: switch/create worker branch.
scripts/worker_status.sh: show worker board and branch ahead/behind state.
scripts/end_session.sh: test/check/optional commit/push session closure.
.github/PULL_REQUEST_TEMPLATE.md, .github/ISSUE_TEMPLATE/task.yml, .github/workflows/ci.yml.

Read the full file on GitHub · 94 lines

Files

What ships with it

17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

12d ago First seen · 94 lines · 112 tokens per session scan A d56681fca647

Subscribe to this mod's changes

multi-agent-repo-handoff is a skill published in the GitHub repository hojinlee/multi-agent-repo-handoff-skill (7 stars, last pushed 2mo ago), licensed MIT. It adds 112 tokens to every session and 1,116 once invoked, about $0.0006 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.

Building agents Git and workflow

prowler-commit

Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.

prowler-cloud/prowler · 33 tokens

gh-auth-isolation

Safely manage multiple GitHub identities (EMU + personal) in agent workflows.

github/gh-aw · 20 tokens

comet-github

A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.

rpamis/comet · 72 tokens

github-skill

Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.

zeenie-ai/OpenCompany · 51 tokens

changelog-composer

Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".

Mathews-Tom/armory · 67 tokens

re0-merge

Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…

LilMGenius/paperthin · 70 tokens