agentmods.dev

multi-agent-repo-handoff

multi-agent-repo-handoff is a cursor rule for Cursor from hojinlee/multi-agent-repo-handoff-skill. It costs 374 tokens per session, scanned A, original, MIT.

Rules for handing work between multiple coding agents in one GitHub repository. They define which project documents to read, how to use separate work-in-progress branches, and how to finish through a pull request.

In plain words
What is it for?
Use them when starting or ending agent work, creating a worker branch, reading handoff documentation, committing changes, or preparing work for review.
Why use it?
They reduce conflicts, preserve project context, and help prevent secrets or unsafe production changes from entering the repository.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions AGENTS.md.

not rated 7repo 2mo ago A scan 374 tokens original MIT

Good fit Use them when starting or ending agent work, creating a worker branch, reading handoff documentation, committing changes, or preparing work for review.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/hojinlee/multi-agent-repo-handoff-skill/multi-agent-repo-handoff
View source ↗ hojinlee/multi-agent-repo-handoff-skill
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.

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

Made for: Cursor.

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 multi-agent-repo-handoff

README.md
[![agentmods](https://agentmods.dev/badge/rules/hojinlee/multi-agent-repo-handoff-skill/multi-agent-repo-handoff/github.svg)](https://agentmods.dev/rules/hojinlee/multi-agent-repo-handoff-skill/multi-agent-repo-handoff)
Your own site
<a href="https://agentmods.dev/rules/hojinlee/multi-agent-repo-handoff-skill/multi-agent-repo-handoff"><img src="https://agentmods.dev/badge/rules/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.

agentmods 80×15 button for multi-agent-repo-handoff

Your own site · 80×15
<a href="https://agentmods.dev/rules/hojinlee/multi-agent-repo-handoff-skill/multi-agent-repo-handoff"><img src="https://agentmods.dev/badge/rules/hojinlee/multi-agent-repo-handoff-skill/multi-agent-repo-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 374 This file is loaded in full into every session.
When invoked 374 The same file — it is already loaded in full.
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 $0.00374 $0.00374
Opus 5 $0.00187 $0.00187
Sonnet 5 $0.00075 $0.00075
Haiku 4.5 $0.00037 $0.00037

Measured 11d ago against content hash 8837b53abcff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 11d 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.

.cursor/rules/multi-agent-repo-handoff.mdc · 55 lines

What it actually says

Multi-Agent Repo Handoff Rules

This repository may be worked on by multiple coding agents. GitHub and repository documents are the source of truth; chat history and local uncommitted changes are not.

First Read

Before changing code, read:

  1. AGENTS.md
  2. WORKLOG.md
  3. TODO.md
  4. docs/WORKERS.md
  5. docs/OPERATING_MODEL.md
  6. docs/HANDOFF.md
  7. docs/WORKER_ONBOARDING.md
  8. Project-specific architecture, data, and test documentation.

Branch Rules

  • Do not work directly on main.
  • Use a dedicated <worker-name>-wip branch.
  • Do not let two workers share a WIP branch concurrently.
  • Completed work should go to main through a PR.

Start

git status --short --branch
scripts/start_worker.sh --branch <worker-name>-wip

End

scripts/end_session.sh --commit -m "Describe completed work" --push

If there are no changes, run:

scripts/end_session.sh

Safety

  • Do not commit .env, API keys, account numbers, tokens, private certificates, raw data, generated reports, or large generated artifacts.
  • Do not run network/data download/live/production commands unless secrets are configured and the user explicitly expects it.
  • scripts/start_worker.sh fetches remotes and fast-forwards the worker branch by default. Update WORKLOG.md, TODO.md, and docs/WORKERS.md after meaningful work.
  • If validation fails, record the exact command and failure before handoff.
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. 11d ago First seen · 55 lines · 374 tokens per session scan A 8837b53abcff

Subscribe to this mod's changes

multi-agent-repo-handoff is a cursor rule published in the GitHub repository hojinlee/multi-agent-repo-handoff-skill (7 stars, last pushed 2mo ago), licensed MIT. It adds 374 tokens to every session, about $0.0019 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.

Git and workflow
Related

Other cursor rules, from other repositories

git-commit-attribution

Git commits must use the human developer identity only; never Cursor Agent co-authorship.

EastStarAI/sanad-agent · 254 tokens

iris

GitHub operations specialist — branches, pull requests, issues, releases, tags. Called by zeus after review. Never pushes or merges without explicit human approval. Integrates with VS Code GitHub Pull Requests extension.

ils15/pantheon-legacy · 43 tokens

rebase-only-merged-agents

When rebasing after a merge, only rebase the agents whose branches you just merged. Do not rebase agents that are still running.

briangmilnes/APAS-VERUS · 297 tokens

git-workflow

Rules for git operations, commit strategy, and GitHub CLI usage.

grafana/grafana-cube-datasource · 616 tokens

skill-management

The Clade capability renderer delivers skills to .cursor/skills/ /, commands to .cursor/commands/, and agent instructions to .cursor/agents/. These are distinct from .cursor/rules/ instruction delivery and from the native Task tool. Keep source/hash ownership for generated artifacts and preserve consumer-owned or…

YuDefine/nuxt-supabase-starter · 0 tokens

release-checklist

What to update with each code change or version release.

yoreai/relay · 215 tokens