isolated-worktree-handoff

isolated-worktree-handoff is a skill for Claude Code, Codex from HappyMonkeyAI/AgentsProtocol. It costs 38 tokens per session (1,030 once invoked), scanned A, original, MIT.

A workflow for giving parallel coding agents separate Git worktrees, branches, and evidence handoffs. A worktree is an isolated working directory connected to its own branch.

In plain words
What is it for?
Use it when several agents implement parts of a task, when a clean branch history is required, or when handing completed work between agents.
Why use it?
It prevents parallel agents from overwriting one another's files and keeps changes reviewable. It also preserves a clear record of what was changed and verified.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/tasks.py claim <task-id>.

Good fit Use it when several agents implement parts of a task, when a clean branch history is required, or when handing completed work between agents.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/HappyMonkeyAI/AgentsProtocol
agentmods
npx agentmods add skills/happymonkeyai/agentsprotocol/isolated-worktree-handoff

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 isolated-worktree-handoff

README.md
[![agentmods](https://agentmods.dev/badge/skills/happymonkeyai/agentsprotocol/isolated-worktree-handoff.svg)](https://agentmods.dev/skills/happymonkeyai/agentsprotocol/isolated-worktree-handoff)
Your own site
<a href="https://agentmods.dev/skills/happymonkeyai/agentsprotocol/isolated-worktree-handoff"><img src="https://agentmods.dev/badge/skills/happymonkeyai/agentsprotocol/isolated-worktree-handoff.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,030 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 $0.00038 $0.01030
Opus 5 $0.00019 $0.00515
Sonnet 5 $0.00008 $0.00206
Haiku 4.5 $0.00004 $0.00103

Measured 3d ago against content hash 2e02ee62f98b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

isolated-worktree-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 3d 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/isolated-worktree-handoff/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Isolated worktree and evidence handoff

Operationalizes ADR-0002. Complements ADR-0001 Owner acceptance.

Upstream pattern: ai-agent-teamwork-prompt (worktree + branch mode).

When to use

  • Parallel Workers on one repo
  • Clean, reviewable branch history required
  • Orchestrator selected branch / worktree mode
  • Delegating implementation to a sub-agent / external CLI

When not to use

  • Solo Quick Mode on an already-correct branch with no parallel writers
  • Read-only reconnaissance
  • Shared-checkout rapid swarm with working file locks and non-overlapping claims (still use evidence handoff shape)

Mode picker

Situation Mode
Solo, small change, clean tree Shared-checkout OK
Parallel implementation Branch / worktree (default)
Teamwork scripts present + rapid prototype Shared-checkout + locks
Merge history must stay linear/reviewable Branch / worktree

Setup (branch / worktree mode)

git status --short --branch
git worktree add .worktrees/<task-id> -b ag/<task-id> <base-ref>
cd .worktrees/<task-id>
  • Protocol branch prefix: ag/<task-id>
  • Teamwork interop: agent/<task-id> accepted; do not mix prefixes for one task
  • Fallback: separate clone if worktrees unavailable
  • Ensure .worktrees/ is gitignored at repo root
  • Confirm path, branch, baseline commit before any edit

Dirty-tree rules

- [ ] Baseline dirty paths recorded in handoff
- [ ] No reset --hard / clean / stash-clobber of pre-existing work
- [ ] No git add . ; stage only in-scope paths
- [ ] Generated artifacts unstaged unless explicitly in scope
- [ ] Commit/push only if user or orchestrator authorized

Pulse dead-end recovery (reset --hard) applies only to this agent’s failed branch/worktree, never to wipe sibling or human dirty state on the primary checkout.

Read the full file on GitHub · 123 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. 3d ago First seen · 123 lines · 38 tokens per session scan A 2e02ee62f98b

Subscribe to this mod's changes

isolated-worktree-handoff is a skill published in the GitHub repository HappyMonkeyAI/AgentsProtocol (5 stars, last pushed 4d ago), licensed MIT. It adds 38 tokens to every session and 1,030 once invoked, about $0.0002 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 2026-09-04.

Related

Other skills, from other repositories

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

codex-autoresearch

Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…

leo-lilinxiao/codex-autoresearch · 80 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