start-worktree

start-worktree is a skill for Claude Code, Codex from jason21wc/ai-governance-mcp. It costs 70 tokens per session (398 once invoked), scanned A, original, Apache-2.0.

A skill for safely preparing and managing an isolated Git worktree. A worktree is a separate checkout of a repository that lets work happen without changing the main checkout.

In plain words
What is it for?
Starting, resuming, validating, or cleaning up worktrees for coding-agent sessions.
Why use it?
It helps prevent concurrent coding sessions from using the same checkout or task branch, while checking that preparation and cleanup are safe.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; mentions Codex.

Good fit Starting, resuming, validating, or cleaning up worktrees for coding-agent sessions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jason21wc/ai-governance-mcp/start-worktree
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 jason21wc/ai-governance-mcp --skill start-worktree
Clone the repo
git clone --depth 1 https://github.com/jason21wc/ai-governance-mcp

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 start-worktree

README.md
[![agentmods](https://agentmods.dev/badge/skills/jason21wc/ai-governance-mcp/start-worktree/github.svg)](https://agentmods.dev/skills/jason21wc/ai-governance-mcp/start-worktree)
Your own site
<a href="https://agentmods.dev/skills/jason21wc/ai-governance-mcp/start-worktree"><img src="https://agentmods.dev/badge/skills/jason21wc/ai-governance-mcp/start-worktree/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 start-worktree

Your own site · 80×15
<a href="https://agentmods.dev/skills/jason21wc/ai-governance-mcp/start-worktree"><img src="https://agentmods.dev/badge/skills/jason21wc/ai-governance-mcp/start-worktree.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 398 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 $0.00398
Opus 5 $0.00035 $0.00199
Sonnet 5 $0.00014 $0.00080
Haiku 4.5 $0.00007 $0.00040

Measured 10d ago against content hash d595fb69745f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

start-worktree 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 10d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (cleanup.sh, preflight.sh, prepare.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.

global-skills/start-worktree/SKILL.md · 30 lines

What it actually says

Start Worktree

Read procedure.md completely, identify the actual host, and follow that host's adapter. The load-bearing behavior lives in the scripts beside this file:

  • preflight.sh verifies exact local/worktree/live-remote name surfaces and base freshness.
  • prepare.sh creates or adopts a checkout through recorded, retryable transitions and detects duplicate task intent across isolated paths.
  • cleanup.sh refuses removal until ownership, durability, completeness, ignored-file, and cleanliness checks pass; a coherent v2 owner can acknowledge finalization atomically without --force.

Do not replace a failed or unavailable script with remembered Git commands. An unrun check is not a pass. Report the script's exit code and findings.

The invariant is one mutating session per checkout and per wt/* topic branch. Task keys detect two isolated sessions doing the same work; they do not replace that checkout isolation or create a global lock. A Git worktree isolates tracked files, the index, HEAD, and branch; it does not isolate ports, databases, daemons, caches, editable installs, ignored files, user configuration, or symlink targets. Use the optional runtime hooks described in procedure.md when those shared resources need namespacing.

Host permissions remain separate from skill execution. In particular, a managed Codex profile may permit checkout edits while denying the common Git-directory writes needed for worktree creation, fetch, staging, commits, refs, and cleanup; the Codex CLI adapter documents the ordinary-shell handoff for that case.

Files

What ships with it

4 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.

  1. 10d ago First seen · 30 lines · 70 tokens per session scan A d595fb69745f

Subscribe to this mod's changes

start-worktree is a skill published in the GitHub repository jason21wc/ai-governance-mcp (0 stars, last pushed 10d ago), licensed Apache-2.0. It adds 70 tokens to every session and 398 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

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