A starting procedure for a new coding task that creates a change in Jujutsu, a version-control system, from the current default branch. It can also assign a named bookmark, similar to a branch label.

It helps begin an issue or feature using an issue number, issue URL, or a supplied bookmark name.

It gives new work a clean, up-to-date starting point and records it separately from unrelated changes.

checkout — Skill for Claude Code by martinemde/dotfiles

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 martinemde/dotfiles --skill checkout

Clone the repo

git clone --depth 1 https://github.com/martinemde/dotfiles

Made for: Claude Code.

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/martinemde/dotfiles/checkout/github.svg)](https://agentmods.dev/skills/martinemde/dotfiles/checkout)

Your own site

<a href="https://agentmods.dev/skills/martinemde/dotfiles/checkout"><img src="https://agentmods.dev/badge/skills/martinemde/dotfiles/checkout/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/martinemde/dotfiles/checkout"><img src="https://agentmods.dev/badge/skills/martinemde/dotfiles/checkout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 665 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00028	$0.00665
Opus 5.5	$0.00011	$0.00266
Sonnet 5.5	$0.00006	$0.00133
Haiku 4.5	$0.00003	$0.00067

Measured 5d ago against content hash 83a176b31bd0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

checkout 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 5d 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.

home/dot_agents/skills/checkout/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Checkout: Start a New Change for an Issue

Arguments

$ARGUMENTS

Gather Context

Before changing revisions, run jj status, jj diff --stat, and a short jj log covering @ and its recent ancestors. Use that output to determine whether the current change is empty, described, conflicted, or contains work that must be preserved.

Constraints

Use jj for all version control operations, never git.
Do not abandon changes or discard work without user confirmation.

Instructions

1. Parse Arguments

Determine what $ARGUMENTS contains:

Pattern	Action
`#123` or issue URL	Fetch issue title, derive bookmark name
Bookmark name (e.g., `feat/dark-mode`)	Use directly
Empty	Ask what to work on

2. Derive Bookmark Name (from issue)

If $ARGUMENTS is an issue reference:

Fetch: gh issue view <number> --json number,title,labels
Derive bookmark name from issue metadata:
- Check labels for conventional commit type hints (bug/fix labels → fix/, feature labels → feat/, chore/maintenance labels → chore/, default → feat/)
- Format: <prefix><number>-<kebab-case-title> (e.g., feat/123-add-dark-mode)
- Truncate to 60 characters max

3. Handle Existing Work

Check the gathered context for the current working copy state.

In jj, the working copy @ is always a change being edited. Before starting new work, assess:

Situation	Action
Working copy is empty (no diff)	Safe to proceed — `jj new` will leave an empty change behind (auto-abandoned)
Working copy has changes with a description	Suggest `jj commit` first to finalize, then proceed
Working copy has changes without a description	Suggest `jj commit -m "..."` or `jj describe -m "..."` first
Conflicts exist (`jj st` shows conflicts)	Inform user and wait for guidance

Read the full file on GitHub · 81 lines

Files

What ships with it

1 file 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.

README.md 2.3 KB

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.

5d ago Changed · -16 lines · +28 tokens per session 83a176b31bd0
1mo ago First seen · 97 lines · 0 tokens per session scan A 2bcc1f11fde7

Subscribe to this mod's changes

checkout is a skill published in the GitHub repository martinemde/dotfiles (10 stars, last pushed 2d ago), licensed ISC. It adds 28 tokens to every session and 665 once invoked, about $0.0001 per session on Opus 5.5. 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.

Claude Code Git and workflow chezmoi dotfiles jj

resolve-conflicts

Resolve Git merge or rebase conflicts by both sides' intent; verify the result.

fmind/dot · 21 tokens

github-pull-request

Open, update, and verify GitHub pull requests.

fmind/dot · 16 tokens

github-repository

Set GitHub repo description, topics, merge policy, and security settings.

fmind/dot · 19 tokens

repo-activity

Scan all git repositories under /repos and report recent activity — last commit age, branch, uncommitted changes — in age-bucketed tables. Use when the user asks for a repo activity overview, "what have I been working on", portfolio status, or which repos are active/dormant.

laurigates/dotfiles · 65 tokens

merge-ready

Drive an existing pull request to a mergeable state: get CI green, resolve merge conflicts with the base branch, address and resolve review comments, trigger required bot reviews/approvals (e.g. commenting '@claude review'), link associated issues, and clean up the PR title and description. Ends with a readiness…

urmzd/dotfiles · 208 tokens

sync-release

Owns release-pipeline conventions: sr.yaml schema, the sr CLI verbs (init/plan/prepare/ release) and urmzd/sr action, typed publishers (cargo/npm/pypi/docker/go/custom), monorepo workspace discovery, versionfiles/stagefiles mapping, and post-release patterns. Language-specific build targets live in scaffold-rust…

urmzd/dotfiles · 136 tokens