commit

A guide for finishing changes in jj, a version-control system similar to Git. It covers describing the current change, separating unrelated work, and leaving the working copy clean.

In plain words
What is it for?
Use it to inspect a diff and recent history, split unrelated files, write a short change description, and advance to a clean working copy.
Why use it?
It prevents mixed changes from being bundled together and avoids vague descriptions of what changed. It also explains that jj's working copy is already a commit.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/martinemde/dotfiles/commit
Any agent
npx skills add martinemde/dotfiles --skill commit
Clone the repo
git clone --depth 1 https://github.com/martinemde/dotfiles

Made for: Claude Code, Codex.

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 561 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00059 $0.00561
Opus 5 $0.00030 $0.00280
Sonnet 5 $0.00012 $0.00112
Haiku 4.5 $0.00006 $0.00056

Measured 2d ago against content hash 78b567170cc7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

commit 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 2d 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_claude/skills/commit/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commit

Produce a clean atomic history ending on a fully clean working copy. In jj the working copy is already a commit, so "committing" is really two questions: is this change described well, and should @ advance.

Look first

Run these together — the description depends on all three:

jj diff                                                      # what actually changed
jj log -r "ancestors(@, 10)" --template builtin_log_oneline   # this repo's style
jj status                                                    # @'s current description

Split before describing

If @ holds unrelated changes, separate them rather than writing a description that lists two things:

jj split -m "message" <files>                # peel off part of @
jj squash --use-destination-message <files>  # fold files into the parent

Write the description

It should complete the phrase "This commit will…", and explain why in the body — the diff already shows what. One or two sentences.

Match the style you saw in the log. Where that log uses conventional commits, follow it; where it doesn't, don't introduce it. The verb carries meaning worth keeping consistent: "add" for something wholly new, "update" for an enhancement to what exists, "fix" for a bug. Add Fixes #NN when an issue closes.

For multi-line messages, use a heredoc so quoting doesn't mangle the body:

jj commit -m "$(cat <<'EOF'
Description here.

Co-Authored-By: Claude <[email protected]>
EOF
)"

Pick the command from @'s state

@ right now Command
Already well described jj new — or jj new -m "next plan"
Needs a description, ready to move on jj commit -m "..." — describes and advances
Needs a description, more work coming jj desc -m "..."

Then run jj status in the same message to confirm where you landed. When this is a handoff into new work, jj new -m "<goal of the new work>" starts it named.

Read the full file on GitHub · 65 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. 2d ago First seen · 65 lines · 59 tokens per session scan A 78b567170cc7

Subscribe to this mod's changes

commit is a skill published in the GitHub repository martinemde/dotfiles (9 stars, last pushed 1mo ago), licensed ISC. It adds 59 tokens to every session and 561 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

dotfiles-bootstrap

Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.

sebastienrousseau/dotfiles · 88 tokens

vibe

Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…

sebastienrousseau/dotfiles · 137 tokens

aiq-research

Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.

laurigates/dotfiles · 25 tokens

obsidian-bases

Obsidian Bases database feature for YAML-based interactive note views. Use when creating .base files, writing filter queries, building formulas, configuring table/card views, or working with Obsidian properties and frontmatter databases.

laurigates/dotfiles · 49 tokens

telegram

Send notifications, interactive questions, or multiple-choice polls to the user via Telegram. Use when the user asks to be notified ("ping me", "notify me on Telegram", "ask me when..."), when a long-running task finishes and the user is likely away, when an irreversible action needs out-of-band confirmation, or when…

laurigates/dotfiles · 117 tokens

chezmoi-expert

Comprehensive chezmoi dotfiles management expertise including templates, cross-platform configuration, file naming conventions, and troubleshooting. Covers source directory management, reproducible environment setup, and chezmoi templating with Go templates. Use when user mentions chezmoi, dotfiles, cross-platform…

laurigates/dotfiles · 88 tokens