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.
npx skills add martinemde/dotfiles --skill commitgit clone --depth 1 https://github.com/martinemde/dotfilesWrote 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.
[](https://agentmods.dev/skills/martinemde/dotfiles/commit)<a href="https://agentmods.dev/skills/martinemde/dotfiles/commit"><img src="https://agentmods.dev/badge/skills/martinemde/dotfiles/commit/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.
<a href="https://agentmods.dev/skills/martinemde/dotfiles/commit"><img src="https://agentmods.dev/badge/skills/martinemde/dotfiles/commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00059 | $0.00561 |
| Opus 5.5 | $0.00024 | $0.00224 |
| Sonnet 5.5 | $0.00012 | $0.00112 |
| Haiku 4.5 | $0.00006 | $0.00056 |
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 1mo 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.
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.
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.
- 1mo ago First seen · 65 lines · 59 tokens per session scan A 78b567170cc7
commit is a skill published in the GitHub repository martinemde/dotfiles (10 stars, last pushed yesterday), licensed ISC. It adds 59 tokens to every session and 561 once invoked, about $0.0002 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.
Other skills, from other repositories
git-delivery
Stage, commit, push, and release scoped changes with Conventional Commits; fix hook failures.
ship
Generate a conventional commit message from staged or unstaged changes and create an atomic commit, then optionally push and watch CI until it passes or fails. Use when the user says "write a commit", "generate a commit message", "commit this", "git add .", or "ship this". Push and CI-watch are optional and skipped if…
git-add-commit-push
Stage, commit (Conventional Commits), and push in one flow, auto-healing lefthook pre-commit and pre-push failures. Use when committing and pushing work end-to-end.
lefthook
Canonical lefthook git-hooks setup — pre-commit (format, check, secret scan) and pre-push (test), each delegating to mise run tasks. Use when configuring or debugging git hooks.
conventional-commit
Write a Conventional Commits subject for the staged changes and commit them. Use when committing staged work with a typed, scoped message.
global-commit
Create a git commit following Conventional Commits specification.