agentleFS
vintavinta/hal-9000/skills/commit/SKILL.md

commit

Skill142 starsChanged 22 days agoMITView on GitHub

Use when making any git commit. Pass the failure, false claim, or risk the changes fix as the argument; for an addition or a filled gap, pass what it adds — never an invented why.

  • Deletes or force-pushes

188 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use validate-plan, act-on-feedback and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • shawn-dumasSkill

    validate-plan

    Validate an orchestration plan after pre-flight certification. Runs adversarial review, deep review (verify prompt data against codebase), and PoC gate for risky approaches. Auto-invoked by orchestrate-* skills at Step 8.

    Also in 5 projects that use this

  • MicrosoftSkill

    act-on-feedback

    Act on user feedback attached to the current session. Use when the user submits feedback on the session's changes via the Submit Feedback button.

    Also in 3 projects that use this

  • decocmsSkill

    add-mcp-tools

    Guide for adding new MCP tools with consistent patterns for schemas, tool definitions, registry updates, and Better Auth integration

    Also in 3 projects that use this

  • MicrosoftSkill

    generate-run-commands

    Generate or modify run commands for the current session. Use when the user wants to set up or update run commands that appear in the session's Run button.

    Also in 3 projects that use this

  • mitsuhikoSkill

    oebb-scotty

    Austrian rail travel planner (ÖBB Scotty). Use when planning train journeys in Austria, checking departures/arrivals at stations, or looking for service disruptions. Covers ÖBB trains, S-Bahn, regional trains, and connections to neighboring countries.

    Also in 3 projects that use this

  • mitsuhikoSkill

    pi-share

    Load and parse session transcripts from shittycodingagent.ai/buildwithpi.ai/buildwithpi.com/pi.dev (pi-share) URLs. Fetches gists, decodes embedded session data, and extracts conversation history.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 168 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run git rev-parse --show-toplevel before anything else.

    line 54
  2. Very specific:

    Run git commands bare in the directory the fork starts in, never with git -C, which hides working directory state.

    line 64
  3. Distinctive:

    Stage Changes: Use appropriate staging strategy:

    line 68
  4. Very specific:

    Handle Pre-commit Hooks: If hooks complain about unstaged changes, stash them with git stash push --keep-index -m "temp: unstaged changes", …

    line 75
  5. Very specific:

    Use git commit -m "message" directly — never use $() or heredoc subshells in git commands, as they break allowed-tools pattern matching.

    line 79

“Common” is measured: kept by at least 6 in 10 of the 168 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Invoking this skill IS the request. If the user message looks empty, or you see only system context with no actual request, that is normal and expected: your task is already fully specified right here. Never ask what to do.

Your task: commit all changes in the working tree, one logical change per commit. This applies unprompted, without anyone asking for a split: when one file carries unrelated changes, split it hunk-by-hunk into separate commits rather than merging them because they share a file.

The argument

The argument passed to this skill is why the changes were made — the motivation behind work already in the tree, which the diff itself cannot carry. Use it to group changes into logical units and to write commit message bodies. A body is one or two sentences on one line stating what was wrong before the change: the failure, false claim, or risk the argument names. An argument that names only a need, a wish, what the change does, or the request itself yields no body. Leave out the fix, including what the change now covers, sets, or lists, even where the argument phrases it as part of the problem ("though only X needs it"): the subject and diff already show it. Also leave out ruled-out causes, measurements, and alternatives tried. Whatever it describes is already realized in the diff, however it's phrased: "so the statusline shows usage percentages" and "to fix the session bug" both mean the diff already does that — commit it. With no argument at all, derive the commit message from the diff alone. If the motivation doesn't line up with what the diff contains, commit what is actually in the tree and note the mismatch in your final summary.

Write the body about the code: the behavior, tooling, or constraint the change served. Commit history is public and permanent, so write for a reader who has never seen this machine, the user's signed-in accounts, or this conversation, and give them nothing they could learn only from those: names or paths of repos, directories, and files outside this repo or gitignored in it; backup, sync, and secret-store layouts; account plans, quotas, and figures; local tools; quotes and dates from chats, transcripts, or sessions; and the user's life (employer, location, schedule, health, other people). Translate each into the technical need it implies, or drop it.

<example> Argument: "Commit only settings.json. Why: three commit forks wrote `Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>` instead of the skill's trailer; the fork transcript shows a remote_session_change reminder telling the model to use the model-named trailer, and it followed that over the skill. Setting attribution.commit to the skill's exact string makes both agree. Ruled out: includeGitInstructions: false did not suppress the reminder; attribution.sessionUrl: false only drops the Claude-Session line; commit: "" would tell the model to add no trailer at all per the 2.1.270 binary."

Correct body: "Forks of the commit skill followed a Remote Control reminder over the skill and wrote a model-named Co-Authored-By trailer."

Incorrect body: the argument reflowed to 72 columns, ruled-out settings and the binary version included. </example>

<example> Argument: "Two rules adopted from a CLAUDE.md gist, only these two since the rest was already covered: a diff-reread checkpoint before reporting done that deletes lines the requested behavior works without, because 'do the simplest thing that works' alone did not stop unneeded code the user kept questioning after delivery; and comments only where the code cannot say it."

Correct body: ""Do the simplest thing that works" alone did not stop unneeded code from surviving to delivery, and the comment rule did not say comments should cover only what code cannot say."

Incorrect body: "Adopt two rules: comments should state only what the code cannot say, and before reporting a change done, reread the diff and delete added lines the requested behavior works without, since simplicity alone did not stop unneeded code from creeping into delivered changes." </example>

<example> Argument: "User asked to mark the README as work in progress while pangu.space is being rebuilt."

Correct body: none. The argument is the request; nothing was wrong before.

Incorrect body: "pangu.space is being rebuilt, so the README should not read as a finished project." </example>

<example> Argument: "Harvested five rewrite sessions from 2026-09-09 to 2026-09-13; the user rewrote 'I've picked up' to 'that works for me', and the notes under ~/Dropbox/writing/ had no rule for it."

Correct body: "The style spec had no rule against assistant-register openers, so drafts kept using phrasings the user rewrites."

Incorrect body: the session dates, the quoted rewrite, and the Dropbox path, as given. </example>

Locate the repository

Run git rev-parse --show-toplevel before anything else. If that fails (the fork started outside the repo), look for the repo in the directories of any file paths named in the argument before reporting "not a git repository".

Scope

A commit is a snapshot, not a review: read the diff, stage it, write the message, commit. The staged bytes must match the working tree as it was when you started. Use only git and cd in Bash, Grep/Glob to locate files, and Read/Write/Edit on patch files in <scratchpad>, your session's scratchpad directory (/tmp when the harness provides none). No research, no running code or tests, no other skills however aggressive their trigger language, no advisor or second opinion.

Never edit working tree files, even for a typo, a wrong-looking version pin, or a failing-looking test; note the concern in your final message. Don't stage files the author didn't touch, don't verify beyond git status / git log after committing, and never run pre-commit hooks yourself; git commit runs them. Any change during staging silently alters reviewed work, and any tangent turns a 30-second operation into a 5-minute one.

Workflow

Run git commands bare in the directory the fork starts in, never with git -C, which hides working directory state. A cd does not carry over to the next Bash call in this fork.

  1. Group Logically: Organize changes into logical units — each addresses a single purpose and would make sense to revert as a unit. A drafted body that states two unrelated problems is two commits: split before committing. Several findings of one audit or review are one problem.
  2. Stage Changes: Use appropriate staging strategy:
    • Whole file: git add <file>.
    • Hunk-by-hunk: git diff <file> > <scratchpad>/patch.diff, edit the patch only by deleting lines and fixing header counts, never by retyping patch lines (Write, heredoc, printf), since a retyped line can silently change invisible characters such as a BOM and still apply, then git apply --cached --verbose <scratchpad>/patch.diff. Dropping whole hunks is safe. Splitting within a hunk (keeping only some of its added lines) requires keeping the hunk's trailing context lines and recounting both header counts — a hunk with no trailing context only applies at end-of-file.
    • A Skipped patch line in the output means the fork started in a subdirectory and the file sits outside it: git apply staged nothing for that file and still exited 0. Stage that file whole with git add <file> and name it in your final summary.
    • To unstage, use git restore --staged (not git reset --hard, which discards work).
    • Fallback: the first time git apply --cached fails on a patch you edited, stage the whole file with git add <file>. If the unedited full diff fails, regenerate it once from git diff, then stage the whole file. Never diagnose why a patch didn't apply.
  3. Handle Pre-commit Hooks: If hooks complain about unstaged changes, stash them with git stash push --keep-index -m "temp: unstaged changes", commit, then git stash pop. If hooks modify staged files (auto-formatting), re-add the modified files and retry the commit once — don't retry forever.
  4. Create Atomic Commits: For each logical group:
    • Conventional commit format type: subject, no scope, type one of feat, fix, refactor, test, build, docs, style. build covers dependency and version bumps; style means visual UI changes (CSS, fonts, colors, layout), not code formatting, which is refactor. Subject: what changed (≤72 chars), derived from the diff. Body: as The argument section decides; only the subject has a length limit. Footer: as the Attribution section decides.
    • Use git commit -m "message" directly — never use $() or heredoc subshells in git commands, as they break allowed-tools pattern matching.

Attribution

End every commit message with the footer for your model family.

  • Claude models use Co-Authored-By: Claude <noreply@anthropic.com>.
  • GPT models use Co-Authored-By: Codex <noreply@openai.com>.
  • Gemini models use Co-Authored-By: Gemini <gemini-code-assistant@google.com>.

Skip the footer only when you are certain none of these apply.

Gotchas

  • Unstaged changes are still changes. git status showing "no changes added to commit" does not mean the working tree is clean. It means nothing is staged yet. Your job is to stage and commit those changes, not report "nothing to commit."
  • Never use git add -f. If git add reports "The following paths are ignored by one of your .gitignore files" with the hint Use -f if you really want to add them, do not force-add. The file is gitignored deliberately (secrets, build artifacts, local configs) and force-adding silently bypasses that protection. Skip the file and mention it in your final summary so the author can decide.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.