commit
Commit the work done in this session, skipping files a parallel session also touched.
Skill by leek
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/leek-commit
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/commit
Tools it pre-approves 10
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Bash(gitstatus*)diffaddcommitshowlogapply--cached
What's inside
- Skill name
commit- Description
- Commit the work done in this session, skipping files a parallel session also touched.
- License
- MIT
- Allowed tools
- Bash(git, status, *), Bash(git, diff, *), Bash(git, add, *), Bash(git, commit, *), Bash(git, show, *), Bash(git, log, *), Bash(git, apply, --cached, *)
- Instructions
- 45 lines in SKILL.md · view on GitHub
Before installing
- Pre-approves some shell commands
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# Commit Commit **only what you changed in this session**. Other sessions may be working in the same repo at the same time; that is expected, and none of their work is yours to commit. ## Process 1. **List your files.** From this conversation, write down every file *you* created, edited, or deleted. Changes under `.claude/agent-memory/` are always yours too, whoever wrote them: they are the notes of agents with `memory: project`, not a parallel session's work in progress, so they ride along in your commit (`git add -- .claude/agent-memory`). If you touched nothing, say so and stop. 2. **Check the tree.** Run `git status --porcelain`. Anything not on your list belongs to someone else, ignore it completely. 3. **Drop the overlaps.** For each of your files, `git diff -- <path>` (`git diff --cached` too if it is already staged). If it contains changes you did not make, leave that file out, the other session will commit it. If a file mixes your hunks with foreign hunks, stage only yours: `git add -p -- <path>` needs an interactive terminal, so where the shell has none (Claude Code's Bash, most agent harnesses), write your hunks to a patch (`git diff -- <path> > "$TMPDIR/mine.patch"`, then delete the foreign hunks from it) and `git apply --cached "$TMPDIR/mine.patch"`. Never include a foreign hunk because it is small. Note which files you skipped. 4. **Commit by path, without touching the index.** Use `git commit --only -m "<subject>" -- <path> <path> …` (options before the `--`). `--only` commits exactly the named paths and ignores whatever another session has already staged, so a foreign `git add` can never ride along. Never `git add -A`, `git add .`, or `commit -a`. For a partially staged file from step 3, `git commit -m "<subject>" -- <path>` after staging your hunks instead. **New files are the exception:** `--only` silently skips untracked paths, so `git add -- <new-path>` each file you created first, then include it in the same `--only` list. Check `git status --porcelain` afterwards; a `??` line for one of your files means it was skipped. 5. **Subject.** Conventional Commits: `type(scope): summary`: imperative mood, lowercase, no trailing period, under 72 chars. Types: `feat`, `fix`, `refactor`, `docs`, `test`, `chore`, `perf`, `build`, `ci`. Scope optional. Add a short body only when *why* is not obvious from the diff. No attribution or co-author trailers. 6. **Report.** One line: the commit subject, the short SHA, and any files you deliberately left out and why. Do not push unless asked. ## Guardrails - **Commit to the current branch, whatever it is.** Never switch, create, or suggest a branch, not even when the current branch is `main`/`master`. No `git checkout`, `git switch`, `git branch`. - One session's work, one commit. Do not amend, rebase, or touch existing history. - If the changes are genuinely two unrelated things, make two commits, still your files only. - Never `git stash`, `git checkout --`, or `git reset`: a parallel session's uncommitted work is unrecoverable if you discard it. - Need a pre-change baseline of a file? Copy it aside and `git show HEAD:<path> > <path>`, run what you need, then restore the copy. A scoped stash plus immediate pop is still a stash.
From leek/agent-skills, MIT.
More from leek/agent-skills
- 0.614score
code-smells-audit
leek
Audit a codebase, path, or branch diff for classic code smells against the 56-smell Luzkan catalog (PHP/Laravel and TS/React heuristics).
SkillAFreshness: A★ 4Claude Code +9 - 0.614score
codebase-design
leek
Shared vocabulary for designing deep modules in any codebase.
SkillAFreshness: A★ 4Claude Code +9 - 0.614score
domain-modeling
leek
Build and sharpen a project's domain model: challenge terms against the glossary, resolve fuzzy language, stress-test concepts with concrete scenarios, and…
SkillAFreshness: A★ 4Claude Code +9 - 0.611score
autopilot
leek
Drive an existing wayfinder map, spec, or set of tickets to completion through fresh top-level Claude Code, Codex, or Grok sessions.
SkillAFreshness: A★ 4Claude Code +9 - 0.611score
browser-test
leek
Test a web app from a start URL and a plain-language prompt.
SkillAFreshness: A★ 4Claude Code +9 - 0.611score
chatter-scout
leek
Sweep the web for new chatter on a topic, skip what earlier runs already saw, verify what is left, and write one ranked, cited findings file to feed a blog…
SkillAFreshness: A★ 4Claude Code - 0.611score
closeout
leek
Check whether this session is safe to close: unsaved work, running jobs, open PRs, unanswered questions, and steps still to run.
SkillAFreshness: A★ 4Claude Code +9 - 0.611score
fix-posthog-issues
leek
Triage active PostHog error-tracking issues by root cause, fix the legit ones, and resolve or suppress the rest with evidence.
SkillAFreshness: A★ 4Claude Code +9 - 0.609score
grilling
leek
Interview the user one decision at a time until reaching shared understanding, resolving each branch of the decision tree with recommended options and…
SkillAFreshness: A★ 4Claude Code +9 - 0.608score
fix-github-issues
leek
Verify, triage, fix, and close review-bot GitHub issues one finding at a time.
SkillAFreshness: A★ 4Claude Code +9 - 0.603score
fix-nightwatch-issues
leek
Triage open Laravel Nightwatch production issues by root cause, fix the legit ones, and resolve them with evidence.
SkillAFreshness: A★ 4Claude Code +9 - 0.603score
dependency-audit
leek
Run a dependency audit for Composer or npm projects and propose a safe upgrade plan.
SkillAFreshness: A★ 4Claude Code
Signals
- Stars
- 4
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 21, 2026 (7 days ago)
- Last release
- Oct 23, 2026 (5 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/leek/agent-skills
- Website
- skills.sh/leek/agent-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from leek
- 0.614score
code-smells-audit
leek
Audit a codebase, path, or branch diff for classic code smells against the 56-smell Luzkan catalog (PHP/Laravel and TS/React heuristics).
SkillAFreshness: A★ 4Claude Code +9 - 0.614score
codebase-design
leek
Shared vocabulary for designing deep modules in any codebase.
SkillAFreshness: A★ 4Claude Code +9 - 0.614score
domain-modeling
leek
Build and sharpen a project's domain model: challenge terms against the glossary, resolve fuzzy language, stress-test concepts with concrete scenarios, and…
SkillAFreshness: A★ 4Claude Code +9 - 0.611score
browser-test
leek
Test a web app from a start URL and a plain-language prompt.
SkillAFreshness: A★ 4Claude Code +9 - 0.611score
autopilot
leek
Drive an existing wayfinder map, spec, or set of tickets to completion through fresh top-level Claude Code, Codex, or Grok sessions.
SkillAFreshness: A★ 4Claude Code +9 - 0.611score
chatter-scout
leek
Sweep the web for new chatter on a topic, skip what earlier runs already saw, verify what is left, and write one ranked, cited findings file to feed a blog…
SkillAFreshness: A★ 4Claude Code
Cite this page
commit skill. Agent Mart. https://agentmart.dev/skills/leek-commit (last updated 2026-10-24)