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 agentmods add skills/paulbreuler/limps/git-commit-best-practicesnpx skills add paulbreuler/limps --skill git-commit-best-practicesgit clone --depth 1 https://github.com/paulbreuler/limpsWhat 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 | $0.00041 | $0.02490 |
| Opus 5 | $0.00020 | $0.01245 |
| Sonnet 5 | $0.00008 | $0.00498 |
| Haiku 4.5 | $0.00004 | $0.00249 |
Grade A, and why
git-commit-best-practices 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.
How it starts
The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Commit Best Practices (limps)
Purpose
Guide the creation of clear, meaningful Git commits that follow conventional commit standards and repository-specific conventions. Ensures commits are atomic, well-documented, and integrate with automated tooling (release-please, changelog generation).
Scope
- If
$ARGUMENTSis "review-commits" or a commit range (e.g.,HEAD~5..HEAD,main..HEAD), review existing commits and suggest improvements. - If
$ARGUMENTSis a scope (paths or component), provide commit guidance for those changes. - If no arguments provided, guide commit message creation for staged changes.
Detecting Breaking Changes
When reviewing commits, detect breaking changes by:
- Parse commit messages:
git log --format="%H%n%s%n%b" <range>(includes full body) - Search for footer: Look for
BREAKING CHANGE:orBREAKING CHANGEin commit body (case-insensitive) - Extract description: Everything after
BREAKING CHANGE:until:- Next footer (e.g.,
Closes #123,Fixes #456) - End of commit message
- Empty line followed by non-footer text
- Next footer (e.g.,
- Example commands:
- Simple:
git log --format=%B main..HEAD | grep -A 10 -i "BREAKING CHANGE" - More robust:
git log --format="%H%n%s%n%b%n---" <range>then parse each commit separately
- Simple:
- Edge cases:
- Multi-line breaking changes: Extract until next footer or end
- Breaking change in subject: Look for
!after type/scope:feat!: breaking change - Merge commits: Check merge commit message for breaking changes
Conventional Commit Format
Structure
<type>(<scope>): <subject>
<body>
<footer>
Types
feat: New feature (triggers minor version bump)fix: Bug fix (triggers patch version bump)docs: Documentation changes onlystyle: Code style changes (formatting, whitespace, no logic change)refactor: Code refactoring (no feature change or bug fix)perf: Performance improvementstest: Adding or updating testschore: Maintenance tasks (deps, config, build)ci: CI/CD changesbuild: Build system changesrevert: Revert a previous commit
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.
- 2d ago First seen · 284 lines · 41 tokens per session scan A 5e9df9986e55
git-commit-best-practices is a skill published in the GitHub repository paulbreuler/limps (10 stars, last pushed 6mo ago), licensed MIT. It adds 41 tokens to every session and 2,490 once invoked, about $0.0002 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.
Other skills, from other repositories
map-plan
ARCHITECT phase - decompose complex tasks into atomic subtasks with research, spec, and branch-scoped plan artifacts under .map.
map-tdd
TDD MAP workflow: write tests from the spec FIRST, then implement, so tests validate intent not implementation. Use when correctness is critical (auth, payments, data integrity). Do NOT use without a spec; use map-efficient instead.
map-review
Interactive 4-section code review using monitor, predictor, and evaluator agents plus the user and maintainer role reviewers on current changes. Use when reviewing a diff, PR, or staged work before merge. Do NOT use to plan or implement; use map-plan or map-efficient.
map-debug
Structured MAP debugging via task-decomposer, actor, and monitor agents. Use when reproducing a bug, isolating a regression, or diagnosing an error with specialized agents — including failing or flaky tests (pytest AssertionError), crashes and segmentation faults, memory-corruption or memory errors in native/C…
map-learn
Capture reusable lessons after a completed MAP workflow. Use when a MAP run has finished and you want rules written to .claude/rules/learned/ from a workflow summary or handoff. Do NOT use during active implementation.
map-efficient
State-machine MAP execution workflow for Codex. Use when implementing an approved MAP plan end to end, resuming from branch MAP taskplan or stepstate.json artifacts, or running non-trivial multi-subtask work. Use map-fast for tiny one-shot edits.