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/lsampaioweb/ai-instructions/prepare-commit-messagesnpx skills add lsampaioweb/ai-instructions --skill prepare-commit-messagesgit clone --depth 1 https://github.com/lsampaioweb/ai-instructionsWrote 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/lsampaioweb/ai-instructions/prepare-commit-messages)<a href="https://agentmods.dev/skills/lsampaioweb/ai-instructions/prepare-commit-messages"><img src="https://agentmods.dev/badge/skills/lsampaioweb/ai-instructions/prepare-commit-messages.svg" alt="Measured on agentmods" 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 | $0.00066 | $0.00623 |
| Opus 5 | $0.00033 | $0.00311 |
| Sonnet 5 | $0.00013 | $0.00125 |
| Haiku 4.5 | $0.00007 | $0.00062 |
Grade A, and why
prepare-commit-messages 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 5d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Logical Git Commit Engine
- Obey
AGENTS.md(project root). - If the user provides a path or feature-scope filter, limit analysis to that scope.
1. Scope & Analysis
- Inspect uncommitted changes (
git status,git diff). - Cluster files into atomic, reversible commits.
- Sort Order: Foundational changes (config, schemas, deps) must be committed before feature layers.
- Grouping Boundary: Group files strictly by feature domain (e.g.,
auth,payment). - Documentation Gate: If Markdown documentation exists for changed code but contains no corresponding updates, flag the affected docs and recommend running
/review-and-sync-docsbefore proceeding.
2. Resolution Rules
- Commit Format: Use Conventional Commits only:
type(scope): description. - Scope Rule: Use a feature domain or infrastructure area.
- Description Rule: Imperative, present tense, max 50 characters, no trailing period.
- Body Rule: Document the why and the impact only.
- Footer Rule: Append
Closes #123or tracking IDs if detected in branch or context.
3. Safety Guards
- Execution Boundary: Read-only analysis. Do not execute any Git commands until the commit plan is confirmed.
- Ask for Confirmation: Output:
Proceed with executing this automated commit sequence? [yes/no] - Post-approval: Run
git addandgit commitsequentially for each cluster. - Verify success after each commit before proceeding to the next cluster.
- Never group files by technical layer; group strictly by feature domain.
- Never use technical-layer identifiers as the commit scope.
- Never list modified files or duplicate diff data in the commit body.
- If files in a cluster span more than one feature domain, flag the cluster and stop.
- Never use commit types not defined by the Conventional Commits specification.
4. Review Plan Layout
Output this plan layout:
Proposed Commit Sequence Plan
Commit [N]: type(scope): description
- Target Files to Stage:
path/to/file1path/to/file2
- Execution Message Blueprint:
type(scope): description Why this change is needed and its impact.
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.
- 5d ago First seen · 70 lines · 66 tokens per session scan A 38052458c9ab
prepare-commit-messages is a skill published in the GitHub repository lsampaioweb/ai-instructions (1 stars, last pushed 13d ago), licensed MIT. It adds 66 tokens to every session and 623 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.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
commit-push-pr
Commit selected local changes, push the branch, and create or update a GitHub pull request with BitFun attribution. Use when the user asks to 提交 PR、提代码、commit and push、开 PR、create a pull request, or wants a Claude Code-like one-command PR publishing flow from BitFun.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
commit
Commit current changes with a clear, descriptive message.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…