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 Jartan-LLC/grimoire --skill commit-pr-writinggit clone --depth 1 https://github.com/Jartan-LLC/grimoireWrote 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/jartan-llc/grimoire/commit-pr-writing)<a href="https://agentmods.dev/skills/jartan-llc/grimoire/commit-pr-writing"><img src="https://agentmods.dev/badge/skills/jartan-llc/grimoire/commit-pr-writing/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/jartan-llc/grimoire/commit-pr-writing"><img src="https://agentmods.dev/badge/skills/jartan-llc/grimoire/commit-pr-writing.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 | $0.00034 | $0.00856 |
| Opus 5.5 | $0.00014 | $0.00342 |
| Sonnet 5.5 | $0.00007 | $0.00171 |
| Haiku 4.5 | $0.00003 | $0.00086 |
Grade A, and why
commit-pr-writing 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 yesterday.
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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit Messages and PR Descriptions
The project's own rules win where they speak. No style or brevity pass over a commit message or a PR description: keep every verification line, issue id and reason.
Before you state how the code behaves when it runs (its output, what a test catches, why a result comes out as it does), run it or watch it. If you only reasoned it out, check it now or leave it out. This does not apply to what the change does or why you chose it.
The Commit Message
Write every commit message to land on the default branch, whatever the merge setting. Under GitHub's default squash merge, every commit message on the branch goes into the squash commit's message (merges from the base branch aside).
- Say why the change was made and why this way; where alternatives were weighed, name the one a later reader would propose and why it lost.
- Describe the change as merged; narrate no review rounds, requests, attempts, CI re-runs or branch history, and let the subject name the change (never "address review findings").
- Do not restate what the reader already has open: no file lists, diff retelling or test totals CI shows.
- State each gap or deferral (with its issue), deliberate omission (with its reason) and hazard a later edit must avoid in the commit message that makes the change. A one-time action only contributors owe (rebuild the dev container) goes in its first paragraph.
- A commit that reverses or replaces an earlier commit's statement or design names that statement or design by the earlier commit's subject, never "the previous commit", in its first paragraph, says why it was not enough, and gives the corrected action. The branch's earlier messages:
git log --reverse --format=%B <base>..HEAD. - A commit that only corrects what this PR added (a typo, a lint, a comment it now drops) takes a subject stating the merged result and no body.
- Make every "every", "all" or "no longer" true of the change as merged, or name the exception.
- A statement that a file was generated holds for its source as merged: a later commit that edits that source regenerates the file or says it predates the edit.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 43 lines · 34 tokens per session scan A c15b5cb82c67
commit-pr-writing is a skill published in the GitHub repository Jartan-LLC/grimoire (2 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 856 once invoked, about $0.0001 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 2026-10-16.
Other skills, from other repositories
pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
phx-pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
extract-pr-review-rules
Extract a repository's inline PR review comments into a per-reviewer pr-review-rules doc for the project's review skills, resuming from the last run's checkpoint.
git-commit
Use when asked to commit, save, or persist changes to Git. Handles atomic commits, branch safety, Conventional Commits format, and project style matching. Do NOT use for pushing, creating PRs, or branch management beyond safety checks.
babysit-pr
Resolve reviewer comments on a pull request or pasted feedback using a six-step evidence-grounded protocol. Use when asked to resolve review feedback, address reviewer comments, process PR comments, triage review feedback, apply review suggestions, handle code review feedback, decide which review comments to accept or…
github-pr-best-practices
Best practices for creating GitHub pull requests including conventional commits, PR formatting, and multi-language support (en/ja). Use when creating PRs, writing PR descriptions, or formatting commit messages.