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 rsturla/eternal-images --skill writing-pull-requestsgit clone --depth 1 https://github.com/rsturla/eternal-imagesWrote 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/rsturla/eternal-images/writing-pull-requests)<a href="https://agentmods.dev/skills/rsturla/eternal-images/writing-pull-requests"><img src="https://agentmods.dev/badge/skills/rsturla/eternal-images/writing-pull-requests/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/rsturla/eternal-images/writing-pull-requests"><img src="https://agentmods.dev/badge/skills/rsturla/eternal-images/writing-pull-requests.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 | $0.00072 | $0.00558 |
| Opus 5 | $0.00036 | $0.00279 |
| Sonnet 5 | $0.00014 | $0.00112 |
| Haiku 4.5 | $0.00007 | $0.00056 |
Grade A, and why
writing-pull-requests 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 11d 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.
What it actually says
Writing pull requests
A good pull request body gives the reviewer a mental model of the change. It answers why, what, and how to test. It reduces review time and back-and-forth.
Write the body in ASD-STE100 Simplified Technical English. For the style rules,
use the asd-ste100 skill.
Workflow
Step 1 — Write the title
- Use the Conventional Commits form:
type(scope): summary. - Use the imperative mood. Example: "fix token refresh on 401", not "fixed".
- Name the component and the effect. Keep it to 50 characters or fewer.
Step 2 — Write the body
Use these sections. Keep each one short. See references/template.md for a copy-ready template and references/examples.md for good and bad examples.
- Why — the problem or the goal. State the motivation, not only a ticket link.
- What — the main changes, as a bulleted list.
- How to test — the exact steps, commands, or checks the reviewer runs.
- Risks and follow-ups — breaking changes, migrations, and later work.
- Links — related issues or documents. Example: "Closes #123".
Step 3 — Guide the reviewer
- Point to the files or the parts that need the most attention.
- Separate mechanical changes from logic changes. Say which parts are a rename, a format, or a generated change, so the reviewer can skim them.
- Add a screenshot or a short video for a user-interface change.
Step 4 — Check the result
- Keep the body scannable. Use headings and bullets, not long paragraphs.
- Aim for 200 to 400 words. Add more only for a large change.
- Do not paste large diffs or execution traces. If the change is too big to explain, split the pull request.
- Read the body as if you were the reviewer. Fix each unclear part.
Keep the pull request small
- Keep each pull request on one topic.
- Aim for a small diff. Review quality drops after about 400 changed lines.
- Put the tests in the same pull request as the code they cover.
What ships with it
2 files 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.
- 11d ago First seen · 55 lines · 72 tokens per session scan A e717816568c7
writing-pull-requests is a skill published in the GitHub repository rsturla/eternal-images (11 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 558 once invoked, about $0.0004 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 2026-08-30.
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.
repo-sync
Manage repo-sync on macOS for shared documents and team context. Use when asked what repo-sync does, to automatically sync a repo, add a repo to repo-sync, stop syncing or un-sync a repo, check sync health, configure repo-sync, uninstall it, or install and maintain its bundled agent skill. Ordinary one-time Git pulls…
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
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…
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.