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 5.5 | $0.00029 | $0.00223 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 yesterday), licensed MIT. It adds 72 tokens to every session and 558 once invoked, about $0.0003 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 2026-08-30.
writing-pull-requests compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| writing-pull-requestsrsturla/eternal-images | Skill | 11 | yesterday | MIT | A | 72 | Claude Code, Codex |
| create-prprisma/orm | Skill | 48k | today | Apache-2.0 | A | 48 | Claude Code, Codex |
| git-commitThinkInAIXYZ/deepchat | Skill | 6.4k | yesterday | Apache-2.0 | A | 15 | Claude Code, Codex |
| repo-syncdavidondrej/skills | Skill | 4.3k | today | MIT | A | 25 | Claude Code, Codex |
| engineer-bot-opsmakecindy/cindy | Skill | 9.4k | today | Apache-2.0 | A | 57 | Claude Code, Codex |
| mcore-split-prNVIDIA/skills | Skill | 3.9k | today | Apache-2.0 | A | 25 | Claude Code |
| git-commit-writermergisi/awesome-openclaw-agents | Skill | 4.1k | 2d ago | MIT | A | 53 | Claude Code, Codex |