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 petekp/claude-code-setup --skill pr-descriptiongit clone --depth 1 https://github.com/petekp/claude-code-setupWrote 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/petekp/claude-code-setup/pr-description)<a href="https://agentmods.dev/skills/petekp/claude-code-setup/pr-description"><img src="https://agentmods.dev/badge/skills/petekp/claude-code-setup/pr-description/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/petekp/claude-code-setup/pr-description"><img src="https://agentmods.dev/badge/skills/petekp/claude-code-setup/pr-description.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00040 | $0.00871 |
| Opus 5.5 | $0.00016 | $0.00348 |
| Sonnet 5.5 | $0.00008 | $0.00174 |
| Haiku 4.5 | $0.00004 | $0.00087 |
Grade A, and why
pr-description 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 18d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR description
Write for a teammate who knows the product, hasn't followed the work, and is reading between other tasks. They should get the point from the bold text alone and stop once they have enough. A dense description goes unread even when it's accurate.
Read the actual diff and enough context to establish the problem, the resulting behavior, and the review risks. Don't invent motivation or claim verification you haven't done.
Shape
- Use the repository's PR template headings when it has them. Under each heading, write bullets, not paragraphs.
- Start each bullet with a bold lead-in that states the point as a full claim. Add one or two short sentences only when the reader needs the reason or the consequence.
- One point per bullet, most important first. A bold label can group related bullets, as in the example.
- Keep the body to one screen, about 300 words including tests. A small change needs one to three bullets. Over budget, cut reasons before points, then the least important points.
- When revising, rewrite the whole body within that budget. Replace a wrong line instead of appending a section for each new finding.
Content
Cover these in order, skipping any that don't apply:
- What was wrong or missing, with its impact as a number when one exists.
- What the change does.
- What behaves differently after merge, including effects outside the changed code.
- Decisions, risks, or known flaws the reviewer should check.
- What's not in this PR, only where a reader would assume otherwise.
- Tests: what was verified, and what wasn't.
Leave out file-by-file narration, how the problem was found, mechanism the diff already shows, boilerplate, and mannered prose.
Evidence
Link evidence from the bullet it supports, such as docs, a dashboard query, or source lines, instead of collecting it in its own section. Reasoning about a specific line belongs in an inline author note from pr-self-review, not the body. Use evidence selection for screenshots, recordings, and other proof. Reuse verification already done for the current change, and put a material gap beside the claim it limits.
What ships with it
3 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.
- 18d ago Changed · +47 lines · +11 tokens per session c4d2b3f0425a
- 1mo ago Changed · -97 lines · -91 tokens per session a37153d079ff
- 1mo ago First seen · 118 lines · 120 tokens per session scan A 877efaf17d6c
pr-description is a skill published in the GitHub repository petekp/claude-code-setup (48 stars, last pushed 14d ago), licensed MIT. It adds 40 tokens to every session and 871 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
github
GitHub via gh CLI: PRs, issues, reviews, repos, auth.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
resolve-drive-pr
Drive an open PR through Polly/OCR, validation, and maintainer handoff.
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.
feature-publish
Commit the feature, write the PR body, publish in the selected mode, and drive the PR.
otto-review-remediation
Handle trusted reviewers' change requests on Otto PRs.