Borrowing it
Nothing to install: this file belongs to starSumi/sumi-docs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/starSumi/sumi-docs/main/.agents/skills/sumi-docs-pr/SKILL.mdgit clone --depth 1 https://github.com/starSumi/sumi-docsWrote 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/starsumi/sumi-docs/sumi-docs-pr)<a href="https://agentmods.dev/skills/starsumi/sumi-docs/sumi-docs-pr"><img src="https://agentmods.dev/badge/skills/starsumi/sumi-docs/sumi-docs-pr/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/starsumi/sumi-docs/sumi-docs-pr"><img src="https://agentmods.dev/badge/skills/starsumi/sumi-docs/sumi-docs-pr.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 | $0.00057 | $0.00586 |
| Opus 5 | $0.00028 | $0.00293 |
| Sonnet 5 | $0.00011 | $0.00117 |
| Haiku 4.5 | $0.00006 | $0.00059 |
Grade A, and why
sumi-docs-pr 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 12d 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.
This is a copy
98% identical to sumi-docs-pr — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prepare a Sumi Docs Pull Request
Read the root and nearest nested AGENTS.md, CONTRIBUTING.md, and the current
pull request template. Inspect live Git status, the diff, and the base branch;
preserve unrelated work and never infer a clean tree from an earlier report.
Classify the record before implementation
- Use a direct pull request for a narrow correction or internal change that preserves public behavior.
- Open a proposal issue before changing a public contract, architecture, security boundary, production dependency, locale or route model, deployment, or host integration.
- Update the product requirements document for durable product scope.
- Record an accepted, durable tradeoff as an ADR in the owning decision directory. Do not use an ADR as a work log.
- Put executable specifications in schemas, TypeScript types, tool schemas, and conformance tests. Do not maintain a prose duplicate of a machine contract.
- Add or update a reproducible benchmark when a performance claim or threshold changes; generated benchmark evidence belongs to CI artifacts.
- Route vulnerabilities through
SECURITY.mdand a private GitHub advisory. Never open a public CVE placeholder or public vulnerability issue.
Verify the net change
Map changed paths to their owning workspace. Run the smallest relevant red test first, then the owning package checks. Before declaring the branch ready, run from the repository root:
pnpm run verify
pnpm run verify:integration
For content changes, require both locales, the reviewed content catalog, fresh
translation-pair records after human semantic review, and a Web-to-MCP URL
round trip. For a public contract change, update active documentation,
examples, tests, and the changelog together. After the initial 0.1.0 npm
bootstrap, add a changeset for every public package whose published behavior
changes. Do not use changeset publish; package promotion remains bound to the
accepted candidate tarballs. Report every failed or skipped gate.
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.
- 12d ago First seen · 59 lines · 57 tokens per session scan A 94f74a5ee0fc
sumi-docs-pr is a skill published in the GitHub repository starSumi/sumi-docs (1 stars, last pushed 3d ago), licensed MIT. It adds 57 tokens to every session and 586 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to sumi-docs-pr, differing in 6 lines, and is treated as a copy.
Other skills, from other repositories
writing-emdash-docs
Write, revise, and review EmDash documentation for technical accuracy, useful structure, house style, and natural prose. Use when working on user documentation, guides, API reference pages, migration or upgrade guides, READMEs, contributor documentation, technical specifications, or release notes in the EmDash…
triage-contributor-pr
Triage open pull requests from external contributors to prisma/prisma and produce a per-PR verdict with evidence. Use when a maintainer asks to triage, evaluate, assess, or review the queue of incoming contributor PRs, to decide whether a fork PR is safe to run CI on, to check whether a PR is in scope for its version…
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
review-triage-phase
Produces canonical review actions from fetched review state and renders action markdown. Use when the user wants only triage/action-planning for the review-framework workflow.
update-pr
Update the pull request for the current session. Use when the user wants to push new changes to an existing PR.
review
Review one pull request for real bugs, regressions, and convention violations. Enumerate candidate issues across the whole diff, verify each against the code, then return structured line-anchored findings and a verdict. Read-only on GitHub; the orchestrator posts the review.