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 atretyak1985/swarmery --skill pr-generatorgit clone --depth 1 https://github.com/atretyak1985/swarmeryWrote 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/atretyak1985/swarmery/pr-generator)<a href="https://agentmods.dev/skills/atretyak1985/swarmery/pr-generator"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/pr-generator/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/atretyak1985/swarmery/pr-generator"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/pr-generator.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 | $0.00048 | $0.00556 |
| Opus 5 | $0.00024 | $0.00278 |
| Sonnet 5 | $0.00010 | $0.00111 |
| Haiku 4.5 | $0.00005 | $0.00056 |
Grade A, and why
pr-generator 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 6d 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
Purpose
A PR description assembled from the real diff and commit history — not from memory of what you meant to do.
Method
- Gather evidence:
git log <base>..HEAD --oneline,git diff <base>...HEAD --stat, and read the diff for anything the summary will claim. - Title: conventional-commit style, ≤72 chars, states the change not the activity ("feat(orders): bulk line-item editing", not "worked on orders").
- Description sections: What (the change in 2-4 sentences), Why (the problem/ticket), How (notable decisions, anything a reviewer would ask about), Testing (what was actually run — never claim untested checks), Breaking changes / rollout (or "None").
- Review checklist: 3-7 items specific to THIS diff (the risky hunks, the contract edges, the migration), not generic boilerplate.
- Respect the project's PR template when the repo has one
(
.github/PULL_REQUEST_TEMPLATE.mdwins over this structure).
Never include Claude/AI attribution lines. Never invent test results.
How to use
What it does
Generates a PR title, a structured description grounded in the branch's real commits and diff, and a diff-specific review checklist — following the repo's own PR template when one exists.
When to use it
After a branch is ready to push: the work is done, checks ran, and the PR needs a description a reviewer can trust.
How to invoke
Load the skill and name the branch and base, e.g. "generate the PR for feature/bulk-edit against main" — or let an orchestrator load it at delivery time.
Worked example
For a 4-commit branch touching an API route and a migration, it produces: title feat(orders): bulk line-item editing, a What/Why/How description citing the expand-migrate design, Testing listing the actual npm test output, and a checklist item "verify migration backfill on a copy of staging data — new NOT NULL column".
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.
- 6d ago First seen · 52 lines · 48 tokens per session scan A c19512833b73
pr-generator is a skill published in the GitHub repository atretyak1985/swarmery (5 stars, last pushed today), licensed Apache-2.0. It adds 48 tokens to every session and 556 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
lean-review
CocoLean diff-scoped over-engineering audit — scans uncommitted git diff and applies five classification tags (delete/stdlib/native/yagni/shrink) to identify unnecessary surface area before commit.
prepare-pr
End-to-end drives working-tree changes to a review-ready pull request — commit, sync base, squash to one commit, open/update the PR — then KEEPS RUNNING IN-SESSION (poll CI + code-review bots in 5-min rounds, up to 10) fixing every legitimate Critical/High finding and build failure until the PR is review-ready (never…
validate-changes
Evaluate staged changes using LLM-as-a-Judge before committing.
gh-address-comments
This skill should be used when addressing GitHub pull request review comments systematically with mandatory resolution tracking. Use when user says "address PR comments", "fix review feedback", "handle PR review", "resolve PR threads", or needs to ensure all review comments are addressed before merging. Fetches…
git-workflow
Git workflow and conventional commits. Use when working with git, branches, commits, pull requests, code review, or version control strategy.
simplify
Use when the user says "simplify this diff" or asks for a compression pass over a change-set. Not for dead-code sweeps: use deslop.