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 dryvist/claude-code-plugins --skill pr-sweepgit clone --depth 1 https://github.com/dryvist/claude-code-pluginsWrote 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/dryvist/claude-code-plugins/pr-sweep)<a href="https://agentmods.dev/skills/dryvist/claude-code-plugins/pr-sweep"><img src="https://agentmods.dev/badge/skills/dryvist/claude-code-plugins/pr-sweep/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/dryvist/claude-code-plugins/pr-sweep"><img src="https://agentmods.dev/badge/skills/dryvist/claude-code-plugins/pr-sweep.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 | $0.00044 | $0.02655 |
| Opus 5.5 | $0.00018 | $0.01062 |
| Sonnet 5.5 | $0.00009 | $0.00531 |
| Haiku 4.5 | $0.00004 | $0.00265 |
Grade A, and why
pr-sweep 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 today.
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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Sweep
Drive open PRs toward zero through repeated rounds: merge what is safe, repair
what is cheaply repairable, and give every other stale PR an owner, next action,
and wake condition. This is triage-and-clear on open PRs;
/prune-branches --sweep acts on repo/worktree state and is a different job.
This skill decides which PRs move and in what order. It never
reimplements merging: each merge is delegated to /merge-pr, each repair to
/finalize-pr.
Completion contract
- Complete only when a fresh query at the end of a round returns zero open
in-scope PRs whose
createdAtis older than 24 hours. - Any nonzero stale count is a round boundary, not completion. PRs younger than 24 hours may be triaged opportunistically and never block completion.
- Report the stale count at the start and end of every round.
- A run blocked on a human stays running: send the batched ask, schedule the next round under the cadence rules, and continue the same workers.
- Finish Phase 5 validation before the end-of-round query. A merge is not done until its required post-merge validation passes.
Invariants
These five hold in every mode. They are the difference between a sweep and a stampede.
- Triage is read-only and confers no merge authority. Classifying a PR never merges it.
- A merge happens only against an execution order that pins the head commit. If the head moved since triage, the order is void — re-triage. This is what makes an approval round impossible to race.
- Serialize within a repo; parallelize across repos. Merge ordering, broken-base diagnosis, and repo-wide gates are all repo-scoped.
- Cap concurrent merges globally (default 2–3). Every merge triggers CI, and CI capacity is finite and shared.
- Every stale PR has exactly one owner, one next action, and one wake condition at every round boundary.
Never pass --admin. Never merge a draft. Never bypass a failing check —
repair it or route it to ESCALATE or HANDOFF.
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.
- today Changed 7dd878d75311
- 6d ago Changed · +46 lines · -13 tokens per session e5e9933d4a03
- 11d ago Changed · +1 lines 33c3f23c3d21
- 13d ago Changed · +4 lines e864eec571c1
- 15d ago Changed · +3 lines bfe1cf8a6a92
- 1mo ago Changed · +1 lines · -9 tokens per session 5126564c6f5b
- 1mo ago First seen · 143 lines · 66 tokens per session scan A 4f5355d4042a
pr-sweep is a skill published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 2,655 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 2026-08-31.
Other skills, from other repositories
review-pr
Multi-agent PR review with four modes (review, re-review, self-review, address-feedback) - spawns parallel subagents, saves diff to /tmp for context efficiency, supports file exclusion patterns.
prkit
Draft and open a GitHub pull request from your branch, with title, summary, and test plan written from the actual commits and diff, then created with the gh CLI, embedding verifykit proof artifacts inline when a bundle is present. Use when the user asks to open a PR, says "create a pull request", "raise a PR", "submit…
mergekit
Take an open GitHub PR and set it up for review on your machine (worktree, project running, review pack), then merge it once you say so, or service review feedback on a PR you authored. Use when you say "pull PR #34 down so I can test it", "merge PR #34", "address the review comments on my PR", or "my PR is red, fix…
code-review-loop
Use when opening a PR for review or when receiving review feedback. Activate for keywords like "code review", "PR review", "request review", "review feedback", "address comments", "reviewer said". Covers both ends of the loop: preparing a reviewable PR and acting on feedback rigorously. Always engage with every…
contribute
Complete contribution workflow using git-town. Create branch → commit → PR → ship. Preflight at every step.
commit-review
Review git commits for quality, clarity, and best practices before pushing. Checks commit message format, diff size, test coverage signals, and common mistakes. Use when reviewing commits, before pushing, when asked to "check my commits", "review changes", or "is this ready to push".