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 agentmods add skills/dryvist/claude-code-plugins/pr-sweepnpx skills add dryvist/claude-code-plugins --skill pr-sweepgit clone --depth 1 https://github.com/dryvist/claude-code-pluginsWhat 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 | $0.00066 | $0.01670 |
| Opus 5 | $0.00033 | $0.00835 |
| Sonnet 5 | $0.00013 | $0.00334 |
| Haiku 4.5 | $0.00007 | $0.00167 |
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 2d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Sweep
Drive a pile of open PRs toward zero: merge what is safe, repair what is
cheaply repairable, and surface the rest with a concrete reason each. 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.
Invariants
These four 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.
Never pass --admin. Never merge a draft. Never bypass a failing check —
repair it or hold the PR.
State warning: PR status, CI, and mergeability change constantly, and
mergeable/mergeStateStatusare computed lazily — a first query often returnsUNKNOWN. Re-query before classifying, and never act on a list gathered earlier in the session.
Merge method is not this skill's business
/merge-pr resolves the merge method from the repo's capabilities and the
branching model — see git-flow-next (git-workflows) for which method each
target branch requires. This skill passes no method flag and states no
default. A promotion PR into a production branch is never swept: hold it and
point at /promote-release.
Scope
/pr-sweep— open PRs in the current repo./pr-sweep --org <owner>— open PRs across the owner's repos, all authors. Bot and teammate PRs are usually the bulk of a real pile.--author <login>— optional filter. Do not default to "mine": some token types (app installation tokens) carry no user identity, so a self-filter silently returns nothing.
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.
- 2d 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 2d ago), licensed Apache-2.0. It adds 66 tokens to every session and 1,670 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
rspec
This skill should be used when the user asks to "write specs", "create spec", "add RSpec tests", "fix failing spec", or mentions RSpec, describe blocks, it blocks, expect syntax, test doubles, or matchers. Should also be used when editing spec.rb files, working in spec/ directory, planning implementation phases that…
activerecord
This skill should be used when the user asks to "write a migration", "add a column", "add column to table", "create an index", "add a foreign key", "set up associations", "fix N+1 queries", "optimize queries", "add validations", "create callbacks", "use eager loading", or mentions ActiveRecord, belongsto, hasmany…
dragonruby
This skill should be used when the user asks to "create a game", "make a game", "game development", "dragonruby", "drgtk", "game loop", "tick method", "sprite rendering", "game state", or mentions args.outputs, args.state, args.inputs, coordinate system, collision detection, animation frames, or scene management.…
draper-decorators
This skill should be used when the user asks to "create a decorator", "write a decorator", "move logic into decorator", "clean logic out of the view", "isn't it decorator logic", "test a decorator", or mentions Draper, keeping views clean, or representation logic in decorators. Should also be used when editing…
mcp-server
This skill should be used when the user asks to "create an MCP server", "build MCP tools", "define MCP prompts", "register MCP resources", "implement Model Context Protocol", or mentions the mcp gem, MCP::Server, MCP::Tool, JSON-RPC transport, stdio transport, or streamable HTTP transport. Should also be used when…
ratatui-ruby
This skill should be used when the user asks to "create a TUI", "terminal interface", "terminal UI", "ratatui", "ratatui-ruby", "inline viewport", "full-screen terminal app", "terminal widgets", "tui.draw", "tui.pollevent", or mentions RatatuiRuby.run, managed loop, terminal rendering, Tea MVU, or building CLI…