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 Generous-Corp/pulp --skill pr-review-sweepgit clone --depth 1 https://github.com/Generous-Corp/pulpWrote 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/generous-corp/pulp/pr-review-sweep)<a href="https://agentmods.dev/skills/generous-corp/pulp/pr-review-sweep"><img src="https://agentmods.dev/badge/skills/generous-corp/pulp/pr-review-sweep.svg" alt="Measured on agentmods" 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 | $0.00073 | $0.01259 |
| Opus 5 | $0.00036 | $0.00629 |
| Sonnet 5 | $0.00015 | $0.00252 |
| Haiku 4.5 | $0.00007 | $0.00126 |
Grade A, and why
pr-review-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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review Sweep
Automated reviewers (cubic-dev-ai, chatgpt-codex-connector / Codex) and humans leave findings on PRs asynchronously — often seconds to minutes after the PR opens, and sometimes only after it merges. A PR that built green is not a reviewed PR. This skill makes the sweep a deliberate step so real P1s (races, state-clobbers, unguarded destructive paths) don't slip through on the exact kind of change where they hurt most.
The rule that motivated this skill: a self-identified P1 on a destructive path was shipped as a "follow-up" and the reviewers confirmed it (plus three more) after merge. Cheap to catch at sweep time; a roundtrip to catch later.
When to sweep (and when not to)
Always sweep — material PRs:
- Touches shipped source / logic:
core/**,examples/**,ship/**,tools/cli/**,src/**(Shipyard), CMake/build wiring. - Concurrency, lock ordering, state machines, serialization, RT-audio, or any destructive / mutating path (delete, abandon, overwrite, force). Treat these as high-risk regardless of diff size.
- Large diffs, or a stack of commits — more surface, more asynchronous review.
Skip is fine — non-material PRs:
- Docs-only / comment-only / pure rename / formatting.
- Trivial config or version-bump-only changes.
If unsure, sweep. It costs one API read and a few minutes of triage.
The sweep
Use ghapp for GitHub API reads (its own rate-limit bucket; plain gh
burns the shared personal token). Use gh for creating/merging PRs.
Pull all three comment surfaces — findings land in different places:
REPO=danielraffel/<repo>; N=<pr>
# Inline review comments (code-anchored — where the bots put P1/P2 findings)
ghapp api repos/$REPO/pulls/$N/comments \
--jq '.[] | "--- \(.path):\(.line // .original_line) by \(.user.login)\n\(.body)\n"'
# PR-level reviews (approve/request-changes summaries)
ghapp api repos/$REPO/pulls/$N/reviews \
--jq '.[] | "\(.user.login) [\(.state)]: \(.body)"'
# Issue comments (human notes, "potential issues flagged here")
ghapp api repos/$REPO/issues/$N/comments \
--jq '.[] | "--- by \(.user.login)\n\(.body)\n"'
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 · 107 lines · 73 tokens per session scan A d4c7548215b0
pr-review-sweep is a skill published in the GitHub repository Generous-Corp/pulp (16 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 1,259 once invoked, about $0.0004 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 2026-09-04.
Other skills, from other repositories
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.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…
write-pr
Reference standards for writing pull request titles and descriptions in the tldraw repository, plus the pre-flight comment sweep over the diff. Use as supporting guidance when another skill or workflow needs PR content standards, not as the user-facing create/update PR workflow.