Borrowing it
Nothing to install: this file belongs to beava-dev/beava. 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/beava-dev/beava/main/.claude/skills/beava-pr-review/SKILL.mdgit clone --depth 1 https://github.com/beava-dev/beavaWrote 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/beava-dev/beava/beava-pr-review)<a href="https://agentmods.dev/skills/beava-dev/beava/beava-pr-review"><img src="https://agentmods.dev/badge/skills/beava-dev/beava/beava-pr-review/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/beava-dev/beava/beava-pr-review"><img src="https://agentmods.dev/badge/skills/beava-dev/beava/beava-pr-review.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 | $0.00119 | $0.02275 |
| Opus 5.5 | $0.00048 | $0.00910 |
| Sonnet 5.5 | $0.00024 | $0.00455 |
| Haiku 4.5 | $0.00012 | $0.00228 |
Grade A, and why
beava-pr-review 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 2mo 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
beava-pr-review
Diff-aware code reviewer tuned for the beava codebase. Checks three
layers in order; surface findings sorted by severity (BLOCK > WARN > NIT)
with file:line anchors.
When to invoke
- User says "review this PR" / "PR review" / "audit this diff" / "check
for slop" against a feature branch or a PR URL on
beava-dev/beava. - After a substantial code change but before requesting
ok-to-testapproval — the local check.sh covers fmt/lint/test, this skill covers the human-judgment layer.
How to run
- Bound the diff.
git diff main...HEAD --stat(orgh pr diff <N> -R beava-dev/beavafor a remote PR). Read only the changed lines + ~30 lines of context per hunk. Do NOT review unchanged code. - Run automated gates first. Before LLM review, surface anything
the existing tools catch:
bash .github/scripts/check.sh --fast— fmt, clippy, ruff, mypy (advisory). If any FAIL, the PR is incomplete; tell the user to fix before requesting human review.
- Apply the three review layers below, in order. Skip a layer only if the diff doesn't touch its scope (e.g. skip "AI slop" for a pure .gitignore change).
- Emit the report in the format under "Output format" at the end.
Layer 1 — Real bugs
The most common categories worth checking against the diff:
- Off-by-one — index math, slice bounds, half-open vs closed
ranges. Especially in
crates/beava-core/src/agg_op.rs,crates/beava-runtime-core/src/router.rs, anywhere computingwindow_secs/bucket_secs. - Null / Option /
?propagation —.unwrap()in non-test code is WARN unless the PR shows the panic is provably unreachable.expect()with a useful message is fine. - Resource leaks — file descriptors, mio tokens, dropped futures (we hand-rolled the runtime; mio leaks don't auto-close like tokio).
- Concurrency — single-threaded apply is locked architecture
(
project_no_sharded_apply); any new thread / parallel iterator insidedispatch_*_syncis BLOCK. - Schema / wire compatibility — changes to
crates/beava-runtime-core/src/router.rsroutes,agg_op.rsAggKindvariants, orpython/beava/_app.py::_descriptor_to_nodewire shape break clients. WARN unless the PR body calls it out and ships a migration note. - TDD discipline (Phase 3+ only) — every plan task must produce a
test(...)commit before itsfeat(...)commit. Commits that showfeat:without a precedingtest:for the same scope are WARN (per CLAUDE.md §Conventions → TDD Discipline).
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.
- 2mo ago First seen · 201 lines · 119 tokens per session scan A 625502a4710e
beava-pr-review is a skill published in the GitHub repository beava-dev/beava (139 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 119 tokens to every session and 2,275 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
review-fix-signoff-loop
Use when writing Agent Relay or Ricky workflows that must loop review, fix, and validation with fresh agent context until independent signoff agents, typically Claude and Codex, both agree the work is comprehensively complete. Covers fresh-context iterations, repairable gates, dual reviewer verdict contracts…
review-animations
Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…