Borrowing it
Nothing to install: this file belongs to swt-labs/vibe-better-with-claude-code-vbw. 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/swt-labs/vibe-better-with-claude-code-vbw/main/.agents/skills/vbw-review-contributor-pr/SKILL.mdgit clone --depth 1 https://github.com/swt-labs/vibe-better-with-claude-code-vbwWrote 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/swt-labs/vibe-better-with-claude-code-vbw/vbw-review-contributor-pr)<a href="https://agentmods.dev/skills/swt-labs/vibe-better-with-claude-code-vbw/vbw-review-contributor-pr"><img src="https://agentmods.dev/badge/skills/swt-labs/vibe-better-with-claude-code-vbw/vbw-review-contributor-pr/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/swt-labs/vibe-better-with-claude-code-vbw/vbw-review-contributor-pr"><img src="https://agentmods.dev/badge/skills/swt-labs/vibe-better-with-claude-code-vbw/vbw-review-contributor-pr.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 | $0.00061 | $0.00910 |
| Opus 5 | $0.00030 | $0.00455 |
| Sonnet 5 | $0.00012 | $0.00182 |
| Haiku 4.5 | $0.00006 | $0.00091 |
Grade A, and why
vbw-review-contributor-pr 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 11d 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VBW Review Contributor PR
Use this skill when the user explicitly asks to review an external or contributor PR for this repo.
Workflow
- Identify the PR and linked issue. If multiple PRs reference the issue, ask which PR to review.
- Read the issue body before reading the contributor diff. The issue is the verification contract.
- Spawn
vbw-fix-plannerwith the issue body only. Do not include PR comments, the PR body, the contributor branch, diff, files changed, or PR narrative. The planner output is the blind baseline. - Check out or enter the contributor branch worktree. Prefer
scripts/adopt-contributor-pr.shor existing worktree helpers over inline worktree logic. - Run
bash testing/run-all.shfrom the worktree and keep the result as review evidence. - Read the PR diff and the full contents of changed files from the worktree.
- Compare the implementation against blind-baseline-review.md.
- Spawn
vbw-qa-investigatorfor a latest GPT x-high full-contract review of the contributor branch. - Read qa-evidence-comments.md, then fetch the PR body, PR issue comments, and commit history as QA evidence only after the blind baseline exists and local tests, diff review, and QA review are underway or complete. PR comments and PR body are evidence, not contract.
- Merge duplicate findings from the baseline comparison, QA report, tests, diff review, and QA evidence into a
review_finding_ledgerbefore posting anything to GitHub. Each finding row must includeid,severity,source,path,line,side,anchor_status,inline_body, andsummary_body.sourcemay includeblind-baseline,qa,tests,diff-review,qa-evidence, or a combined source list. - Read github-review-submission.md, then submit exactly one GitHub PR review with
APPROVE,REQUEST_CHANGES, orCOMMENT. - Anchor every unique blocking finding with a valid diff line as an inline review comment, capped at 12 inline comments after deduping by root cause and severity. Put repeated, unanchorable, or over-cap findings in the review body under
Unanchored blockerswith the reason they were not inline. - Submit the review on the PR head SHA using the GitHub app
_add_review_to_prwhen available, passingaction,review,commit_id, andfile_comments. If that tool is unavailable, use thegh api repos/:owner/:repo/pulls/:pull_number/reviewsfallback with equivalentevent,body,commit_id, andcomments[]JSON. - Do not use
gh pr reviewwhen inline comments are expected; it cannot carry the required inline comment payload. It is acceptable only when there are zero anchorable findings. - Verify the submitted review before reporting success: fetch the submitted reviews and inline review threads, confirm the latest review by the actor has the expected state, head commit, body marker or finding IDs, and expected inline comments.
- When a remote Codex review request is required, post
gh pr comment <pr-number> --repo swt-labs/vibe-better-with-claude-code-vbw --body '@codex review'. This does not replace the local blind-baseline review verdict.
What ships with it
4 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.
- 11d ago First seen · 34 lines · 61 tokens per session scan A 27e86fa9613b
vbw-review-contributor-pr is a skill published in the GitHub repository swt-labs/vibe-better-with-claude-code-vbw (79 stars, last pushed 2mo ago), licensed MIT. It adds 61 tokens to every session and 910 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 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
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"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…