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 alonbaron/claude-skills --skill review-swarmgit clone --depth 1 https://github.com/alonbaron/claude-skillsWrote 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/alonbaron/claude-skills/review-swarm)<a href="https://agentmods.dev/skills/alonbaron/claude-skills/review-swarm"><img src="https://agentmods.dev/badge/skills/alonbaron/claude-skills/review-swarm/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/alonbaron/claude-skills/review-swarm"><img src="https://agentmods.dev/badge/skills/alonbaron/claude-skills/review-swarm.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 | $0.00149 | $0.01277 |
| Opus 5 | $0.00075 | $0.00639 |
| Sonnet 5 | $0.00030 | $0.00255 |
| Haiku 4.5 | $0.00015 | $0.00128 |
Grade A, and why
review-swarm 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 12d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Swarm
Review the working changes with a panel of specialists in parallel, then keep only the findings that survive scrutiny. Free and local (Claude subagents).
Proactive use
If the user asks to review, check, or assess changes — or you've just finished a non-trivial implementation and a PR is next — invoke this without being asked: announce in one line ("Running review-swarm on ") and proceed. Never ask permission to run the skill.
Steps
- Scope the diff. Default: working tree vs the default branch.
staged→git diff --staged;branch→ vs merge-base with main; a path → limit to it. Read the changed hunks and enough surrounding code to judge them. Size guard: over ~40 changed files or ~2000 changed lines, don't swarm the whole thing — split by area and say which slice you reviewed, or ask which slice matters. A swarm that overruns its context reports confidently on code it never read. - Fan out specialists — in parallel. Spawn the reviewers below with the
Agent tool, all in one message so they run concurrently. Give each the
diff plus the files it needs and its single lens. Each returns findings as:
severity · file:line · what · why · suggested fix.- Correctness — logic errors, edge cases, null/empty, off-by-one, concurrency/races.
- Security & trust boundaries — authz/authn (JWT), input validation at boundaries, injection, IDOR, leaked secrets.
- Data & performance — N+1 (JPA/Hibernate, SQLAlchemy), missing indexes, unbounded queries, transaction scope, lazy-load traps.
- Architecture & altitude — does it fit the domain model? are invariants enforced at the core? wrong layer, leaky abstraction.
- Simplicity (ponytail lens) — over-engineering, premature abstraction, dead code, a stdlib/native one-liner that replaces the change.
- Tests & failure paths — non-trivial logic with no test, untested failure paths, error handling that could lose data.
- Adversarially verify. For each non-trivial finding, spawn a verifier that tries to refute it: is it real, reproducible, not already handled elsewhere? Drop findings that don't survive. Default to dropping when uncertain.
- Synthesize. Dedup overlaps, then rank: Blockers → Should-fix → Nits, each with file:line and a one-line fix. Close with a short "what's solid".
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.
- 12d ago First seen · 103 lines · 149 tokens per session scan A 4ac612731e0c
review-swarm is a skill published in the GitHub repository alonbaron/claude-skills (13 stars, last pushed 1mo ago), licensed MIT. It adds 149 tokens to every session and 1,277 once invoked, about $0.0007 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
gemini
Cross-model second opinion from Google Gemini — a different AI reviewing the same changes, with deep Google ecosystem knowledge. Three modes: review (pass/fail gate for Google Ads campaigns, SEO metadata, or code), challenge (adversarial stress-test that tries to break your changes), and consult (open Q&A with Gemini…
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
critical-code-reviewer
Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.
boundaries
Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.
challenge
Challenge mode reviews - rigorous questioning before approving changes. Use when you want thorough scrutiny of Ecto changes, LiveView events, OTP designs, or PR readiness.
triage
Triage review findings interactively — approve, skip, or prioritize each issue. Use after /phx:review to filter findings before fixing.