← ClaudeAtlas

review-swarmlisted

Local, free, multi-specialist review of a diff: parallel Claude subagents (correctness, security/trust boundaries, data/perf, architecture-altitude, ponytail-simplicity, tests/failure paths), adversarial verification, dedup, ranked file:line report. Use proactively when asked to review, check, or assess a diff, branch, or PR — and after any non-trivial implementation, before the PR. Also on "review-swarm", "swarm review", "deep review". Not for trivial diffs, not when asked to fix rather than review, not when security alone is the whole ask (built-in "security-review"), and not when "/code-review" is named explicitly.
alonbaron/claude-skills · ★ 13 · Code & Development · score 78
Install: claude install-skill alonbaron/claude-skills
# 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 <scope>") and proceed. Never ask permission to run the skill. ## Steps 1. **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. 2. **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**