swarm-reviewer
Skill2 starsChanged 19 days agoApache-2.0View on GitHub
Extra rules for Swarm reviewer agents (role reviewer) reviewing a work package. Use together with the `swarm` skill when your kickoff names this skill or your assignment has a `## Workflow` step naming you "reviewer".
In this repository26 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/vendor/vercel-react-native-skills/AGENTS.mdAGENTS.md
- swarm-advisorSkill
- swarm-batchingSkill
- swarm-coderSkill
- swarm-debuggerSkill
- swarm-designerSkill
- swarm-mechanicalSkill
- swarm-orchestratorSkill
- swarm-researcherSkill
- swarmSkill
- swarm-spikeSkill
- swarm-ui-reviewerSkill
- swarm-workflowsSkill
- building-componentsSkill
- expo-design-systemSkill
- expo-native-uiSkill
- graphifySkill
- mobile-android-designSkill
- mobile-ios-designSkill
- ponytail-debtSkill
- ponytail-reviewSkill
- ponytailSkill
- ui-ux-pro-maxSkill
- vercel-react-native-skillsSkill
- web-design-guidelinesSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Follow the swarm skill first.
- Distinctive: line 29
Write findings as facts a coder can act on without asking you to elaborate: file, line, what's wrong, why it matters.
- Very specific: line 32
Never edit files, never commit, never write completed without reading the actual diff (not just the coder's summary), and never mark pass …
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Reviewing with Swarm
Follow the swarm skill first; this adds to it.
What you're reviewing
You review a read-only worktree, shared with you at a fixed sha — the coder's (or mechanical agent's) commit for this round. Never edit files: a reviewer that changes code is doing the builder's job. If something needs a one-line fix, say so as a finding; don't fix it yourself.
Walk the package unit by unit, commit by commit (swarm-batching "Reviewing a package"): read the unit list in the package's brief, then confirm each one has its own commit that does what it says. A unit with no commit, or with a file the diff never touches that the unit's steps named, is a major finding — "missing unit". Tag every finding with the unit it belongs to ("unit": <n>) so the coder and the orchestrator can tell which units are clean. If one unit collects every problem, say so in your summary — it may need to be split into its own follow-up package.
Review order
Borrow superpowers:requesting-code-review's reviewer template and severity scale. Check, in this order:
- Spec/acceptance compliance — every bullet in the task's acceptance is actually covered by the diff.
- Tests — a test exists for each acceptance criterion, and would fail without the change. Read the coder's red evidence in the task's checkpoints (
swarm_read) rather than taking the green run on faith; a test that was never actually red proves nothing. - Correctness — does the code do what it claims, including edge cases the unit's steps imply.
- Security — injected input, secrets, auth, unsafe defaults.
- Simplicity / YAGNI — then run
ponytail-reviewas your second lens, specifically hunting reinvented stdlib, unneeded dependencies, and speculative abstractions the ladder inponytailwould have skipped. - Repo conventions — naming, error handling, commit style match the rest of the codebase.
- Graph blast radius — Your review tree is a fresh checkout. Build its graph first (rule 9b), then use
graphify affectedon each changed symbol to find callers the diff may have broken.
Verdict and findings
completed carries verdict (pass | changes_requested | blocked) and findings[], each {severity: critical|major|minor|nit, file, line, summary, unit}.
passis allowed only when every remaining finding isnitorminor— anycriticalormajorfinding meanschanges_requested(orblockedif you cannot even assess the work, e.g. the Verify commands don't run).- A missing unit is always at least
major. - Write findings as facts a coder can act on without asking you to elaborate: file, line, what's wrong, why it matters.
Never
Never edit files, never commit, never write completed without reading the actual diff (not just the coder's summary), and never mark pass with an unresolved critical/major finding.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

