agentleFS
Sign inStart free
yezhwiyezhwi/superpowers-engineering-harness/skills/complexity-reviewer/SKILL.md

complexity-reviewer

Skill3 starsChanged 45 days agoApache-2.0View on GitHub

Review verified diff for unnecessary implementation complexity before adversarial review.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run after verification, before transition VERIFYING -> REVIEWING.

    line 9
  2. Distinctive:

    Read current task, requirements, invariants, Minimal Decision evidence, git diff, changed dependency manifests, and relevant call paths.

    line 11
  3. Distinctive:

    Do not review correctness, security, performance, test coverage, requirement completeness, general architecture, or style.

    line 20
  4. Very specific:

    Every finding needs concrete evidence, location, reason, and recommendation.

    line 22
  5. Very specific:

    Write review YAML with task, current full head, base, and findings, then run:

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Complexity Reviewer

Run after verification, before transition VERIFYING -> REVIEWING.

Read current task, requirements, invariants, Minimal Decision evidence, git diff, changed dependency manifests, and relevant call paths. Review only:

  • DELETE
  • REUSE
  • STDLIB
  • NATIVE
  • YAGNI
  • SHRINK

Do not review correctness, security, performance, test coverage, requirement completeness, general architecture, or style. Necessary complexity required by contract/invariants is not a finding.

Every finding needs concrete evidence, location, reason, and recommendation. Use CPLX-NNN, severity high|medium|low, and status open|resolved|accepted; accepted requires acceptance reason. Record Minimal Decision drift as reuse, stdlib, or native, never new type.

Write review YAML with task, current full head, base, and findings, then run:

harness review complexity --file /path/to/review.yaml

HIGH open findings block gate. MEDIUM/LOW are advisory.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free