agentleFS
openclosed-orgopenclosed-org/axum-harness/.agents/skills/harness-architecture-review/SKILL.md

harness-architecture-review

Skill48 starsChanged 6 months agoApache-2.0View on GitHub

Finds architecture deepening opportunities using seams, module depth, deletion tests, evidence hierarchy, and repository ownership boundaries. Use when reviewing architecture, reducing coupling, improving testability, or evaluating whether a module, trait, adapter, worker, service, or boundary is too shallow.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to surface architecture friction before proposing refactors.

    line 12
  2. Very specific:

    Read AGENTS.md, agent/codemap.yml, docs/architecture/north-star.md, and accepted ADRs in the area.

    line 18
  3. Distinctive:

    Check whether a seam has real variation, testing value, or topology-late value.

    line 22
  4. Distinctive:

    Check ownership boundaries before recommending changes.

    line 23
  5. Distinctive:

    Ask which candidate to explore before designing interfaces or changing code.

    line 38

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Harness Architecture Review

Use this skill to surface architecture friction before proposing refactors.

Workflow skills guide process. Ownership skills still decide writable boundaries.

Process

  1. Read AGENTS.md, agent/codemap.yml, docs/architecture/north-star.md, and accepted ADRs in the area.
  2. Explore code and tests before judging architecture.
  3. Identify where understanding requires bouncing across many shallow modules.
  4. Apply the deletion test to suspected pass-through modules.
  5. Check whether a seam has real variation, testing value, or topology-late value.
  6. Check ownership boundaries before recommending changes.
  7. Present candidates only. Do not edit first.

Candidate Format

For each candidate, report:

  1. files or owner areas involved
  2. problem and evidence
  3. why the current module or seam is shallow
  4. proposed deeper interface in plain English
  5. benefit in leverage, locality, and testability
  6. ADR or north-star conflict, if any
  7. risk and suggested verification

Ask which candidate to explore before designing interfaces or changing code.

Repository-Specific Rules

  1. A service library can be a semantic boundary without becoming a process boundary.
  2. A Rust trait is not automatically a useful seam.
  3. Platform metadata must not absorb service-local semantics.
  4. Server handlers adapt protocols; they do not own domain rules.
  5. Worker reliability claims require executable retry, checkpoint, dedupe, replay, and recovery evidence at the claimed level.

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.