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.
In this repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- backend-engineeringSkill
- contract-agentSkill
- harness-diagnoseSkill
- harness-grillSkill
- harness-tddSkill
- harness-zoom-outSkill
- plannerSkill
- platform-ops-agentSkill
- server-agentSkill
- service-agentSkill
- skill-authoringSkill
- worker-agentSkill
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
- Distinctive: line 12
Use this skill to surface architecture friction before proposing refactors.
- Very specific: line 18
Read AGENTS.md, agent/codemap.yml, docs/architecture/north-star.md, and accepted ADRs in the area.
- Distinctive: line 22
Check whether a seam has real variation, testing value, or topology-late value.
- Distinctive: line 23
Check ownership boundaries before recommending changes.
- Distinctive: line 38
Ask which candidate to explore before designing interfaces or changing code.
≈ “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.
Files
Harness Architecture Review
Use this skill to surface architecture friction before proposing refactors.
Workflow skills guide process. Ownership skills still decide writable boundaries.
Process
- Read
AGENTS.md,agent/codemap.yml,docs/architecture/north-star.md, and accepted ADRs in the area. - Explore code and tests before judging architecture.
- Identify where understanding requires bouncing across many shallow modules.
- Apply the deletion test to suspected pass-through modules.
- Check whether a seam has real variation, testing value, or topology-late value.
- Check ownership boundaries before recommending changes.
- Present candidates only. Do not edit first.
Candidate Format
For each candidate, report:
- files or owner areas involved
- problem and evidence
- why the current module or seam is shallow
- proposed deeper interface in plain English
- benefit in leverage, locality, and testability
- ADR or north-star conflict, if any
- risk and suggested verification
Ask which candidate to explore before designing interfaces or changing code.
Repository-Specific Rules
- A service library can be a semantic boundary without becoming a process boundary.
- A Rust trait is not automatically a useful seam.
- Platform metadata must not absorb service-local semantics.
- Server handlers adapt protocols; they do not own domain rules.
- Worker reliability claims require executable retry, checkpoint, dedupe, replay, and recovery evidence at the claimed level.
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.

