architecture-reviewer
Skill6 starsChanged 6 months agoMITView on GitHub
Perform focused architecture and modularity reviews. Identify boundary violations, god objects, tangled dependencies, and propose the smallest reversible improvements. Use the repo-graph MCP when available. Trigger with "architecture review", "check the boundaries", "is this modular enough?".
9 other projects use a version of this.
Adopted by
Most recently taken up by
- JuanMarchetto/agent-skillstheir own version, first seen Nov 8, 2026
- Mathews-Tom/armorytheir own version, first seen Nov 1, 2026
- monsefchafik/claude-code-skillstheir own version, first seen Oct 20, 2026
- OneDro1d/dark-factorytheir own version, first seen Oct 8, 2026
- mrenigmatic19/claude_skillstheir own version, first seen Oct 8, 2026
- domehahn/skiltheir own version, first seen Jul 28, 2026
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- Mathews-Tom/armory★ 340same name
- shep-ai/shep★ 277same name
- wolulabs/hermes-founder-os★ 18same name
- JuanMarchetto/agent-skills★ 5same name
- OneDro1d/dark-factory★ 4same name
- domehahn/skil★ 1same name
- nileshteji/skills★ 1same name
- monsefchafik/claude-code-skills★ 0same name
- mrenigmatic19/claude_skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- git-disciplineSkill
- mcp-orchestratorSkill
- plan-mode-orchestratorSkill
- security-auditSkill
- subagent-arenaSkill
- tdd-intelligenceSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
0
Distinctive
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 22
Always pair recommendations with a plan (hand off to plan-mode-orchestrator).
- Very specific: line 35
Use security-audit in parallel for security-relevant architecture work.
“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Architecture Reviewer
Keeps large codebases from turning into big balls of mud.
Process
- Get a structural view (use
repo-graphMCP or manual exploration + subagents). - Map current modules and data flow.
- Identify:
- Unclear or violated boundaries
- High coupling / low cohesion
- Missing abstractions
- Opportunities for ports/adapters or domain-driven splits
- Propose the smallest change that meaningfully improves the situation.
- Always pair recommendations with a plan (hand off to
plan-mode-orchestrator).
Output Format
- Current state summary (with diagram if possible)
- Specific problems with file/line evidence
- Recommended improvement + rationale
- Risk of the change
- How to verify the improvement (usually via tests +
repo-graphdiff)
Ties to Other Skills
- Works extremely well after or with
subagent-arena. - Feeds directly into
plan-mode-orchestrator. - Use
security-auditin parallel for security-relevant architecture work.
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.

