agentleFS
Sign inStart free
joinwell52-AIjoinwell52-AI/CodeFlowMu-open/skills/architect-boundary-review/SKILL.md

architect-boundary-review

Skill2 starsChanged 4 months agoMITView on GitHub

Review CodeFlowMu proposals for boundary violations. Use when an architect needs to check MCP vs Playbook separation, lifecycle authority, REPORT/EVAL/TASK semantics, public-submission safety, PM runtime ID preservation, or protocol-change risk.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when a proposal may cross runtime, lifecycle, governance, public-submission, or protocol boundaries.

    line 10
  2. Distinctive:

    Check for layer mixing.

    line 14
  3. Distinctive:

    Check lifecycle and ADMIN authority.

    line 15
  4. Distinctive:

    Check REPORT, EVAL, TASK, ISSUE, and REVIEW semantics.

    line 16
  5. Distinctive:

    Do not let MCP decide governance.

    line 25
  6. Distinctive:

    Do not auto-submit GitHub issues.

    line 26
  7. Distinctive:

    Do not archive, delete, or move lifecycle from playbook advice.

    line 27
  8. Distinctive:

    Do not modify formal FCoP protocol.

    line 28

≈ “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

Architect Boundary Review

When to use

Use this skill when a proposal may cross runtime, lifecycle, governance, public-submission, or protocol boundaries.

Rules

  • Check for layer mixing.
  • Check lifecycle and ADMIN authority.
  • Check REPORT, EVAL, TASK, ISSUE, and REVIEW semantics.
  • Recommend the smallest compliant shape.

Required output

Use docs/skills/architect-playbook/boundary-review.md.

Forbidden actions

  • Do not let MCP decide governance.
  • Do not auto-submit GitHub issues.
  • Do not archive, delete, or move lifecycle from playbook advice.
  • Do not modify formal FCoP protocol.

Minimal example

Conclusion: reject
Crossed boundary: EVAL would submit public GitHub issue
Safer shape: internal draft with admin_approved=false

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