architect-boundary-review

architect-boundary-review is a skill for Claude Code, Codex from joinwell52-AI/CodeFlowMu-open. It costs 52 tokens per session (231 once invoked), scanned A, original, MIT.

An architecture review checklist for CodeFlowMu proposals. It checks whether responsibilities cross boundaries between tools, playbooks, lifecycle control, governance, and public submissions.

In plain words
What is it for?
Reviewing proposals involving MCP and playbook separation, REPORT/EVAL/TASK meanings, public GitHub issues, runtime IDs, or protocol changes.
Why use it?
It helps catch unsafe designs before they change runtime behavior, lifecycle state, governance, or formal protocols.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Reviewing proposals involving MCP and playbook separation, REPORT/EVAL/TASK meanings, public GitHub issues, runtime IDs, or protocol changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/joinwell52-ai/codeflowmu-open/architect-boundary-review
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add joinwell52-AI/CodeFlowMu-open --skill architect-boundary-review
Clone the repo
git clone --depth 1 https://github.com/joinwell52-AI/CodeFlowMu-open

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for architect-boundary-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/joinwell52-ai/codeflowmu-open/architect-boundary-review/github.svg)](https://agentmods.dev/skills/joinwell52-ai/codeflowmu-open/architect-boundary-review)
Your own site
<a href="https://agentmods.dev/skills/joinwell52-ai/codeflowmu-open/architect-boundary-review"><img src="https://agentmods.dev/badge/skills/joinwell52-ai/codeflowmu-open/architect-boundary-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for architect-boundary-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/joinwell52-ai/codeflowmu-open/architect-boundary-review"><img src="https://agentmods.dev/badge/skills/joinwell52-ai/codeflowmu-open/architect-boundary-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 231 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.00231
Opus 5 $0.00026 $0.00115
Sonnet 5 $0.00010 $0.00046
Haiku 4.5 $0.00005 $0.00023

Measured 10d ago against content hash 8fd4f6767610, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

architect-boundary-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/architect-boundary-review/SKILL.md · 37 lines

What it actually says

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
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 37 lines · 52 tokens per session scan A 8fd4f6767610

Subscribe to this mod's changes

architect-boundary-review is a skill published in the GitHub repository joinwell52-AI/CodeFlowMu-open (2 stars, last pushed 16d ago), licensed MIT. It adds 52 tokens to every session and 231 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.