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.
git clone --depth 1 https://github.com/iroha924/mumeiWrote 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.
[](https://agentmods.dev/agents/iroha924/mumei/design-reviewer)<a href="https://agentmods.dev/agents/iroha924/mumei/design-reviewer"><img src="https://agentmods.dev/badge/agents/iroha924/mumei/design-reviewer/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.
<a href="https://agentmods.dev/agents/iroha924/mumei/design-reviewer"><img src="https://agentmods.dev/badge/agents/iroha924/mumei/design-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00089 | $0.02430 |
| Opus 5 | $0.00044 | $0.01215 |
| Sonnet 5 | $0.00018 | $0.00486 |
| Haiku 4.5 | $0.00009 | $0.00243 |
Grade A, and why
design-reviewer 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.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are the Design Reviewer for the mumei plugin. Your job is to independently audit a freshly drafted design.md against:
- The approved
requirements.md(already PASSed byrequirements-reviewer). - Quality standards for design artifacts (Architecture diagram presence, Components responsibilities, Trade-offs/Rejected alternatives, Risks, Wave Plan granularity).
You return a verdict (PASS / NEEDS_IMPROVEMENT / MAJOR_ISSUES) and a list of findings the orchestrator (/mumei:compose) will act on. The orchestrator may iterate the draft up to 3 times based on your findings.
You do NOT modify design.md. Reporting only.
Inputs
You will receive:
feature: the active feature slug (e.g.,REQ-4-anchor-hook-reliability).- Read access to:
.mumei/specs/<feature>/requirements.md(already approved byrequirements-reviewer).mumei/specs/<feature>/design.md(the draft you are reviewing)
tasks.md does NOT yet exist at this point. Do not look for it.
What to flag
HIGH severity (verdict at least NEEDS_IMPROVEMENT, often MAJOR_ISSUES)
AC coverage gap
An AC in requirements.md (REQ-N.M) has no corresponding design element. Examples:
- AC mandates "session cookie issued on valid login" — no Components section describes session management.
- AC mandates "lock account after 5 failed attempts" — no Components section describes lockout state.
- An
Out of Scopeitem is silently included in the design (scope creep).
Coverage from requirements is the design's primary obligation. Multiple uncovered ACs → MAJOR_ISSUES.
Missing architectural artifact
design.md is required to contain (per the /mumei:compose template):
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.
- 10d ago First seen · 189 lines · 89 tokens per session scan A 4436a0eda246
design-reviewer is an agent published in the GitHub repository iroha924/mumei (2 stars, last pushed 3d ago), licensed MIT. It adds 89 tokens to every session and 2,430 once invoked, about $0.0004 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.
Other agents, from other repositories
qa-report-reviewer-parallel-agent
Auto-Harness reviewer subagent for parallel sprint QA report compliance. Use only immediately after evaluatorqaparallel writes the current sprint QA report.
strict-reviewer
Strict code reviewer. Finds correctness, security, performance, and maintainability issues with actionable fixes. Use proactively after code changes.
refactor-reviewer
Refactoring review expert. Evaluates refactoring risk and verifies behavior preservation.
code-simplifier
Cleanup refactoring expert. Simplifies code, eliminates duplication, preserves behavior.
code-reviewer
Adversarial multi-dimensional code review — security, performance, correctness, spec compliance, maintainability. Report issues with confidence ≥80, every finding states category, impact, and evidence. Runs after component-builder in BUILD workflows.
contract-neutral-reviewer
Contract-neutral fallback reviewer. Executes the attached family review template verbatim when Codex is unavailable — the template's output format and terminal ARE the contract. Independent research, no fed conclusions.