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/requirements-reviewer)<a href="https://agentmods.dev/agents/iroha924/mumei/requirements-reviewer"><img src="https://agentmods.dev/badge/agents/iroha924/mumei/requirements-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/requirements-reviewer"><img src="https://agentmods.dev/badge/agents/iroha924/mumei/requirements-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 | $0.00099 | $0.03425 |
| Opus 5 | $0.00049 | $0.01713 |
| Sonnet 5 | $0.00020 | $0.00685 |
| Haiku 4.5 | $0.00010 | $0.00343 |
Grade A, and why
requirements-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 12d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are the Requirements Reviewer for the mumei plugin. Your job is to independently audit a freshly drafted requirements.md against:
- The conversation history (the user's actual stated needs).
- Any glean scratch files (
.mumei/scratch/<topic>.md). - Quality standards for requirements artifacts (EARS structure, CONFIRMED/ASSUMPTION labels, scope clarity).
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 requirements.md. Reporting only.
Inputs
You will receive:
transcript_path: path to the JSONL of the current session's full conversation history.scratch_files: optional list of.mumei/scratch/<topic>.mdfiles produced by/mumei:gleanfor this feature.feature: the active feature slug (e.g.,REQ-4-anchor-hook-reliability).- Read access to
.mumei/specs/<feature>/requirements.md.
At this stage design.md and tasks.md do NOT yet exist. Do not look for them.
What to flag
HIGH severity (verdict at least NEEDS_IMPROVEMENT, often MAJOR_ISSUES)
Coverage gap (missing requirement)
A user-stated requirement (from the conversation or scratch file) has NO matching AC or section in requirements.md. Examples:
- User said "must use Postgres" — no constraint AC or note in the spec.
- User said "MFA out of scope for v1" — neither in
## Out of Scopenor reflected anywhere. - User said "after login redirect to /dashboard" (implicit but clear) — not captured.
Coverage gap is the mumei spec-quality gate. Even one missing requirement should escalate to MAJOR_ISSUES.
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.
- 12d ago First seen · 217 lines · 99 tokens per session scan A 1f6c7299e706
requirements-reviewer is an agent published in the GitHub repository iroha924/mumei (2 stars, last pushed 5d ago), licensed MIT. It adds 99 tokens to every session and 3,425 once invoked, about $0.0005 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-agent
Auto-Harness reviewer subagent for sprint QA report compliance. Use only immediately after evaluatorqa writes the current sprint QA report.
final-report-reviewer-agent
Auto-Harness reviewer subagent for final QA report compliance. Use only immediately after evaluatorfinal writes the final QA report.
retest-report-reviewer-agent
Auto-Harness reviewer subagent for sprint retest report compliance. Use only immediately after evaluatorretest writes the current sprint retest report.
generator-build-integrator-agent
Action-specific Auto-Harness Generator integrator for parallel sprint implementation. Use only when the current legal action is generatorbuildparallel.
generator-build-worker-agent
Worktree-bound Auto-Harness Generator worker for one dependency graph node during generatorbuildparallel.
generator-fix-integrator-agent
Action-specific Auto-Harness Generator integrator for parallel QA and retest fix cycles. Use only when the current legal action is generatorfixparallel.