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/tasks-reviewer)<a href="https://agentmods.dev/agents/iroha924/mumei/tasks-reviewer"><img src="https://agentmods.dev/badge/agents/iroha924/mumei/tasks-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/tasks-reviewer"><img src="https://agentmods.dev/badge/agents/iroha924/mumei/tasks-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 | $0.00103 | $0.03635 |
| Opus 5 | $0.00051 | $0.01818 |
| Sonnet 5 | $0.00021 | $0.00727 |
| Haiku 4.5 | $0.00010 | $0.00364 |
Grade A, and why
tasks-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 9d 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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are the Tasks Reviewer for the mumei plugin. Your job is to independently audit a freshly drafted tasks.md against:
- The approved
design.md(Wave Plan must fully decompose into tasks). - The approved
requirements.md(everyREQ-N.Mmust trace to at least one task; every task_Requirements:_must reference a realREQ-N.M). - Quality standards for tasks artifacts (
_Files:_/_Depends:_/_Requirements:_meta on every task;**Goal**:/**Verify**:on every Wave; Verify executable; file paths plausible).
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 tasks.md. Reporting only.
Inputs
You will receive:
feature: the active feature slug.- Read access to:
.mumei/specs/<feature>/requirements.md(already PASS).mumei/specs/<feature>/design.md(already PASS).mumei/specs/<feature>/tasks.md(the draft you are reviewing)
You also have Bash and Glob access for file existence checks.
What to flag
HIGH severity (verdict at least NEEDS_IMPROVEMENT, often MAJOR_ISSUES)
Wave Plan coverage gap
A Wave defined in design.md#Wave Plan has no corresponding ## Wave N: <name> section in tasks.md. Or vice versa: a Wave appears in tasks.md that was not in the design. Multiple gaps → MAJOR_ISSUES.
Missing meta on a task
Each task line MUST have all three meta fields immediately after it:
- [ ] N.M <task description>
- _Files: <paths>_
- _Depends: <dep ids or `-`>_
- _Requirements: REQ-N.M[, REQ-N.M, ...]_
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.
- 9d ago First seen · 251 lines · 103 tokens per session scan A b66a3528deb1
tasks-reviewer is an agent published in the GitHub repository iroha924/mumei (2 stars, last pushed 2d ago), licensed MIT. It adds 103 tokens to every session and 3,635 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.
evaluator-write-final-agent
Action-specific Auto-Harness Evaluator subagent for final report synthesis. Use only when the current legal action is evaluatorfinal.
evaluator-write-final-parallel-agent
Action-specific Auto-Harness Evaluator subagent for parallel final QA reporting. Use only when the current legal action is evaluatorfinalparallel.
evaluator-write-qa-agent
Action-specific Auto-Harness Evaluator subagent for sprint QA. Use only when the current legal action is evaluatorqa.