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.
npx skills add iroha924/mumei --skill gleangit 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/skills/iroha924/mumei/glean)<a href="https://agentmods.dev/skills/iroha924/mumei/glean"><img src="https://agentmods.dev/badge/skills/iroha924/mumei/glean.svg" alt="Measured on agentmods" 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 | $0.00107 | $0.02433 |
| Opus 5 | $0.00053 | $0.01216 |
| Sonnet 5 | $0.00021 | $0.00487 |
| Haiku 4.5 | $0.00011 | $0.00243 |
Grade A, and why
glean 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 8d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Glean
Run a structured gleaning session with the user before they invoke /mumei:compose. The output is a scratch file at .mumei/scratch/<topic>.md that captures the user's intent in a form /mumei:compose can consume cleanly.
When to use
- The user describes a vague feature request ("I want X", "let's add Y").
- The user asks for help thinking through a problem before specing it.
- The user invokes
/mumei:gleandirectly.
Do NOT use this skill if /mumei:compose is already running — compose does its own clarification.
Method
Run up to 3 rounds of 5 questions each (15 total cap). Each round:
- Use
AskUserQuestionwith multiple-choice options where possible. - Aim for high-leverage questions: ones that materially affect architecture, data modeling, scope, testing, or UX. Skip trivial questions ("what should the variable be named?").
- Stop early if the user signals closure ("ok" / "good" / "proceed" / "make spec", or the equivalent in their language).
Round 1 — Cover the 5 axes
Aim to cover all five in this round. Use multiple-choice for speed:
| # | Axis | Example phrasing |
|---|---|---|
| Q1 | Goal / JTBD | "What problem does this solve? A) End-user authentication for SaaS B) Internal tool C) Prototype D) Other" |
| Q2 | Scope (MoSCoW Won't) | "Which of the following are EXPLICITLY out of scope for v1?" |
| Q3 | Existing constraints | "Which auth library/framework, if any?" |
| Q4 | Critical edge case | "Which failure modes matter most?" |
| Q5 | Done definition | "What is 'done'? A) Functions in dev B) Tests pass C) Deployed to staging D) Other" |
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.
- 8d ago First seen · 193 lines · 107 tokens per session scan A 6d27359fba39
glean is a skill published in the GitHub repository iroha924/mumei (2 stars, last pushed yesterday), licensed MIT. It adds 107 tokens to every session and 2,433 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 skills, from other repositories
harness
A meta-skill for designing and maintaining a project harness: a coordinated set of specialist agents, skills, and project instructions. It defines their roles, connects them to the project, and updates the setup as the work changes.
evaluator-write-qa-parallel
Internal Auto-Harness evaluator skill for parallel sprint QA and QA report writing. Use only inside the Evaluator subagent during evaluatorqaparallel.
evaluator-write-qa
Internal Auto-Harness evaluator skill for sprint QA and QA report writing. Use only inside the Evaluator subagent during qa mode.
evaluator-review-contract-parallel
Internal Auto-Harness evaluator skill for parallel sprint contract review before implementation. Use only inside the Evaluator subagent during review mode.
evaluator-write-final-parallel
Internal Auto-Harness evaluator skill for parallel final QA report aggregation. Use only inside the Evaluator subagent during evaluatorfinalparallel.
evaluator-write-retest-parallel
Internal Auto-Harness evaluator skill for parallel sprint retest and retest report writing. Use only inside the Evaluator subagent during evaluatorretestparallel.