glean

glean is a skill for Claude Code from iroha924/mumei. It costs 107 tokens per session (2,433 once invoked), scanned A, original, MIT.

A guided questioning workflow used before designing a software feature. It asks structured questions about the goal, scope, constraints, edge cases, and what completion means, then saves the results for later specification work.

In plain words
What is it for?
Use it to run up to three rounds of focused questions, record the answers in a scratch file, and prepare input for the feature composition workflow.
Why use it?
It turns a vague feature idea into clearer working material before design begins. This helps expose missing requirements and decisions early.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the mumei plugin — 11 skills, 10 agents, 18 hooks shipped together

Good fit Use it to run up to three rounds of focused questions, record the answers in a scratch file, and prepare input for the feature composition workflow.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/iroha924/mumei/glean
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 iroha924/mumei --skill glean
Clone the repo
git clone --depth 1 https://github.com/iroha924/mumei

Made for: Claude Code.

Or install mumei, the plugin that ships this one along with the rest of its 11 skills, 10 agents, 18 hooks.

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 glean

README.md
[![agentmods](https://agentmods.dev/badge/skills/iroha924/mumei/glean.svg)](https://agentmods.dev/skills/iroha924/mumei/glean)
Your own site
<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>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,433 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 $0.00107 $0.02433
Opus 5 $0.00053 $0.01216
Sonnet 5 $0.00021 $0.00487
Haiku 4.5 $0.00011 $0.00243

Measured 8d ago against content hash 6d27359fba39, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

skills/glean/SKILL.md · 193 lines

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:glean directly.

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:

  1. Use AskUserQuestion with multiple-choice options where possible.
  2. 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?").
  3. 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"

Read the full file on GitHub · 193 lines

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. 8d ago First seen · 193 lines · 107 tokens per session scan A 6d27359fba39

Subscribe to this mod's changes

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.