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 receptron/mulmoterminal --skill summarizegit clone --depth 1 https://github.com/receptron/mulmoterminalWrote 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/receptron/mulmoterminal/summarize)<a href="https://agentmods.dev/skills/receptron/mulmoterminal/summarize"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/summarize/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/skills/receptron/mulmoterminal/summarize"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/summarize.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 | $0.00054 | $0.00725 |
| Opus 5.5 | $0.00022 | $0.00290 |
| Sonnet 5.5 | $0.00011 | $0.00145 |
| Haiku 4.5 | $0.00005 | $0.00072 |
Grade A, and why
blueprint-summarize-summarize 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 24d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Summarize, sentence by sentence
.blueprint/answers.json names the documents (documents, one path per line), how long the summary may be
(length), who reads it (reader, may be empty) and what they most want to know (focus, may be empty). Read
every document in full. The person may not be an engineer: say what you do in plain words.
Change nothing in the repository: the documents stay exactly as they are. Write only under .blueprint/.
The parts a summary answers for
Run sh <base pack>/checks/chaff.sh tree <file> --format json on each document. Its parts are its articles
(kind article) when it has any; otherwise its sections at the first level with more than one (under a single
title heading, the sections below it). Every part is either cited by some sentence of the summary or left out on
purpose, with a reason the person can judge — never dropped silently.
Write .blueprint/summary.json
{
"sentences": [
{
"text": "経理部の確認が済んだ申請は、毎月25日に給与口座へ振り込まれる。",
"citations": [{ "source": "keihi.md", "address": "h1.3", "quote": "毎月25日にまとめて給与口座へ振り込みます" }]
}
],
"omitted": [{ "source": "keihi.md", "address": "h1.4", "why": "例外の手続きで、この読み手には要らないため" }]
}
- One claim a sentence, in the reader's language and plain words, in the order that serves the reader —
focusfirst when it names something. - Every sentence has at least one quotation that says what the sentence says:
sourceasdocumentsnames it,addressfrom the tree (the paragraph or item the words are in, or the part itself),quotecopied character for character. The check runschaff citeon every one. - A number is copied, never made. Every number a sentence states must appear in one of its quotations (or in the name of a place it cites, such as 第4条): the check refuses any other. Do not add up, convert or round.
- The length is the most sentences
lengthallows (短く 5, ふつう 10; くわしく has no limit). When the parts outnumber the sentences, one sentence may cite several parts, or a part the reader does not need may be left out inomitted— with a reason.
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.
- 24d ago First seen · 51 lines · 54 tokens per session scan A b4005407f979
blueprint-summarize-summarize is a skill published in the GitHub repository receptron/mulmoterminal (245 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 725 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-01.
Other skills, from other repositories
moai-docs-generation
Documentation generation patterns for technical specs, API docs, user guides, and knowledge bases using real tools like Sphinx, MkDocs, TypeDoc, and Nextra. Use when creating docs from code, building doc sites, or automating documentation workflows.
moai-domain-html-report
Markdown-to-single-file-HTML report renderer. Six modes (status, incident, plan, explainer, financial, pr) selected by report type, crossed with three audience tiers (expert, basic, learn) derived from the active output style. The basic and learn tiers enrich the HTML with mermaid flowcharts, worked examples, and…
ase-docs-proofread
Analyze the documents for spelling, capitalization, punctuation, word break, or grammar errors. Use when the user wants to "proofread" or "spellcheck" a document.
ospec
Document-driven OSpec workflow for initialization, change/goal routing, validation, archiving, and durable project knowledge.
gdoc
Read publicly shared Google Docs using curl to download into a file.
atelier-setup
Configure a repository for Atelier's development workflow. Use only when explicitly invoked; inspect existing guidance, issue-tracker and domain-document conventions, preview the proposed configuration, and write only after approval. It does not install Atelier or initialize external tooling.