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 draftgit 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/draft)<a href="https://agentmods.dev/skills/receptron/mulmoterminal/draft"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/draft/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/draft"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/draft.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 | $0.00036 | $0.00784 |
| Opus 5.5 | $0.00014 | $0.00314 |
| Sonnet 5.5 | $0.00007 | $0.00157 |
| Haiku 4.5 | $0.00004 | $0.00078 |
Grade A, and why
blueprint-write-draft 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 26d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write one part
Take the first part in .blueprint/outline.json whose status is "todo". Write that part only; the
next round writes the next one.
Before writing
Read .blueprint/brief.md, the part's points, and — when the folder has one — STYLE.md. Read the parts
already written, so terms, tone and numbering continue rather than restart.
Write
- Write the part to its
file, beginning with its title as a heading. - Follow
STYLE.md: voice, sentence endings, terms, structure. It is the part of the style a machine cannot check, and the reason it exists. - Cover every one of the part's
points. - State a fact only if it is in the brief's facts from sources, or is common knowledge. Anything else is an open question for the report, not a sentence.
Cite what came from the sources
For each sentence that states something taken from a source, record the source passage in
.blueprint/citations/<part id>.json:
[{ "source": "annual-report.md", "address": "h1.2", "quote": "売上は前年比 12% 増えた" }]
address is where the passage sits in the source's tree: sh <base pack>/checks/chaff.sh tree .blueprint/sources/<file> prints it (a heading's h1.2, an article's 3.2). quote is the source's own
words, copied, not your paraphrase. The check runs chaff cite on each source.
Check it yourself
sh <base pack>/checks/chaff.sh <the part's file> must report no warning or error. Fix the text, not the
style. Set a finding aside only in one of two cases, by adding it to the part in .blueprint/outline.json:
{ "id": "intro", "file": "01-intro.md", "status": "done",
"dismissed": [{ "rule": "max-sentence-length", "line": 8, "because": "meaning", "why": "資料の一文をそのまま引用している" }] }
"because": "wrong"— chaff misread the text (a heading it took for a sentence, a name it took for jargon). Each one becomes a draft report to chaff in the report step."because": "meaning"— chaff is right, but fixing it would change what must stay exact (a quotation).
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.
- 26d ago Changed · +13 lines c175b6306652
- 27d ago First seen · 51 lines · 36 tokens per session scan A 6865d8a2c044
blueprint-write-draft is a skill published in the GitHub repository receptron/mulmoterminal (245 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 784 once invoked, about $0.0001 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 2026-09-28.
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.