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 briefgit 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/brief)<a href="https://agentmods.dev/skills/receptron/mulmoterminal/brief"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/brief/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/brief"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/brief.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 | $0.00033 | $0.00530 |
| Opus 5.5 | $0.00013 | $0.00212 |
| Sonnet 5.5 | $0.00007 | $0.00106 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
blueprint-write-brief 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 27d 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.
What it actually says
The brief
.blueprint/answers.json holds what the person asked for. The person may not be a writer or an engineer:
say what you do in plain words.
Change nothing in the repository: this step writes only inside .blueprint/. The person reads the brief
and approves it before anything of theirs is written.
Collect the sources (when sources is not empty)
Copy each file, or fetch each page's article body only, as Markdown into .blueprint/sources/, and
list them in .blueprint/sources.json as [{ "file", "origin" }]. Never rewrite a source: a later check
compares quotations against it word for word.
Write .blueprint/brief.md
In the language the document will be written in, with these sections (either name works):
## 目的/## Purpose— what the document is for, in one or two sentences.## 読者/## Audience— who reads it and what they can do after reading.## 要点/## Key points— every point from the answerpoints, plus what the topic needs.## 資料から取る事実/## Facts from sources— each fact the document will state, with the source file it comes from. With no sources, write "資料なし — 事実は書き手の知識による" and say which facts need checking.## 決まっていないこと/## Open questions— what you would ask the person. Write "なし" if there is none.
Do not invent facts. A number, a name, a date or a quotation that is not in the sources goes under open questions, not under facts.
Which style
If the answer style is the folder's style, read STYLE.md and chaff.yaml now and note anything in them
that shapes this document. If they are missing, stop: the check tells the person to make the style first
or to choose chaff's defaults.
Done when
node <usecase pack>/checks/brief.mjs (with BLUEPRINT_BASE and BLUEPRINT_USECASE set to the pack
folders from your prompt) passes.
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.
- 27d ago First seen · 44 lines · 33 tokens per session scan A 366aed5328f5
blueprint-write-brief is a skill published in the GitHub repository receptron/mulmoterminal (245 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 530 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-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…
self-assessment
Interactive skill assessment with personalized learning path generation.
project-design
Roteador de processos de design e marca que carrega orientações para criar arquivos DESIGN.md completos para um projeto e suas aplicações de interface.
loom-swift
Swift language expertise for idiomatic, production-quality code.
loom-usage
Meta-orchestration skill for Claude driving loom itself.
loom-c
C language expertise (C11/C17/C23) for memory-safe, portable, production-quality systems code.