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 sourcesgit 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/sources)<a href="https://agentmods.dev/skills/receptron/mulmoterminal/sources"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/sources/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/sources"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/sources.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 | $0.00031 | $0.00448 |
| Opus 5.5 | $0.00012 | $0.00179 |
| Sonnet 5.5 | $0.00006 | $0.00090 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
blueprint-style-sources 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
Collect the models
.blueprint/answers.json → sources lists what the person wants the style taken from: files, folders
or URLs, one per line. The person may not be an engineer; tell them in plain words what you collected.
Change nothing in the repository: copies go into .blueprint/sources/, and the originals are only read.
The person approves the collected models before the next step writes anything of theirs.
How
- A file: copy it to
.blueprint/sources/<name>.md. A.txtbecomes.mdunchanged. A Word or PDF file: extract the text faithfully (headings as#, lists as-); say in the report that it was converted. - A folder: take the documents in it (Markdown and text). Ask before taking more than about twenty.
- A URL: fetch the page and keep only the article body, as Markdown — no navigation, footer, cookie banner or share buttons. Those are the site's words, not the author's, and would be measured as the style.
- Never rewrite the text: a fixed typo in a model changes what is measured.
- Keep them in one language and one kind of document. If the list mixes them, ask which to keep.
Write .blueprint/sources.json, one entry per file:
[{ "file": "about-us.md", "origin": "https://example.com/about" }]
Done when
node <usecase pack>/checks/sources.mjs (with BLUEPRINT_BASE and BLUEPRINT_USECASE set to the pack folders from your prompt) passes: every file is listed with its origin and every
listed file exists. There must be at least two documents with enough text between them to measure a
style — one short text is that text's habits, not a style. If there is too little, ask the person for more.
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 · 36 lines · 31 tokens per session scan A 86f02f25104c
blueprint-style-sources is a skill published in the GitHub repository receptron/mulmoterminal (245 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 448 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.