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 rulesgit 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/rules)<a href="https://agentmods.dev/skills/receptron/mulmoterminal/rules"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/rules/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/rules"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/rules.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 | $0.00043 | $0.01463 |
| Opus 5.5 | $0.00017 | $0.00585 |
| Sonnet 5.5 | $0.00009 | $0.00293 |
| Haiku 4.5 | $0.00004 | $0.00146 |
Grade A, and why
blueprint-style-rules 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write the style
The style ends up in two places, and they do different jobs:
chaff.yaml— what a machine checks on every document: the genre, the language, how strict each rule is, the team's own words. chaff is a linter; it never judges meaning and never rewrites.STYLE.md— what the writer (you, in a later build, or a person) reads and follows: voice, sentence endings, terms, structure. Everything a machine cannot measure goes here.
Read .blueprint/answers.json for the kind of document, the language, the audience and how strict to be.
Run chaff from the folder as sh <base pack>/checks/chaff.sh … — the wrapper the checks use, so what you
measure is what they will measure. Below it is written chaff … for short.
1. Measure
- Genre:
chaff genreslists them, each with what it is for. Pick the one for the answerkind— contracts (legal/contract), rules and regulations (legal/statute), manuals (docs/manual), FAQs, glossaries, papers and literature have genres of their own. Only when none fits, pick the closest and say so in the report. A genre chaff does not know stops every run, so copy it from the list. - Language: from the answer, or what chaff detects on the sources.
- Thresholds:
chaff eval .blueprint/sourcessweeps each rule's limits over the models and recommends one. Read it rule by rule. - What fires now:
chaff .blueprint/sources --genre <genre>with no config yet.
2. Decide, one rule at a time
For each rule that fires on the models, or that eval recommends changing:
- The models do it on purpose (a long sentence is how this author writes): relax it, or turn it off.
- The models slip and the person chose "少し厳しく": keep it, and write in STYLE.md why the models are not the example there. The models must still pass, so this means a level they meet.
- Never set a rule the models do not tell you about. A style is measured, not imagined.
Write chaff.yaml with genre, language and rules: (strict | normal | relaxed | off). Add
jargon: for the team's own words only if the models show them.
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 Changed · +1 lines 6e6e25335c2b
- 25d ago Changed · +5 lines 3f91c3cbbf58
- 27d ago First seen · 81 lines · 43 tokens per session scan A 95063ae4f222
blueprint-style-rules is a skill published in the GitHub repository receptron/mulmoterminal (245 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 1,463 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 2026-09-28.
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.