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 countergit 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/counter)<a href="https://agentmods.dev/skills/receptron/mulmoterminal/counter"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/counter/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/counter"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/counter.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 | $0.00025 | $0.00478 |
| Opus 5.5 | $0.00010 | $0.00191 |
| Sonnet 5.5 | $0.00005 | $0.00096 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
blueprint-style-counter 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 25d 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
Show that the style catches something
A style that no bad text can trip is a style nothing checks. This is the documents' version of breaking the code to see a test go red.
Write a few short texts in .blueprint/counter/, in the same language and kind as the models. Each
breaks the guide on purpose, and each in a different way: a long run-on sentence, the wrong sentence
ending mixed in, a heading the next sentence merely repeats, padding and cushion phrases, a term spelled
against STYLE.md. Keep them plausible — the kind of draft a real writer produces on a bad day.
List them in .blueprint/counter.json:
[{ "file": "run-on.md", "breaks": "語調と文末: 一文に三つ以上のことを詰めない" }]
Done when
node <usecase pack>/checks/counter.mjs (with BLUEPRINT_BASE and BLUEPRINT_USECASE set to the pack folders from your prompt) passes: chaff reports something in every counter text,
at least three different rules fire across them, and every rule chaff.yaml turns on fires in at least one of
them (a note counts). A consistency rule (contractions, the Oxford comma, heading case) reports only against a
clear majority, so its text must lean one way and break it once or twice — a text split evenly shows nothing. Never
write in the report that a rule "does not react" unless a text built to trip it was run and stayed silent. If a text raises nothing, the style does not reach what
it breaks: either that part belongs in STYLE.md only (a machine cannot see it — say so in the report),
or a rule is too loose or off — change it in chaff.yaml and record the new level and its reason in
.blueprint/rule-decisions.json. This step's check runs the rules step's check again first, so a change
that makes the models fail their own style, or a change without a reason, stops here.
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.
- 25d ago Changed · +3 lines c9677b913b45
- 27d ago First seen · 30 lines · 25 tokens per session scan A 3729006be831
blueprint-style-counter is a skill published in the GitHub repository receptron/mulmoterminal (245 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 478 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
ralph
Self-referential loop until task completion with configurable verification reviewer.
tdd
Test-first at pre-agreed seams — one test, one implementation, tracer-bullet red/green; independent expected values; substitutions only at the seam's boundary class; launch Phase 4 reference.
moai-ref-testing-pyramid
Test pyramid strategy, coverage targets, test patterns, and quality metrics reference. Agent-extending skill that amplifies manager-develop test-creation and quality-validation work with production-grade testing patterns. NOT for: production code implementation, architecture design, DevOps, security audits.
tdd
Build this test-first, one behavior at a time: $ARGUMENTS.
moai-workflow-loop
Ralph Engine - Automated feedback loop with LSP diagnostics and AST-grep integration for continuous code quality improvement. Use when implementing error-driven development, automated fixing, or continuous quality validation workflows.
moai-workflow-testing
Use when writing tests, measuring coverage, or running characterization, performance, or PR-review QA. Comprehensive specialist combining DDD testing, characterization tests, performance profiling, and TRUST 5 quality-assurance validation.