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 readgit 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/read)<a href="https://agentmods.dev/skills/receptron/mulmoterminal/read"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/read/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/read"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/read.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 | $0.00037 | $0.00978 |
| Opus 5.5 | $0.00015 | $0.00391 |
| Sonnet 5.5 | $0.00007 | $0.00196 |
| Haiku 4.5 | $0.00004 | $0.00098 |
Grade A, and why
blueprint-review-read 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.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read the documents and write the findings
.blueprint/answers.json names the documents (documents, one path per line), what kind they are
(kind), what the person is worried about (focus) and how far to go (proposals). The person may not be
a lawyer or an engineer: write for them in plain words, in their language.
Change nothing in the repository: this step only reads. The documents are the person's originals and stay
exactly as they are — the next check fails if one of them changes. Write only under .blueprint/.
First, what chaff finds by machine
For each document run, from the folder, sh <base pack>/checks/chaff.sh <document> --experimental --compact.
Three rules read the document's structure (chaff tree <document> shows the addresses they use):
dangling-reference— a reference such as "第12条" or "Section 4.2" to a provision that does not exist;numbering-gap— articles, paragraphs or items numbered with a gap or out of order;duplicate-definition— the same term defined twice.
Every one of these must appear in the findings as a finding with a machine field
({ "rule", "file", "line" }: the rule and line as chaff reported them, the file as documents names it), or in dismissed with the same fields and a
why — for example, a reference into another law that the document names. Do not claim a machine result
chaff did not report. Other chaff findings (style) are not the subject of this review; leave them.
Then, what only reading finds
Read the whole of every document, starting with focus. Look for:
- contradiction — two provisions that cannot both hold (different amounts, periods, parties, conditions; one permits what another forbids);
- ambiguity — a provision a reasonable reader could apply two ways, a term used but never defined, a deadline without a start;
- omission — something the rest of the document relies on but never says (who pays, what happens when a condition fails).
Report only what the text supports. A finding you cannot quote is not a finding.
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 · 78 lines · 37 tokens per session scan A 494598b52fef
blueprint-review-read is a skill published in the GitHub repository receptron/mulmoterminal (245 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 978 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
lifecycle-messaging
Email/SMS lifecycle and deliverability framework for SMB Product-Builder products that send transactional or lifecycle messages (booking reminders, CRM sequences, receipts, win-back). Codifies provider selection (Resend/Postmark/Twilio/SendGrid), domain auth (SPF/DKIM/DMARC), consent and compliance (TCPA, CAN-SPAM…
civic-publish-gate
Run deterministic source, citation, freshness, privacy, meeting-certainty, accessibility, correction-state, and human-approval checks before civic publication.
editorial-correction-review
Review a challenged civic claim and prepare a visible, append-only correction or withdrawal with downstream propagation evidence.
kdd-compliance-scan
Guia a cualquier agente (no depende de ningun modelo puntual) para producir un scan de compatibilidad de licencias de dependencias de un repositorio en el formato de contrato de Capa 3 de KDD -- findings.json -- que despues gatea scripts/validatecompliancefindings.py. Usala cuando se pida auditar licencias de…
kdd-privacy-scan
Guia a cualquier agente (no depende de ningun modelo puntual) para producir un scan de datos personales/PII y su base legal de tratamiento en el formato de contrato de Capa 3 de KDD -- findings.json -- que despues gatea scripts/validateprivacyfindings.py. Usala cuando se pida mapear datos personales que recolecta un…
contract-and-proposal-writer
Generate business documents — contracts, proposals, SOWs, NDAs, MSAs — with jurisdiction-aware clauses for US, EU, UK, and DACH. Use when starting client engagements, writing proposals, drafting agreements, or needing GDPR-compliant DPAs.