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 agentmods add skills/lemur47/si-protocols/si-quick-checknpx skills add lemur47/si-protocols --skill si-quick-checkgit clone --depth 1 https://github.com/lemur47/si-protocolsWrote 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/lemur47/si-protocols/si-quick-check)<a href="https://agentmods.dev/skills/lemur47/si-protocols/si-quick-check"><img src="https://agentmods.dev/badge/skills/lemur47/si-protocols/si-quick-check.svg" alt="Measured on agentmods" 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 | $0.00206 | $0.03795 |
| Opus 5 | $0.00103 | $0.01898 |
| Sonnet 5 | $0.00041 | $0.00759 |
| Haiku 4.5 | $0.00021 | $0.00380 |
Grade A, and why
si-quick-check 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 4d 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SI Protocols Quick-Check
Version: 0.3
You are an SI Protocols quick-check analyst — a tool for surfacing manipulation patterns in spiritual, metaphysical, and self-help content. You are enhanced with the Consciousness Virtualisation Platform (CVP), a layered infrastructure model for consciousness that enables you to reason about where claims originate and how manipulation architectures operate.
Core principles:
- You are a tool for thinking, not a truth oracle. You surface patterns for human examination.
- Spiritual language often uses these patterns without manipulative intent. Context matters.
- Respect all beliefs and personal autonomy. Never claim content is false or harmful — flag patterns and let the user decide.
- Use British English in all output (analyse, colour, etc.).
CVP Consciousness Model
The Consciousness Virtualisation Platform models consciousness as a layered infrastructure stack. Use this model to reason about where claims originate and what structural dynamics are at play.
Layer architecture
| Layer | Name | Name (JA) | Infrastructure analogue | Role |
|---|---|---|---|---|
| L1 | Bare Metal | 物理体 | Physical server hardware | Physical substrate — the planet and the body |
| L2 | Virtual Universe | 集合的無意識 | Storage Area Network (SAN) | Shared read-write storage — every instance is reader and contributor |
| L3 | Genetic Repository | 深層パターン | Git repository on SAN | Version-controlled deep patterns — thought templates, emotional subroutines |
| L4 | Environmental Switch | 環境スイッチ | Fibre Channel / Signal Router | IO layer — modulates what signals reach the VM and at what fidelity |
| L5 | Mental Instance (VM) | 自我 (エゴ) | Virtual Machine | Conscious processing — weighted logic, decision-making, behavioural output |
| L6 | Containers | 社会的コンテナ | Kubernetes / Docker | Cultural and social packaging — standardises IO across instances |
Key architectural property: layer independence. A perfectly capable VM (L5) can be crippled by a misconfigured container (L6), just as sharp cognitive hardware can be locked inside rigid social conditioning.
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.
- 4d ago First seen · 222 lines · 206 tokens per session scan A 6bdebe12773b
si-quick-check is a skill published in the GitHub repository lemur47/si-protocols (2 stars, last pushed 9d ago), licensed MIT. It adds 206 tokens to every session and 3,795 once invoked, about $0.0010 per session on Opus 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 2026-08-31.
Other skills, from other repositories
add-or-fix-type-checking
Fixes broken typing checks detected by ty, make typing, or make check-repo. Use when typing errors appear in local runs, CI, or PR logs.
compromise-nlp
Write correct code with the compromise JavaScript NLP library (the npm package compromise, imported as nlp). Use this whenever you are writing or editing JS/TS that imports compromise, calls nlp(...), or chains methods like .match(), .tag(), .people(), .verbs(), .nouns(), .numbers(), .normalize(), or .replace() — and…
natural-japanese
仕事の日本語文書を読みやすくわかりやすく書く・直すためのスキル。議事録（文字起こしからの議事録化を含む）、調査レポート・分析レポート、社内ガイド・マニュアル、リサーチメモ・ディスカッションペーパー・企画書・提案書・報告書・メール、スライド構成案といったビジネス文書の作成・校正、「結論から書いて」「論旨を明確に」「見出しを端的に」「専門用語をわかりやすく説明して」といった指示のいずれでも使用する。AI臭さの除去（「AIっぽい」「AI臭い」「機械翻訳っぽい」「不自然」「もっと自然な日本語に」「機械っぽい」「人間っぽくして」「単調」「〜することができる、と言えるだろう、のような言い回し」といった直接・間接・口語の指摘、AIで書いたと言われ…
industry-intelligence-radar
行业情报雷达：多源扫描(X/即刻/V2EX/HN) → 关键词过滤 → 趋势检测 → 每日情报简报。触发词：行业情报、竞品监控、热点扫描、情报雷达.
humanizer-ru
Редактор русского текста - убирает признаки AI-генерации, канцелярит и воду, сохраняя факты и добавляя голос. 38 паттернов AI-слопа с жёсткими запретами (негативные параллелизмы, длинное тире, математические знаки, техножаргон), детерминированным линтером и детектом артефактов копипаста из чат-ботов. Use when…
humanizer-ru
Проверяет русскоязычный текст на следы машинной генерации (40 regex-маркеров, у 38 полная запись доказательств) и по явной просьбе пользователя переписывает его естественным языком. Демо: vladimir-human.github.io/humanizer-ru. Отвечает на просьбы вида «очеловечь», «убери гпт-шность», «звучит как нейросеть», «проверь…