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 instructions/lemur47/si-protocols/claude-mdgit 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/instructions/lemur47/si-protocols/claude-md)<a href="https://agentmods.dev/instructions/lemur47/si-protocols/claude-md"><img src="https://agentmods.dev/badge/instructions/lemur47/si-protocols/claude-md.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 | $0.01651 | $0.01651 |
| Opus 5 | $0.00826 | $0.00826 |
| Sonnet 5 | $0.00330 | $0.00330 |
| Haiku 4.5 | $0.00165 | $0.00165 |
Grade A, and why
si-protocols CLAUDE.md 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 3d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code (claude.ai/code) working in this repository.
Boot note. If CLAUDE.local.md exists at the project root, read it before starting work — it is the operator runbook (operating model, KV-TMS boot ritual, work-tracker protocol, trust boundaries) and changes independently of this file. It is classified INTERNAL and gitignored, so it is absent from public clones — that's fine, proceed without it.
What is this?
VEGA — the open-source Spiritual Intelligence tooling stream. Hybrid tech-psychic protocols to detect disinformation in metaphysical and spiritual content. Think "cybersecurity for the soul".
Local-only: never host, collect, or analyse third-party content.
The repo carries the Python toolkit, the zero-install Claude skills, and the documentation. The former editorial websites were handed over to a separate web line in July 2026, preserved at tag web-handover-2026-07; their toolkit docs now live under docs/.
Commands
The usual uv / ruff / pytest / pyright invocations behave as expected. These are the ones worth knowing:
bash scripts/post-sync.sh # (re)install the spaCy models — needed after uv sync
uv run pytest -m "not slow" # skip the spaCy-dependent tests
osv-scanner scan source --config=osv-scanner.toml --recursive . # the config flag is required
uvicorn app.main:app --host 127.0.0.1 --port 8000 # loopback only; the API is not hosted
CLI entry points:
uv run si-threat-filter <file>—--format rich|json,--lang en|jauv run si-topology <file>—--engine rule|anthropic,--format svg|json,--lang en|ja,-o OUTPUT
AnthropicEngine needs the anthropic extra and an ANTHROPIC_API_KEY. Its retired model pin and request shape were restored for the current generation and verified against the live endpoint on 2026-08-13 — EN and JA corpus samples, request accepted, response parsed, variables classified. No key is kept on this machine, so re-verification needs a fresh one. Rich output respects NO_COLOR.
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.
- 3d ago First seen · 80 lines · 1,651 tokens per session scan A 613a32db6dab
si-protocols CLAUDE.md is an instructions file published in the GitHub repository lemur47/si-protocols (2 stars, last pushed 8d ago), licensed MIT. It adds 1,651 tokens to every session, about $0.0083 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 instructions, from other repositories
transformers copilot-instructions.md
Instructions for huggingface/transformers, covering copilot-instructions.md guide for hugging face transformers, core project structure, coding conventions for hugging face transformers, copying and inheritance and testing.
transformers AGENTS.md
Instructions for huggingface/transformers, a project described as: 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
compromise AGENTS.md
Instructions for spencermountain/compromise, covering agents.md — using compromise, read these first, 30-second mental model, rules that prevent most mistakes and not supported (don't try).
natural-japanese AGENTS.md
Instructions for coji/natural-japanese, covering agents.md, このスキルについて, openskills 経由で読み込む場合 and 検査スクリプトの実行.
humanizer-ru AGENTS.md
AGENTS.md instructions for Vladimir-Human/humanizer-ru, covering agents.md — карта репозитория для агентов-редакторов, что это за репозиторий, инварианты (нарушение ломает ci), полный чек-лист одной командой and куда что класть.
ai-microcore AGENTS.md
Instructions for Nayjest/ai-microcore, covering agents.md, commands, architecture and conventions.