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/cm2489/oravan/agents-mdgit clone --depth 1 https://github.com/cm2489/oravanWhat 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 | $0.00478 | $0.00478 |
| Opus 5 | $0.00239 | $0.00239 |
| Sonnet 5 | $0.00096 | $0.00096 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
oravan AGENTS.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 yesterday.
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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- yesterday First seen · 40 lines · 478 tokens per session scan A 70f377e09b8f
oravan AGENTS.md is an instructions file published in the GitHub repository cm2489/oravan (1 stars, last pushed 2d ago), licensed AGPL-3.0. It adds 478 tokens to every session, about $0.0024 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
Codex-Skills AGENTS.md
Instructions for TheGoat395/Codex-Skills, covering repository operating notes, required checks, evidence rules and change hygiene.
claude-wp-builder CLAUDE.md
Instructions for yojahny55/claude-wp-builder, covering claude.md, what this repo is, testing, architecture and two independent i18n systems — do not mix them.
SoDam-Design-Kit AGENTS.md
Instructions for sodam-ai/SoDam-Design-Kit, covering sodam-design-kit — codex 규칙, 목표, 작업 순서 (고정), 절대 금지 and 완료 조건.
forthepeople CLAUDE.md
Claude Code instructions for jayanthmb14/forthepeople, covering claude.md — forthepeople.in project instructions, project, database schema changes (critical — changed june 2026), documentation location and completed prompts archive.
can-fed-camp-mcp AGENTS.md
AGENTS.md instructions for JCrossman/can-fed-camp-mcp: This repository is Open State: Camping — a local MCP that helps a citizen find and book Parks Canada campsites accessibly. It is an implementation of the Civic Access Protocol and conforms to The Open State Constitution…
groundtruth CLAUDE.md
Claude Code instructions for jackstewart254/groundtruth, a project described as: Assessing how well a place is actually served, from published sources. Data gathered by AI agents through the app's own MCP server. Layer one: policing.