Borrowing it
Nothing to install: this file belongs to Dhi13man/oorep-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Dhi13man/oorep-mcp/master/AGENTS.mdgit clone --depth 1 https://github.com/Dhi13man/oorep-mcpWrote 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/dhi13man/oorep-mcp/agents-md)<a href="https://agentmods.dev/instructions/dhi13man/oorep-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/dhi13man/oorep-mcp/agents-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 5.1 | $0.00917 | $0.00917 |
| Opus 5 | $0.00458 | $0.00458 |
| Sonnet 5 | $0.00183 | $0.00183 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
oorep-mcp 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 8d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Operating Manual — OOREP MCP
This repository hosts the implementation of oorep-mcp, a Model Context Protocol (MCP) server that exposes OOREP’s repertory and materia medica search endpoints as structured MCP tools. Follow the guidance below whenever you work in this project.
Mission & Scope
- Build and maintain an open, publishable MCP server that lets any MCP-enabled client query OOREP (remote or self-hosted) safely and efficiently.
- Initial scope is read-only and anonymous: list repertories/materia medicas/remedies and search them. Secure
/api/sec/...endpoints will be treated as future/advanced work. - Favor TypeScript and the official
@modelcontextprotocol/sdkfor the server implementation, exposing the functionality over stdio.
Core Workflow
-
Perceive
- Understand the requested change or question and review relevant code/docs first.
- Prefer referencing existing plans (see
README.md, design docs, or issue notes) before inventing new approaches. - Ask at most 3 clarifying questions if blockers arise.
-
Plan
- Break tasks into concrete subtasks before editing.
- For anything beyond a trivial tweak, produce a multi-step plan (use the planning tool if applicable).
- When creating new MCP tools/endpoints, start from the functional contract (inputs/outputs) before writing code.
-
Act
- Implement smallest viable increments with clear commits.
- Mirror OOREP’s existing API semantics (see
README.mdsummary) and keep schemas LLM-friendly. - Default to TypeScript, zod-style validation, and async/await for HTTP calls.
-
Check
- Add/adjust tests when behavior changes; smoke-test against a local OOREP Docker stack when feasible.
- Run
npm run lint/npm run testonce they exist. - Verify formatting (Prettier/ESLint once configured).
-
Reflect
- Summarize what changed and why in responses/PRs.
- Call out follow-ups or risks (rate limiting, schema changes upstream, auth assumptions).
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.
- 8d ago First seen · 77 lines · 917 tokens per session scan A 3d1da1a1364d
oorep-mcp AGENTS.md is an instructions file published in the GitHub repository Dhi13man/oorep-mcp (3 stars, last pushed yesterday), licensed MIT. It adds 917 tokens to every session, about $0.0046 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.