raven-mcp: Instructions file for Codex

AGENTS.md

raven-mcp AGENTS.md is an instructions file for Codex, OpenCode from rhinocap/raven-mcp. It costs 1,106 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for an MCP project whose visual decisions are stored in a shared decision graph. The graph records agreed choices about the interface, such as colors, spacing, layout, motion, and component structure.

In plain words
What is it for?
Use it before changing the interface or making visual decisions, so the agent can check the relevant design rulings and apply them.
Why use it?
It prevents an agent from accidentally contradicting decisions that the team has already made about how the product should look and behave.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is rhinocap/raven-mcp's own configuration. It tells Codex and OpenCode how to work on raven-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything raven-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rhinocap/raven-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.

Copy the file
curl -O https://raw.githubusercontent.com/rhinocap/raven-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/rhinocap/raven-mcp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for raven-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rhinocap/raven-mcp/agents-md.svg)](https://agentmods.dev/instructions/rhinocap/raven-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/rhinocap/raven-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/rhinocap/raven-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,106 This file is loaded in full into every session.
When invoked 1,106 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01106 $0.01106
Opus 5 $0.00553 $0.00553
Sonnet 5 $0.00221 $0.00221
Haiku 4.5 $0.00111 $0.00111

Measured 7d ago against content hash aa9ee1be2a5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

raven-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 7d 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.

AGENTS.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design decisions

This repo keeps its design intent — the resolved rulings on how the UI should look and behave — in a shared decision graph under .raven/decisions/. It is the source of truth for design choices; a teammate or a prior agent already settled these, and they outrank your defaults.

Before you choose or change anything visual — color, type, spacing, layout, motion, component structure, interaction — consult it first:

node scripts/consult.mjs <query>

Pass a term for the choice you're about to make (e.g. color, spacing, motion, layout). It returns the active decisions that apply. Follow them. If a decision conflicts with what you were about to do, the decision wins; if you believe it's wrong, say so rather than silently overriding it.

If nothing matches your query, proceed on your own judgment — there's no ruling yet.

Target customer (customer-lens-kickoff, 2026-07-09; evolved 2026-07-12)

Strategic evolution (Andrew, 2026-07-12; boundary clarified 2026-07-18): the TEAM is now the primary customer. The team paid service is Morven, a separate superset product (all of Raven is in Morven; not all of Morven is in Raven) — Raven itself stays the free open-source tier serving the solo indie dev forever. Judge new features through the team lens first (shared workflows, multi-user consent, admin approval, org data handling), while never regressing the indie dev's free "under a minute" path. New-feature kickoffs default to asking the delta question against BOTH lenses.

Primary lens — the paying team (2026-07-12)

  • We are a product/design team (designers + engineers) with an existing design practice and shared tooling (Slack, Figma, a design system in some state of maturity)
  • We are trying to make our design decisions, taste, and system knowledge durable and enforceable across people and AI agents
  • But our decisions live scattered in Slack threads, meeting notes, and heads — they get re-litigated and lost
  • Because no tool maintains a living, queryable decision/taste graph that both humans and coding agents consult
  • Which makes us feel like we're paying a coordination tax on every project
  • Meets the product: via a team member (often the indie-dev free user) advocating internally; evaluated with IT/admin approval, procurement, and data-handling questions in the room
  • Bounces on: anything requiring broad data access without clear consent controls, unclear data retention/LLM handling, per-seat pricing with no obvious team-level win over the free tier

Read the full file on GitHub · 51 lines

Changes

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.

  1. 7d ago First seen · 51 lines · 1,106 tokens per session scan A aa9ee1be2a5f

Subscribe to this mod's changes

raven-mcp AGENTS.md is an instructions file published in the GitHub repository rhinocap/raven-mcp (6 stars, last pushed 14d ago), licensed Apache-2.0. It adds 1,106 tokens to every session, about $0.0055 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.

Related

Other instructions, from other repositories

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens