Raven is an open-source agent harness for running long-term AI work with terminal execution, tracing, memory, skills, evaluation, and reusable workflows. People use the current release to operate and improve persistent AI workflows, while its described future direction is a multi-agent system that combines specialized harnesses.
Borrowing it
Nothing to install: this file belongs to EverMind-AI/Raven. 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/EverMind-AI/Raven/main/AGENTS.mdgit clone --depth 1 https://github.com/EverMind-AI/RavenWrote 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/evermind-ai/raven/agents-md)<a href="https://agentmods.dev/instructions/evermind-ai/raven/agents-md"><img src="https://agentmods.dev/badge/instructions/evermind-ai/raven/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/evermind-ai/raven/agents-md"><img src="https://agentmods.dev/badge/instructions/evermind-ai/raven/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.05914 | $0.05914 |
| Opus 5.5 | $0.02366 | $0.02366 |
| Sonnet 5.5 | $0.01183 | $0.01183 |
| Haiku 4.5 | $0.00591 | $0.00591 |
Grade A, and why
Raven 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 2d 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 — 427 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Raven AI-collaboration spec. Read this file before making any code change in this repo.
Scope: Codex / Claude Code / Claude API / any AI-assisted work. When a rule here conflicts with an ad-hoc instruction in conversation, this file wins — unless the user explicitly says "ignore rule X in AGENTS.md".
Hard constraints only (violations get reverted / rejected). Soft suggestions and style preferences belong in personal notes or conversation, not here. See the Maintenance note before adding sections — shorter is better.
| # | Section | Gist |
|---|---|---|
| 1 | Code comments | Don't comment unless necessary; source in English (named exemption zones) |
| 2 | Branch naming | <type>/<snake_desc>; confirm base before cutting |
| 3 | Commits | Conventional Commits, all-English, Co-authored-by trailer |
| 4 | Dependencies | uv only — never pip / hand-edit lockfile |
| 5 | Tests | uv run pytest; strict file-naming |
| 6 | Domain terms | Consult CONTEXT-MAP.md before naming; use canonical terms |
| 7 | Repository assets | No report assets, web artifacts, or large files in PRs |
1. Code comments
§1.1 Top rule: don't add comments unless necessary
- Every new code file must document its purpose in English with an appropriate module docstring or equivalent file-level documentation. Inline comments still follow the necessity rules below.
- Match the style of surrounding lines. If neighboring code has no comments, don't add one to your new line.
- Comment only when:
- the logic is non-obvious;
- there's a hidden constraint (e.g. call-order sensitivity, a caller must do X first);
- you need to explain why, not what (the name already says what).
- Don't add comments that:
- describe what the code does (
# Increment counternext tocounter += 1); - mark edits (
# ← new/# changed this line); - reference a PR / Issue / locally-visible-only doc path (
# Refs: ...— invisible to others); - describe transient task context (
# For the X bug— stale once the task is done).
- describe what the code does (
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.
- 2d ago Changed · +1 lines · -58 tokens per session 2edc925b8135
- 1mo ago Changed · +12 lines · +205 tokens per session 28ddc5af6aec
- 1mo ago Changed · +3 lines · +60 tokens per session 8fbda536c7f5
- 1mo ago Changed · +35 lines · +829 tokens per session a37b56493a29
- 2mo ago First seen · 376 lines · 4,878 tokens per session scan A 3606e3db3b29
Raven AGENTS.md is an instructions file published in the GitHub repository EverMind-AI/Raven (6,047 stars, last pushed today), licensed Apache-2.0. It adds 5,914 tokens to every session, about $0.0237 per session on Opus 5.5. 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 2026-08-30.
Raven AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Raven AGENTS.mdEverMind-AI/Raven | Instructions file | 6.0k | today | Apache-2.0 | A | 5,914 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |