agentmods.dev

raven AGENTS.md

raven AGENTS.md is an instructions file for Codex, OpenCode from giggsoinc/raven. It costs 999 tokens per session, scanned A, original, MIT.

Repository instructions for Raven, a project assistant that loads rules and selected memory at the start of a coding session. They define required startup scripts and how later sessions should behave.

In plain words
What is it for?
Use them when working in the Raven repository to boot the assistant, record each prompt, load permitted memory, and choose the expected work route.
Why use it?
They make the assistant's startup process consistent and prevent it from skipping required logs, rules, or stored context.

Instructions file for CodexOpenCode

Installs and runs on its own, but its text points at files inside the plugin that ships it — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed.

not rated 5 2d ago A scan 999 tokens original MIT
View the source file giggsoinc/raven
Install

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.

agentmods
npx agentmods add instructions/giggsoinc/raven/agents-md
Clone the repo
git clone --depth 1 https://github.com/giggsoinc/raven

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 AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/giggsoinc/raven/agents-md.svg)](https://agentmods.dev/instructions/giggsoinc/raven/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/giggsoinc/raven/agents-md"><img src="https://agentmods.dev/badge/instructions/giggsoinc/raven/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 999 This file is loaded in full into every session.
When invoked 999 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00999 $0.00999
Opus 5 $0.00500 $0.00500
Sonnet 5 $0.00200 $0.00200
Haiku 4.5 $0.00100 $0.00100

Measured 3d ago against content hash 79705bb7133c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

AGENTS.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Grok / Codex / Cursor boot

Codex also reads AGENTS.override.md first (same directory). Do not skip it.

First load (same UX every IDE)

  1. python3 scripts/ops/raven-first.py --boot (rebuild + open once). Fallback: python3 "${CLAUDE_PLUGIN_ROOT}/scripts/ops/raven-first.py" --boot. Print host= rules= memory= load= educate= route= expected_route= first_load=.
  2. If load=1, Read only the memory= card. If load=0, no vault, no invented memory.
  3. python3 scripts/ops/raven-first.py --session-start — print that banner (version, host, rules, educate, expected SIMPLE/MEDIUM/COMPLEX).
  4. Later turns: do not re-open the dashboard unless they ask (raven dashboard / /raven-dashboard → ide-boot.py --open).

0. BEFORE any answer or tool — every user turn. No exemptions.

  • Run python3 scripts/ops/raven-first.py --prompt "<their full message>" first. Fallback: python3 "${CLAUDE_PLUGIN_ROOT}/scripts/ops/raven-first.py" --prompt "<their full message>". That write fills dashboard Logs. Skipping it leaves Logs empty for this IDE.
  • Do not lead with bash scripts/raven-python.sh as the only path — Codex in a public app repo often has no wrapper until raven-first copies the engine from the plugin root.
  • There is no “direct path” that skips this. Not git log, git status, “what shipped”, smoke tests, or “I didn’t need the router.” Claude PreToolUse denies other tools without .raven/.route-stamp. Codex/Cursor/AntiGravity/Grok have no that hook — empty dashboard Logs = you skipped. That is the proof, not a design exemption.
  • Line 1 = printed 🔀 Router · …
  • Line 2 = printed 💰 total-cost= last_turn= est=
  • Line 3 = printed educate= guided|off and expected=<recommend model>
  • Line 4 = session=<the model writing this>
  • Line 5 = Intent: plan|debug|direct — {why}
  • Then tools/answer. Spawn SIMPLE-tier if this IDE can. Do not only print the toast.
  • Recap: python3 scripts/ops/raven-first.py --end → 💰 turn= total-cost= (or ? if Stop has not priced yet).

Read the full file on GitHub · 34 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. 3d ago First seen · 34 lines · 999 tokens per session scan A 79705bb7133c

Subscribe to this mod's changes

raven AGENTS.md is an instructions file published in the GitHub repository giggsoinc/raven (5 stars, last pushed 2d ago), licensed MIT. It adds 999 tokens to every session, about $0.0050 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.

Design and UXFrontend
Related

Other instructions, from other repositories

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

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

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

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 · 4,345 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

next.js 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