ferrus: Instructions file for Codex

AGENTS.md

ferrus AGENTS.md is an instructions file for Codex, OpenCode from ferrus-dev/ferrus. It costs 4,698 tokens per session, scanned C, original, Apache-2.0.

Repository instructions for ferrus, a Rust program that coordinates software-development agents through planning, implementation, and review. It uses SQLite as its runtime source of truth and stores project run data in .ferrus files.

In plain words
What is it for?
Use it when working on ferrus, its command-line interface, agent workflow, MCP integration, or project documentation and code.
Why use it?
It clarifies which instructions control agent behavior, where project state lives, and which style rules apply. This helps avoid changing the wrong files or treating supporting files as the live state.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is ferrus-dev/ferrus's own configuration. It tells Codex and OpenCode how to work on ferrus 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 ferrus configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ferrus-dev/ferrus. 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/ferrus-dev/ferrus/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/ferrus-dev/ferrus

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 ferrus AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ferrus-dev/ferrus/agents-md/github.svg)](https://agentmods.dev/instructions/ferrus-dev/ferrus/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ferrus-dev/ferrus/agents-md"><img src="https://agentmods.dev/badge/instructions/ferrus-dev/ferrus/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.

agentmods 80×15 button for ferrus AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ferrus-dev/ferrus/agents-md"><img src="https://agentmods.dev/badge/instructions/ferrus-dev/ferrus/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,698 This file is loaded in full into every session.
When invoked 4,698 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.04698 $0.04698
Opus 5.5 $0.01879 $0.01879
Sonnet 5.5 $0.00940 $0.00940
Haiku 4.5 $0.00470 $0.00470

Measured 8d ago against content hash 50fc93f775c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

ferrus AGENTS.md scanned grade C with 1 finding 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- ferrus-executor-instructions -->
AGENTS.md · 359 lines

How it starts

The opening of the file, as written. The whole thing — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Coding guidance for AI agents working in this repository.

Project

ferrus is a Rust AI agent orchestrator for software projects. It drives a Supervisor-Executor workflow: the Supervisor plans tasks and reviews submissions, while the Executor implements and checks its own work. SQLite is the runtime source of truth. Project-local .ferrus/ files contain templates, task intent, scoped run artifacts, agent registry data, and logs; they are not a mirrored state machine. Agents coordinate through native tools or MCP.

Licensed under Apache 2.0.

Runtime behavior for a Ferrus-managed agent is defined by its initial prompt and exposed Ferrus tools. This file is supporting context and must not override them. Read .agents/skills/ferrus/SKILL.md for the current Ferrus CLI, MCP tools, resources, state machine, and artifact layout.

Characters

Write documentation and code using only characters found on a US layout keyboard. Avoid special punctuation such as em dashes, Unicode arrows, or single-character ellipses. Use their plain-ASCII equivalents instead:

  • Use - or -- instead of an em dash.
  • Use -> or <- instead of a Unicode arrow.
  • Use ... (three periods) instead of a single ellipsis character.

Keep punctuation plain ASCII.

Intentional Unicode test fixtures and terminal UI glyph tables are exceptions when the characters themselves are the behavior under test or part of the rendered interface.

Code Style

  • Do not call unwrap() or expect() outside tests. Propagate errors, handle missing values explicitly, or model invariants so invalid states cannot be constructed. Clippy enforces this rule; do not replace these calls with panic-based equivalents or suppress the lints to bypass it.
  • Separate functions, methods, type declarations, and distinct logical steps with one blank line. Keep closely related statements together when they form one operation; avoid adding blank lines inside compact expressions or between every statement. Keep related mod/pub mod declarations together without blank lines, like use imports.
  • Keep Rust source files at or below 1000 lines, including tests. Split larger modules by responsibility into focused submodules, preserving visibility and behavior. Do not use include! or arbitrary numbered chunks to work around the limit.

Read the full file on GitHub · 359 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. 8d ago Changed · +15 lines · +218 tokens per session 50fc93f775c9
  2. 12d ago Changed · +4 lines · +92 tokens per session 085e595c0804
  3. 14d ago Changed · +1 lines · +31 tokens per session 3be7120fbe03
  4. 19d ago Changed · +3 lines · +54 tokens per session 13641c2ab321
  5. 21d ago Changed · +1 lines · +19 tokens per session a3a4f5bab2ef
  6. 27d ago Changed · +2 lines · +45 tokens per session 9e979d07eea0
  7. 28d ago Changed · +8 lines · +110 tokens per session a29e47e89b1c
  8. 2mo ago Changed · +12 lines · +263 tokens per session e1c524fbd865
  9. 2mo ago Changed · +88 lines · +1,348 tokens per session b0eab33ccecd
  10. 2mo ago First seen · 225 lines · 2,518 tokens per session scan C 7a98b4bb0aa1

Subscribe to this mod's changes

ferrus AGENTS.md is an instructions file published in the GitHub repository ferrus-dev/ferrus (2 stars, last pushed 7d ago), licensed Apache-2.0. It adds 4,698 tokens to every session, about $0.0188 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

ferrus AGENTS.md compared with instructions from other repositories

ferrus AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ferrus AGENTS.mdferrus-dev/ferrusInstructions file27d agoApache-2.0C4,698Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode