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.
npx agentmods add instructions/ferrus-dev/ferrus/agents-mdgit clone --depth 1 https://github.com/ferrus-dev/ferrusWhat 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 | $0.02518 | $0.02518 |
| Opus 5 | $0.01259 | $0.01259 |
| Sonnet 5 | $0.00504 | $0.00504 |
| Haiku 4.5 | $0.00252 | $0.00252 |
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 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.
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 --> How it starts
The opening of the file, as written. The whole thing — 225 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. Coordination uses MCP as an
implementation detail.
Licensed under Apache 2.0.
Runtime behavior for a Ferrus-managed agent is defined by its initial prompt and exposed MCP
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.
Use em dashes sparingly.
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.
Build and Test
cargo build # compile
cargo build --release # optimized build
cargo test # run all tests
cargo test <name> # run a single test by name
cargo clippy -- -D warnings # lint (warnings are errors)
cargo fmt # format
cargo fmt --check # check formatting without writing
cargo check # fast type-check
Before submitting, cargo clippy -- -D warnings, cargo fmt --check, and cargo test must
all pass.
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 First seen · 225 lines · 2,518 tokens per session scan C 7a98b4bb0aa1
ferrus AGENTS.md is an instructions file published in the GitHub repository ferrus-dev/ferrus (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 2,518 tokens to every session, about $0.0126 per session on Opus 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.
Other instructions, from other repositories
kungfu copilot-instructions.md
Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.
sofagent GEMINI.md
Instructions for KongFangXun/sofagent, covering gemini.md · sofagent gemini cli 适配(薄挂载), 会话开始时按序加载(四层加载链), 审计强制(平台无关) and 连接 mcp server.
agents CLAUDE.md
Instructions for eloylp/agents, covering claude.md, project overview, directory structure, config model and build & run.
growmos AGENTS.md
Instructions for codician-team/growmos: This repository keeps a knowledge graph in .growmos/ (entities, typed relations, provenance, profiles, a journal). It is the shared world model that survives context windows. Treat it as memory you read at the start of work and write to as you develop. Zero-config commands.
ideate AGENTS.md
Instructions for paultyng/ideate, covering agents.md, build features as mcp tools first, ui second, when to add ui and pattern.
omk CLAUDE.md
Claude Code instructions for dmae97/omk, covering claude.md, precedence (read this first), omk runtime map (what you're operating inside), this repo: open-multi-agent-kit / omk monorepo and build / test / check commands.