AutoAgents AGENTS.md

Repository guidelines for AutoAgents, a Rust project made of libraries, examples, documentation, and sample machine-learning models. They define the folder structure, naming style, error handling, logging, and testing expectations.

In plain words
What is it for?
Use it when adding or changing Rust crates, examples, tests, documentation, or shared AutoAgents components.
Why use it?
They help an agent place code correctly and follow the project's rules for readable names, useful errors, and safe library behavior.

Instructions file for CodexOpenCode

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/liquidos-ai/autoagents/agents-md
Clone the repo
git clone --depth 1 https://github.com/liquidos-ai/AutoAgents

Made for: Codex, OpenCode.

Per session 880 This file is loaded in full into every session.
When invoked 880 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 $0.00880 $0.00880
Opus 5 $0.00440 $0.00440
Sonnet 5 $0.00176 $0.00176
Haiku 4.5 $0.00088 $0.00088

Measured 3d ago against content hash c9c7ac436e9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AutoAgents 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 · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AutoAgents Repository Guidelines

Project Structure & Module Organization

  • Workspace layout: crates/* (core libraries), examples/* (runnable crates), docs/ (documentation), assets/ (images), demo_models/ (sample models).
  • Key crates: autoagents (entry), autoagents-core, autoagents-llm, autoagents-derive, autoagents-toolkit.
  • Tests live alongside code (mod tests) and as integration tests under each crate’s tests/.

Code Quality

  • Code should be production ready and modular
  • Should not implement half baked work or TODO.
  • The code whould be fully functional

Naming conventions

  • snake_case for functions, variables, modules.
  • CamelCase for types, traits, enums.
  • SCREAMING_SNAKE_CASE for constants.
  • Use descriptive, domain-focused names; avoid abbreviations.

Error handling

  • Propagate errors with ? and define meaningful error types.
  • Add context to errors when it helps debugging.
  • Avoid panics in library code; in binaries, panic only for truly fatal states.

Logging and diagnostics

  • Use structured logging when a logging crate is introduced.
  • Do not print with println! in library code; reserve for examples or CLI output.

Build, Test, and Development Commands

  • Build workspace: cargo build --workspace --features full
  • Lint: cargo clippy --all-features --all-targets -- -D warnings
  • Format: cargo fmt --all
  • Test fast (CI-like): cargo test --workspace --features default --exclude autoagents-burn --exclude autoagents-mistral-rs --exclude wasm_agent
  • Docs: cargo doc --all-features --no-deps
  • Run examples: cargo run -p basic-example or cargo run -p coding_agent
  • Git hooks: install once with lefthook install; run locally via lefthook run pre-commit

Testing Guidelines

  • Use Rust’s built-in test harness; async tests with #[tokio::test] where needed.
  • Place integration tests in crates/<name>/tests/ with descriptive snake_case filenames.
  • Coverage (optional): cargo install cargo-tarpaulin && cargo tarpaulin --all-features --out html.

Read the full file on GitHub · 70 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 · 70 lines · 880 tokens per session scan A c9c7ac436e9b

Subscribe to this mod's changes

AutoAgents AGENTS.md is an instructions file published in the GitHub repository liquidos-ai/AutoAgents (744 stars, last pushed 7d ago), licensed Apache-2.0. It adds 880 tokens to every session, about $0.0044 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 2026-08-30.