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/liquidos-ai/autoagents/agents-mdgit clone --depth 1 https://github.com/liquidos-ai/AutoAgentsWhat 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 | $0.00880 | $0.00880 |
| Opus 5 | $0.00440 | $0.00440 |
| Sonnet 5 | $0.00176 | $0.00176 |
| Haiku 4.5 | $0.00088 | $0.00088 |
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.
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’stests/.
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_casefor functions, variables, modules.CamelCasefor types, traits, enums.SCREAMING_SNAKE_CASEfor 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-exampleorcargo run -p coding_agent - Git hooks: install once with
lefthook install; run locally vialefthook 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 descriptivesnake_casefilenames. - Coverage (optional):
cargo install cargo-tarpaulin && cargo tarpaulin --all-features --out html.
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.
- 3d ago First seen · 70 lines · 880 tokens per session scan A c9c7ac436e9b
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.
Other instructions, from other repositories
timbal CLAUDE.md
Instructions for timbal-ai/timbal, covering claude.md, commands, development and testing, benchmarks and repository layout.
typedai AGENTS.md
Instructions for TrafficGuard/typedai, covering general code standards, clean code style guidelines, example, original code and analysis.
sublayer CLAUDE.md
Instructions for sublayerapp/sublayer, covering claude.md, project overview, development commands, setup and testing.
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
claude-code-karma CLAUDE.md
Instructions for JayantDevkar/claude-code-karma, covering claude.md, project overview, quick start, clone (no submodule init needed — this is a monorepo) and start api (terminal 1).
hatch3r CLAUDE.md
Instructions for hatch3r/hatch3r, covering hatch3r — development instructions, architecture, development commands, two-axis pillar framework (2.0.0) and orchestrator self-discipline (bypass protection).