autoany CLAUDE.md

autoany CLAUDE.md is an instructions file for coding agents from broomva/autoany. It costs 512 tokens per session, scanned A, original, MIT.

A Python skill and Rust-based framework for designing and running agent systems. Its components include a core execution engine, persistence and runtime adapters, examples and automated checks.

In plain words
What is it for?
It is for building EGRI-based agent systems, running the Rust and Python checks, and testing separate adapters such as the Arcan runtime and Lago persistence connector.
Why use it?
It gives projects a defined structure for coordinating agent loops, recording trials and testing the supporting code.

Instructions file

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/broomva/autoany/claude-md
Clone the repo
git clone --depth 1 https://github.com/broomva/autoany

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 autoany CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/broomva/autoany/claude-md.svg)](https://agentmods.dev/instructions/broomva/autoany/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/broomva/autoany/claude-md"><img src="https://agentmods.dev/badge/instructions/broomva/autoany/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 512 This file is loaded in full into every session.
When invoked 512 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 $0.00512 $0.00512
Opus 5 $0.00256 $0.00256
Sonnet 5 $0.00102 $0.00102
Haiku 4.5 $0.00051 $0.00051

Measured 3d ago against content hash 369a8254dc9c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

autoany CLAUDE.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.

CLAUDE.md · 54 lines

What it actually says

Autoany — EGRI Framework

Project Structure

  • autoany/ — Agent skill (Python): problem compilation, scaffolding, EGRI doctrine
  • autoany-core/ — Rust microkernel: loop orchestrator, traits, ledger, budget, promotion
    • New: dead_ends.rs, stagnation.rs, strategy.rs, inheritance.rs
  • autoany-aios/ — Arcan runtime adapter: EGRI execution via Arcan HTTP sessions
  • autoany-lago/ — Lago persistence adapter: EGRI trials as EventKind::Custom with "egri." prefix
  • examples/ — End-to-end demos (ticket-classifier)

Commands

make check       # Lint + format check (Rust clippy + fmt, Python ruff)
make test        # Run all tests (Rust + Python)
make build       # Build Rust crate
make smoke       # Quick validation: build + check + test
make fmt         # Auto-format all code

# Adapter crates (standalone, not in workspace)
cd autoany-aios && cargo test    # 9 tests
cd autoany-lago && cargo test    # 10 tests

Architecture Rules

  1. Skill = compilerautoany/ teaches agents to design EGRI systems
  2. Core = microkernelautoany-core/ is domain-agnostic loop substrate
  3. Instance = generated — domain logic lives in user projects, not in core
  4. Never add domain-specific logic to autoany-core/
  5. All trait implementations belong in user crates or examples/

Rust Conventions

  • Edition 2024
  • All public items must have doc comments
  • cargo clippy -- -D warnings must pass
  • cargo fmt --check must pass
  • Integration tests in tests/, unit tests inline with #[cfg(test)]

Python Conventions

  • Scripts must support --help and output JSON to stdout
  • No external dependencies in skill scripts (stdlib only)

EGRI Safety Laws (enforced in code)

  1. Never mutate evaluator and artifact in the same trial
  2. Never promote without constraint checks
  3. Budget fails closed — no "one more try"
  4. Rollback must always be available
  5. Every trial is logged to the ledger
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 · 54 lines · 512 tokens per session scan A 369a8254dc9c

Subscribe to this mod's changes

autoany CLAUDE.md is an instructions file published in the GitHub repository broomva/autoany (2 stars, last pushed 4mo ago), licensed MIT. It adds 512 tokens to every session, about $0.0026 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.