agentmods.dev

AutoHelix CLAUDE.md

AutoHelix CLAUDE.md is an instructions file for coding agents from awslabs/AutoHelix. It costs 1,370 tokens per session, scanned A, original, Apache-2.0.

Project instructions for developing AutoHelix, a tool that repeatedly asks AI agents to improve code in isolated Git worktrees and merges only validated results.

In plain words
What is it for?
Setting up the development environment, navigating AutoHelix's source code, running its command-line workflow, and testing changes.
Why use it?
They give agents the setup commands, code locations, available commands, and testing expectations needed to work safely in the project.

Instructions file

not rated 20 +1 changed yesterday A scan 1,370 tokens original Apache-2.0
View the source file awslabs/AutoHelix
About the project

AutoHelix is a harness that lets an AI agent repeatedly propose changes toward a measurable goal while checks decide which changes are accepted. It is for tasks such as code optimization or model training where constraints, metrics, file scope, isolation, and budgets need to be controlled. Its catalogue contains instructions and a skill for running the improvement loop.

awslabs/AutoHelix · 20 stars · on GitHub

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/awslabs/autohelix/claude-md
Clone the repo
git clone --depth 1 https://github.com/awslabs/AutoHelix

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 AutoHelix CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/awslabs/autohelix/claude-md.svg)](https://agentmods.dev/instructions/awslabs/autohelix/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/awslabs/autohelix/claude-md"><img src="https://agentmods.dev/badge/instructions/awslabs/autohelix/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,370 This file is loaded in full into every session.
When invoked 1,370 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 $0.01370 $0.01370
Opus 5 $0.00685 $0.00685
Sonnet 5 $0.00274 $0.00274
Haiku 4.5 $0.00137 $0.00137

Measured yesterday against content hash ffbe5d1b43c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AutoHelix 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 yesterday.

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 · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AutoHelix Development

AutoHelix is an agent-powered iterative optimization tool. It runs AI agents in a loop — each iteration is isolated in a git worktree, validated, and only merged when it passes. See README.md for user-facing docs. For setting up training/eval (ML benchmark) cells, see docs/ml-experiments.md.

Setup

Activate the virtual environment before running any commands:

source .venv/bin/activate

If the venv doesn't exist yet:

uv venv
source .venv/bin/activate
uv pip install -e ".[dev]"

Project Layout

  • src/autohelix/harness.py - main iteration loop (start here)
  • src/autohelix/cli.py - CLI commands (init, run, clear, watch, report)
  • src/autohelix/config.py - configuration dataclasses and parsing
  • src/autohelix/agents/ - agent backends (claudecode, codex, opencode, mock)
  • src/autohelix/sandbox.py - git worktree management and scope enforcement
  • src/autohelix/checks.py - constraint and metric execution
  • src/autohelix/history.py - iteration history (JSONL)
  • src/autohelix/display.py - live Rich display
  • src/autohelix/prompt_template.py - agent prompt rendering
  • tests/ - test suite (pytest)
  • examples/ - example projects (sorting, ml-recipe, writing, task-queue, research, workflow-optimization, algotune, posttrain, kernelbench, nested-autohelix)
  • scripts/run_dev_test.sh - quick real-agent test against a bundled example (supports --parallel N)
  • docs/ - user-facing documentation (plain markdown)

CLI Commands

autohelix init         # Initialize project (creates .autohelix/ and config template)
autohelix run          # Start or resume optimization loop
autohelix parallel     # Run multiple workers in parallel on the same goal
autohelix clear        # Archive state, start fresh
autohelix watch        # Live-tail agent output (second terminal)
autohelix hint         # Send a hint to the running agent (picked up next iteration)
autohelix report       # Agent-written analysis of the run

Read the full file on GitHub · 83 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. yesterday Changed · +2 lines · +13 tokens per session ffbe5d1b43c1
  2. 5d ago First seen · 81 lines · 1,357 tokens per session scan A e854c9409d96

Subscribe to this mod's changes

AutoHelix CLAUDE.md is an instructions file published in the GitHub repository awslabs/AutoHelix (20 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,370 tokens to every session, about $0.0068 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.

agenticai-agentsautomationclaudecode-optimizationdeveloper-tools
Related

Other instructions, from other repositories

html-anything AGENTS.md

AGENTS.md instructions for nexu-io/html-anything, covering this is not the next.js you know, workspace shape and commands.

nexu-io/html-anything · 386 tokens

codex-autoresearch AGENTS.md

Instructions for TheGreenCedar/codex-autoresearch, covering agents.md, purpose and scope, canonical sources, stable product boundaries and source and package boundaries.

TheGreenCedar/codex-autoresearch · 2,034 tokens

framework AGENTS.md

AGENTS.md instructions for ai-driven-dev/framework, covering agents.md, behavior, communication, action and memory management.

ai-driven-dev/framework · 825 tokens

platform CLAUDE.md

Claude Code instructions for ambient-code/platform, covering ambient code platform, structure, key files, session flow and commands.

ambient-code/platform · 2,307 tokens

toh-framework CLAUDE.md

Claude Code instructions for wasintoh/toh-framework, covering claude.md — toh framework (repo development guide), what this is, everyday commands, verification protocol and single source, transformed per ide.

wasintoh/toh-framework · 3,979 tokens

jentic-one GEMINI.md

Gemini CLI instructions for jentic/jentic-one: Otherwise, read AGENTS.md — this repo's canonical agent guidance.

jentic/jentic-one · 51 tokens