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.
Borrowing it
Nothing to install: this file belongs to awslabs/AutoHelix. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/awslabs/AutoHelix/main/AGENTS.mdgit clone --depth 1 https://github.com/awslabs/AutoHelixWrote 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.
[](https://agentmods.dev/instructions/awslabs/autohelix/agents-md)<a href="https://agentmods.dev/instructions/awslabs/autohelix/agents-md"><img src="https://agentmods.dev/badge/instructions/awslabs/autohelix/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/awslabs/autohelix/agents-md"><img src="https://agentmods.dev/badge/instructions/awslabs/autohelix/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00286 | $0.00286 |
| Opus 5.5 | $0.00114 | $0.00114 |
| Sonnet 5.5 | $0.00057 | $0.00057 |
| Haiku 4.5 | $0.00029 | $0.00029 |
Grade A, and why
AutoHelix 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 1mo 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.
What it actually says
AGENTS.md
Guidance for AI coding agents working on the AutoHelix codebase. This mirrors
the conventions in CLAUDE.md — read that for full detail.
Quick orientation
- AutoHelix runs AI agents in an iterative optimization loop. Each iteration is
isolated in a git worktree, validated against constraints, and only merged when
it passes. Start in
src/autohelix/harness.py. - See
README.mdfor user-facing docs and the config reference.
Working rules
- Setup: activate the venv first (
source .venv/bin/activate). The package is an editable install — edits undersrc/autohelix/are live, no reinstall needed. - Test before you finish:
pytest(fast suite). Usepytest -m slowonly when a real agent is needed. - Do not commit optimized example code —
examples/must keep the slow baseline so users can see the optimization potential. - Don't break backward compatibility in config parsing: new config keys should be
optional and gated, so existing
autohelix.yamlfiles keep working.
For architecture notes, gotchas, and project layout, see CLAUDE.md.
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.
- 1mo ago First seen · 25 lines · 286 tokens per session scan A f0175d2d4797
AutoHelix AGENTS.md is an instructions file published in the GitHub repository awslabs/AutoHelix (32 stars, last pushed today), licensed Apache-2.0. It adds 286 tokens to every session, about $0.0011 per session on Opus 5.5. 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
runtm copilot-instructions.md
Copilot instructions for runtm-ai/runtm, covering runtm tool instructions, critical rules, structure, adding endpoints and app/api/v1/myendpoint.py.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.