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.
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 skills/awslabs/autohelix/workflow-optimizationnpx skills add awslabs/AutoHelix --skill workflow-optimizationgit 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/skills/awslabs/autohelix/workflow-optimization)<a href="https://agentmods.dev/skills/awslabs/autohelix/workflow-optimization"><img src="https://agentmods.dev/badge/skills/awslabs/autohelix/workflow-optimization.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00073 |
| Opus 5 | $0.00000 | $0.00036 |
| Sonnet 5 | $0.00000 | $0.00015 |
| Haiku 4.5 | $0.00000 | $0.00007 |
Grade A, and why
workflow-optimization 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.
What it actually says
Order request decisions
Read the customer request, account record, and supplied policies before choosing an action. Policy overrides the customer's requested remedy.
Return one supported action with the policy reason that justifies it. Do not invent facts, actions, or reason codes. Escalate when policy requires human review rather than attempting a monetary or inventory action.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 9 lines · 0 tokens per session scan A 1d94efd91c22
workflow-optimization is a skill published in the GitHub repository awslabs/AutoHelix (20 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 73 tokens. 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 2026-09-04.
Other skills, from other repositories
build-monetized-app
Use when the task is building a new app on Eliza Cloud that earns money — chat apps, agent apps, MCP-backed tools, anything that calls the cloud's chat/messages/inference endpoints on behalf of users. Covers app registration, container deploy, markup configuration, affiliate header, app charge requests, x402 payment…
eliza-cloud-buy-domain
Use whenever a user wants to register or buy a custom domain for an Eliza Cloud app — including in the same request as building the app ("build me X and put it on Y.com"). Uses Cloudflare as registrar after explicit user confirmation, paid from the user's existing cloud credit balance. Pairs with build-monetized-app…
ordercli
Foodora CLI for checking past orders and active order status. Use when the user asks to check food delivery orders, track a Foodora delivery, view order history, reorder a meal, look up past food orders, check delivery status, or manage Foodora sessions and authentication.
returns-policy
Answer return, refund, and warranty questions for electronics. Use when the user mentions returns, refunds, RMAs, warranty coverage, damaged items, or opened packaging.
integrations
One-request, complete setup of external services — payment (Stripe, PromptPay, Omise, 2C2P), email, auth, analytics, storage and other integrations, including Thai-market services. Installs SDKs, creates API routes, env templates, and UI components in one pass. Use when the user asks to add payments, email, login…
reconcile-shelf
Check the shelf against the returns that were approved, and report what is missing.