create

A command for creating an OpenHands automation, which is a scheduled task run by the OpenHands service. It guides you through the automation's name, instructions, schedule, timezone, and optional timeout.

In plain words
What is it for?
Use it to create recurring OpenHands tasks, such as running an instruction on a cron schedule—a time pattern like every Monday at 9 AM UTC.
Why use it?
It removes the need to build a custom API script just to schedule an automated job. It also helps collect the settings required to create the job.

Command

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 commands/openhands/extensions/create
Clone the repo
git clone --depth 1 https://github.com/OpenHands/extensions
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 570 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00009 $0.00570
Opus 5 $0.00005 $0.00285
Sonnet 5 $0.00002 $0.00114
Haiku 4.5 $0.00001 $0.00057

Measured 2d ago against content hash 955be0d35fd5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

allowed-tools: Bash(curl:*), Bash(cat:*), Bash(echo:*), Bash(jq:*)
plugins/openhands/commands/create.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create OpenHands Automation

Guide the user through creating a new automation interactively.

API Base URL: https://app.all-hands.dev/api/automation/v1

Full API Reference: See skills/openhands-automation/SKILL.md for complete documentation.

⚠️ CRITICAL: Always use the preset/prompt endpoint to create automations. Do NOT write custom SDK scripts or create tarballs unless the user explicitly requests it. If the prompt approach cannot meet the user's needs, explain the available options and let them choose.

Workflow

Step 1: Understand What the User Wants

Ask the user to describe what the automation should do. In most cases, the user's description can be used directly as the prompt for the preset endpoint.

Step 2: Collect Required Fields

  1. Name: Descriptive name for the automation (1-500 characters)
  2. Prompt: What the automation should do — use the user's description
  3. Cron Schedule: e.g., 0 9 * * 1 (Mondays at 9 AM UTC)
  4. Timezone (optional): IANA timezone (default: UTC)
  5. Timeout (optional): Max execution time in seconds

Step 3: Create the Automation

curl -X POST "https://app.all-hands.dev/api/automation/v1/preset/prompt" \
  -H "Authorization: Bearer ${OPENHANDS_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "USER_PROVIDED_NAME",
    "prompt": "USER_PROVIDED_DESCRIPTION_OF_WHAT_TO_DO",
    "trigger": {
      "type": "cron",
      "schedule": "USER_PROVIDED_SCHEDULE",
      "timezone": "USER_PROVIDED_TIMEZONE_OR_UTC"
    }
  }'

Step 4: Present Result

On success (HTTP 201): Show automation ID, name, schedule, and status.

On error: Show the error message from the API response.

If the Preset Is Not Enough

If the user needs custom dependencies, a non-Python entrypoint, or full control over the SDK code, explain the options and let them decide. If they choose a custom automation, refer to references/custom-automation.md for the tarball upload and custom creation workflow.

Read the full file on GitHub · 56 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. 2d ago First seen · 56 lines · 9 tokens per session scan A 955be0d35fd5

Subscribe to this mod's changes

create is a command published in the GitHub repository OpenHands/extensions (137 stars, last pushed 4d ago), licensed MIT. It adds 9 tokens to every session and 570 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.