Agent Claws

A standardized way to schedule AI agents to run recurring, unattended tasks

A claw is a job an agent runs on its own, on a schedule, described by a single CLAW.md file.

CLAW.md

---
version: 1
name: inbox-tidy
description: Keep alice@example.com's spam labels honest and surface the threads that still need a reply.
system_prompt: |
  You are a meticulous inbox keeper. You value a tidy inbox, act only when you are confident, never delete a message, and would rather leave mail in place than misfile it.
schedule: every 5m
runtime: agent
---

# catch missed spam

Scan new mail in alice@example.com's inbox for messages that are clearly spam but arrived unlabeled, and move each one to the Spam folder. Leave anything uncertain where it is.

# rescue good mail

Review alice@example.com's Spam folder for real messages caught by mistake, a known contact, a receipt, a reply in an ongoing thread, and move those back to the inbox.

# flag replies needed

Find threads in alice@example.com's inbox still waiting on a reply from her and star them so they are easy to find.

What are Agent Claws?

Agent Claws are an open format for work you would normally hand to a coding agent so it can run on its own. At its core, a claw is a job described by a single CLAW.md file. The file holds YAML frontmatter, with name and description at minimum, followed by one or more ordered tasks. There are no companion directories, scripts, or assets. Everything the claw needs lives in the one file.

CLAW.md

---
version: 1
name: weather-morning
description: Daily morning weather brief for your city, emailed at 07:00.
schedule: daily @ 07:00
---

# brief

Look up today's forecast for your city, including conditions, high and low temperatures, and chance of rain. Write a short three to five sentence morning brief and email it to yourself.

Why Agent Claws?

Claws let an agent handle recurring work on its own.

They run on a schedule you set.
Each task reuses the tools, CLIs, and integrations the host agent already has.

Why CLAW.md?

The format keeps a claw simple and portable.

One self-contained file, with no companion directories, scripts, or assets.
Plain Markdown, so it reads, edits, and diffs like any other text.
An open, vendor-neutral standard, so the same file runs on any compatible runner.

How do Agent Claws work?

A runner reads the claw's frontmatter, then runs its tasks in source order. Each task runs as an agent with full tool use, reusing the tools, CLIs, and integrations the host already provides, or as a plain bash step.

How is a claw different from a cron job?

A claw is closer to an agentic cron job. It runs on a schedule like cron, but instead of a fixed script it runs an agent that reasons about what it finds and acts on it. Each claw is a named, ordered set of agent or bash steps rather than a single command.

Where can I use Agent Claws?

Any CLAW.md-compatible runner can execute a claw. Because the format carries no vendor-specific mechanisms, a claw authored for one runner runs unchanged on another. See the clients that support the format.

How is Agent Claws developed?

Agent Claws was originally developed by Clor and released as an open standard so any runner can adopt it. The specification is vendor-neutral and the project welcomes ecosystem contributions. Come join the discussion on GitHub.

How do I write a claw?

Start from the specification for the complete format, then adapt one of the working examples. A minimal claw needs only a name, a description, and at least one task heading.