LaunchKit · 2026
Back to Skills

opcode

Zero-token execution layer for AI agents.

0
1.1k downloads
by @rendis

Setup & Installation

openclaw skills install @rendis/opcode

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install opcode

Version History

v1.2.2Feb 13, 2026 - Version note by skill developer:

- Reworded description and introduction for clarity, emphasizing zero-token execution and persistence. - Mentioned support for 26 built-in actions (was 25). - Highlighted the advantage of defining workflows once and running them for free with deterministic results. - No structural or functional changes to tools or API.

What This Skill Does

OPCODE is a workflow execution runtime for AI agents. Workflows are defined once as JSON DAGs and run repeatedly at zero token cost after the initial definition. Supports scheduled triggers, parallel branches, loops, conditions, human-in-the-loop reasoning nodes, and a secret vault.

Defining a workflow once and re-running it deterministically costs zero inference tokens per execution, unlike agent loops that re-reason every step from scratch.

When to use it

  • Running scheduled data pipelines without re-reasoning each step
  • Coordinating multiple agents on a shared persistent workflow
  • Adding human approval checkpoints before irreversible automated actions
  • Retrying failed shell commands with configurable exponential backoff
  • Parallelizing HTTP requests across multiple endpoints in a single workflow

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: Set up a pipeline that fetches a JSON feed, filters results by keyword, and writes a summary file on a daily schedule

AGENT
  1. 1Call opcode.define with a template name, cron trigger, and steps using http.get, expr.eval, and fs.write
  2. 2Call opcode.run with the template name and any input parameters to test the workflow
  3. 3Call opcode.status to verify the workflow completed or to inspect any suspended reasoning steps
  4. 4Call opcode.query with resource workflows to retrieve execution history and outputs
OUTPUT

Workflow registered and running on schedule, writing summary files each day with no token cost per run

Requirements

Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.

OPCODE_VAULT_KEY environment variable