LaunchKit · 2026
Back to Skills

agent-step-sequencer

Multi-step scheduler for in-depth agent requests.

3
1.7k downloads
by @gostlightai

Setup & Installation

openclaw skills install @gostlightai/agent-step-sequencer

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

npx clawhub install agent-step-sequencer

Version History

v1.1.0Feb 10, 2026 - Version note by skill developer:

Require STEP_AGENT_CMD (no more silent echo default), fix openclaw CLI command refs, add OpenClaw-compliant metadata, capture agent stdout in stepRuns, fix step delay between steps

What This Skill Does

Multi-step scheduler that detects when a user request requires sequential actions, proposes a step plan, waits for confirmation, then persists and executes each step. Survives gateway resets by writing state to disk and resuming on the next heartbeat. Handles automatic retries and failure recovery without user intervention.

Persisting state to disk and resuming on heartbeat means a mid-execution gateway reset does not lose progress, unlike single-shot agent calls that fail completely if interrupted.

When to use it

  • Running a multi-phase research and writing workflow
  • Executing sequential API calls with rate-limit delays between steps
  • Automating multi-file migrations or setup tasks
  • Recovering long-running agent tasks after a connection drop
  • Chaining dependent steps where each step's output feeds the next

Example Workflow

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

INPUT

User asks: Research a topic, write a paper based on the research, then produce an outline of the paper

AGENT
  1. 1Detects 3 sequential actions with output dependencies, proposes a 3-step plan and waits for user confirmation
  2. 2User confirms; agent asks whether to apply 2-minute delays between steps for rate-limit safety
  3. 3Agent persists state.json with step definitions and immediately invokes step-sequencer-check.py
  4. 4Runner executes step-1, verifies requiredOutputs exist, marks DONE, and advances to step-2
  5. 5Heartbeat re-invokes check script on schedule; if a step is FAILED, runner retries with a troubleshoot prompt
OUTPUT

All steps marked DONE; agent posts a summary with paths to all files created during the workflow

Requirements

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

STEP_AGENT_CMD environment variable (command used to invoke the agent, e.g. openclaw agent --message)