LaunchKit · 2026
Back to Skills

hitl-protocol

HITL Protocol — the open standard for human decisions in autonomous agent workflows.

2
320 downloads
by @rotorstar

Setup & Installation

openclaw skills install @rotorstar/hitl-protocol

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

npx clawhub install hitl-protocol

Version History

v0.7.2Mar 2, 2026 - Version note by skill developer:

- Version 0.7.2 Optional quality Improvement in API

What This Skill Does

HITL Protocol is an open standard for inserting human decisions into autonomous agent workflows. When a service needs human input, it returns HTTP 202 with a review URL. The agent forwards that URL to the user, polls for the structured result, and continues execution.

It enforces human control over irreversible agent actions using plain HTTP with no SDK, no UI framework, and no custom messenger integration beyond optional native buttons.

When to use it

  • Reviewing job listings before an agent submits applications
  • Confirming a non-refundable booking before payment goes through
  • Approving a generated email batch before it sends
  • Selecting a deployment plan before an agent executes it
  • Escalating a failed agent action to a human for recovery

Example Workflow

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

INPUT

User asks: Find senior developer jobs in Berlin and apply to the best ones

AGENT
  1. 1Posts search query to job board API
  2. 2Receives HTTP 202 with a HITL object containing review_url and poll_url
  3. 3Sends review_url to user: '5 jobs found. Select which to apply for: [url]'
  4. 4Polls poll_url every 30 seconds until status changes from pending
  5. 5Reads selected job IDs from result.data and submits applications
OUTPUT

Applied to 2 user-selected jobs.