·harness
""

harness

This skill should be used for multi-session autonomous agent work requiring progress checkpointing, failure recovery, and task dependency management. Triggers on '/harness' command, or when a task involves many subtasks needing progress persistence, sleep/resume cycles across context windows, recovery from mid-task failures with partial state, or distributed work across multiple agent sessions. Synthesized from Anthropic and OpenAI engineering practices for long-running agents.

44Installs·5Trend·@cexll

Installation

$npx skills add https://github.com/cexll/myclaude --skill harness

How to Install harness

Quickly install harness AI skill to your development environment via command line

  1. Open Terminal: Open your terminal or command line tool (Terminal, iTerm, Windows Terminal, etc.)
  2. Run Installation Command: Copy and run this command: npx skills add https://github.com/cexll/myclaude --skill harness
  3. Verify Installation: Once installed, the skill will be automatically configured in your AI coding environment and ready to use in Claude Code, Cursor, or OpenClaw

Source: cexll/myclaude.

SKILL.md

View raw

Executable protocol enabling any agent task to run continuously across multiple sessions with automatic progress recovery, task dependency resolution, failure rollback, and standardized error handling.

Free-text log of all agent actions across sessions. Never truncate.

Task statuses: pending → inprogress (transient, set only during active execution) → completed or failed. A task found as inprogress at session start means the previous session was interrupted — handle via Context Window Recovery Protocol.

This skill should be used for multi-session autonomous agent work requiring progress checkpointing, failure recovery, and task dependency management. Triggers on '/harness' command, or when a task involves many subtasks needing progress persistence, sleep/resume cycles across context windows, recovery from mid-task failures with partial state, or distributed work across multiple agent sessions. Synthesized from Anthropic and OpenAI engineering practices for long-running agents. Source: cexll/myclaude.

Facts (cite-ready)

Stable fields and commands for AI/search citations.

Install command
npx skills add https://github.com/cexll/myclaude --skill harness
Category
""Writing
Verified
First Seen
2026-02-23
Updated
2026-03-10

Browse more skills from cexll/myclaude

Quick answers

What is harness?

This skill should be used for multi-session autonomous agent work requiring progress checkpointing, failure recovery, and task dependency management. Triggers on '/harness' command, or when a task involves many subtasks needing progress persistence, sleep/resume cycles across context windows, recovery from mid-task failures with partial state, or distributed work across multiple agent sessions. Synthesized from Anthropic and OpenAI engineering practices for long-running agents. Source: cexll/myclaude.

How do I install harness?

Open your terminal or command line tool (Terminal, iTerm, Windows Terminal, etc.) Copy and run this command: npx skills add https://github.com/cexll/myclaude --skill harness Once installed, the skill will be automatically configured in your AI coding environment and ready to use in Claude Code, Cursor, or OpenClaw

Where is the source repository?

https://github.com/cexll/myclaude