← Back to Skills Marketplace
long-running-agent-harness
by
wenkangwei
· GitHub ↗
· v1.0.0
· MIT-0
121
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install long-running-agent-harness
Description
Long-running agent workflow automation. Initialize project scaffolding, manage feature lists, track progress across sessions, and orchestrate coding agents.
README (SKILL.md)
Agent Harness Skill
Automates the long-running agent workflow from Anthropic's engineering blog. Manages feature lists, progress tracking, and session orchestration across multiple Claude Code sessions.
Commands
/harness-init \x3Cproject-description>
Initialize a new project with:
feature_list.json— comprehensive feature trackingclaude-progress.txt— cross-session progress loginit.sh— development server startup script.harness.json— harness configuration
/harness-run
Start a coding session. Reads progress, picks the next feature, and follows the incremental development workflow.
/harness-status
Show current project progress: features completed, next features to implement, recent session history.
/harness-feature \x3Cdescription>
Add a new feature to the feature list.
/harness-commit
Commit current work with structured message and update progress file.
Architecture
┌─────────────┐ ┌──────────────┐ ┌──────────────┐
│ Initializer │────▶│ Coding Agent│────▶│ Next Coding│
│ Agent │ │ Session #1 │ │ Agent #2 │
└─────────────┘ └──────────────┘ └──────────────┘
│ │ │
▼ ▼ ▼
┌─────────────────────────────────────────────────────────┐
│ Shared State │
│ ┌───────────────┐ ┌──────────────┐ ┌────────────────┐ │
│ │feature_list │ │claude-progress│ │ Git History │ │
│ │ .json │ │ .txt │ │ (commits) │ │
│ └───────────────┘ └──────────────┘ └────────────────┘ │
└─────────────────────────────────────────────────────────┘
Workflow
- Init:
harness init "Build a chat app"— sets up project skeleton - Code:
harness run— each session picks ONE feature - Track: Features marked passing only after end-to-end testing
- Commit: Progress documented in git + progress file
- Repeat: Continue until all features pass
Key Principles
- Incremental: One feature per session
- Tested: End-to-end testing before marking complete
- Clean state: Always leave codebase merge-ready
- Persistent state: Git + progress file bridge context windows
Usage Guidance
This skill appears to do what it says: scaffold per-session feature tracking, prompt agents, and run git commits. Important cautions: 1) The harness will create and modify files in whatever directory you run it in and can run git init / git commit — do not run it in a production or important repository without a backup or in a throwaway clone. 2) The provided init.sh is a template that could be customized to run arbitrary commands; review its contents before executing. 3) The coding prompts instruct agents to run tests and use browser automation/curl — ensure required tooling is installed and sandbox any automation you don't trust. 4) The skill expects you to paste prompts to an external Claude agent/service (per README/prompt guidance); be mindful of any data you send there. If you want extra safety, run the harness in an isolated directory, inspect and edit the templates (init.sh, feature_list.json) before use, and keep version control (or a disposable branch) so you can review or revert commits.
Capability Analysis
Type: OpenClaw Skill
Name: long-running-agent-harness
Version: 1.0.0
The 'agent-harness' skill is a project management framework designed to orchestrate long-running AI agent workflows by tracking features and progress across multiple sessions. The core logic in `scripts/harness.sh` uses standard shell commands and Python for JSON state management, while the markdown prompts (`prompts/coder.md`, `prompts/initializer.md`) provide structured instructions for incremental development and testing. No indicators of data exfiltration, malicious execution, or harmful prompt injection were found.
Capability Tags
Capability Assessment
Purpose & Capability
Name/description (long-running agent harness) match the provided templates, prompts, and scripts. Declared dependencies (bash, git, python3) are reasonable for the operations the harness performs (file templating, git init/commit, small Python snippets). No unrelated credentials, binaries, or external services are required by the skill itself.
Instruction Scope
SKILL.md, prompts, and harness.sh consistently instruct agents to: initialize templates, read/write feature_list.json and claude-progress.txt, run init.sh, inspect git history, perform one feature per session, run end-to-end tests, and commit changes. All of these are within scope for an automation that manages incremental coding sessions. The prompts explicitly tell agents to modify files and run git commands — this is expected but is powerful (it modifies your repository).
Install Mechanism
Instruction-only skill with included scripts and templates; no install spec, no network/downloads, and no archives extracted. Files are shipped with the skill; there is no remote installer or URL-based fetch. This is a low-risk install mechanism.
Credentials
The skill declares no required environment variables or secrets. It uses local tooling (git, bash, python3) appropriate to the task. There are no requests for unrelated credentials or access tokens.
Persistence & Privilege
always: false and disable-model-invocation: false (normal). The harness writes files (.harness.json, feature_list.json, claude-progress.txt, init.sh) and runs git operations (init, commit, checkout/stash guidance). This is appropriate for its purpose but gives the skill the ability to modify the user's repository; users should be aware and supervise runs in critical repos.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install long-running-agent-harness - After installation, invoke the skill by name or use
/long-running-agent-harness - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
long-running agent-harness paradigm
Metadata
Frequently Asked Questions
What is long-running-agent-harness?
Long-running agent workflow automation. Initialize project scaffolding, manage feature lists, track progress across sessions, and orchestrate coding agents. It is an AI Agent Skill for Claude Code / OpenClaw, with 121 downloads so far.
How do I install long-running-agent-harness?
Run "/install long-running-agent-harness" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is long-running-agent-harness free?
Yes, long-running-agent-harness is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does long-running-agent-harness support?
long-running-agent-harness is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created long-running-agent-harness?
It is built and maintained by wenkangwei (@wenkangwei); the current version is v1.0.0.
More Skills