← 返回 Skills 市场

long-running-agent-harness

Name: long-running-agent-harness
Author: wenkangwei

作者 wenkangwei · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ✓ 安全检测通过

121

总下载

当前安装

版本数

在 OpenClaw 中安装

/install long-running-agent-harness

功能描述

Long-running agent workflow automation. Initialize project scaffolding, manage feature lists, track progress across sessions, and orchestrate coding agents.

使用说明 (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 tracking
claude-progress.txt — cross-session progress log
init.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

安全使用建议

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.

功能分析

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.

能力标签

crypto

能力评估

✓ 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.

ℹ 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.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install long-running-agent-harness
安装完成后，直接呼叫该 Skill 的名称或使用 /long-running-agent-harness 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

long-running agent-harness paradigm

元数据

Slug long-running-agent-harness

版本 1.0.0

许可证 MIT-0

累计安装 1

当前安装数 1

历史版本数 1

常见问题