Agent skill

Autonomous Agent Harness

by affaan-m in affaan-m/ECC

将 Claude Code 转变为具有持久记忆、定时操作、计算机使用和任务队列的完全自主代理系统。通过利用 Claude Code 的原生定时任务、调度、MCP 工具和记忆,取代独立的代理框架(Hermes、AutoGPT)。当用户需要持续自主操作、定时任务或自我导向的代理循环时使用。

MITAuto-check passedAgent Workflows

Install Autonomous Agent Harness

skills CLI
$ npx skills add affaan-m/ECC --skill autonomous-agent-harness -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install affaan-m/ECC autonomous-agent-harness --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/affaan-m/ECC.git skills-src && mkdir -p .claude/skills && cp -r skills-src/docs/zh-CN/skills/autonomous-agent-harness .claude/skills/autonomous-agent-harness && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
autonomous-agent-harness
GitHub stars
276k
Token cost
~1.5k tokens
SKILL.md length
181 words
Files
1
Skills in repo
683
Repo updated
First seen
Licence
MIT

At a glance

将 Claude Code 转变为具有持久记忆、定时操作、计算机使用和任务队列的完全自主代理系统。通过利用 Claude Code 的原生定时任务、调度、MCP 工具和记忆,取代独立的代理框架(Hermes、AutoGPT)。当用户需要持续自主操作、定时任务或自我导向的代理循环时使用。

  • Works in 5 steps: 持久化内存 → 计划操作(定时任务) → 调度 / 远程代理 → …
  • Tasks that involve Autonomous loops
  • SKILL.md covers 同意与安全边界, 何时激活, 架构 and 核心组件, plus 4 more sections
  • Calls claude and curl; reaches api.anthropic.com; needs ANTHROPIC_API_KEY

What it does

Autonomous Agent Harness is an agent skill from affaan-m/ECC. 将 Claude Code 转变为具有持久记忆、定时操作、计算机使用和任务队列的完全自主代理系统。通过利用 Claude Code 的原生定时任务、调度、MCP 工具和记忆,取代独立的代理框架(Hermes、AutoGPT)。当用户需要持续自主操作、定时任务或自我导向的代理循环时使用。

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Autonomous loops. It works with Model Context Protocol. The repository describes itself as: The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. The licence is MIT.

When your agent uses it

  • Tasks that involve Autonomous loops

Example prompts

  • “/autonomous-agent-harness”

Requirements

  • A credential in ANTHROPIC_API_KEY

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. 持久化内存
  2. 计划操作(定时任务)
  3. 调度 / 远程代理
  4. 计算机使用
  5. 任务队列

What it can do on your machine

Read from SKILL.md and the folder at commit 4eb71d9. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • claude
    • curl

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • api.anthropic.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • ANTHROPIC_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Autonomous Agent Harness loads about 1.5k tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 181 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from affaan-m/ECC at commit 4eb71d9, republished under its MIT licence (© affaan-m). 181 words, ~1,543 tokens.

Download SKILL.mdSave it as .claude/skills/autonomous-agent-harness/SKILL.md (or your agent's skills folder).
name
autonomous-agent-harness
description
将 Claude Code 转变为具有持久记忆、定时操作、计算机使用和任务队列的完全自主代理系统。通过利用 Claude Code 的原生定时任务、调度、MCP 工具和记忆,取代独立的代理框架(Hermes、AutoGPT)。当用户需要持续自主操作、定时任务或自我导向的代理循环时使用。
origin
ECC

自主代理框架

仅使用原生功能和 MCP 服务器,将 Claude Code 转变为持久化、自我导向的代理系统。

同意与安全边界

自主操作必须由用户明确请求并划定范围。除非用户已批准该能力以及当前设置的目标工作空间,否则不得创建计划、调度远程代理、写入持久化内存、使用计算机控制、发布外部内容、修改第三方资源或处理私人通信。

在启用定期或事件驱动操作之前,优先使用预演计划和本地队列文件。将凭据、私有工作空间导出、个人数据集和账户特定自动化排除在可复用的 ECC 工件之外。

何时激活

  • 用户需要一个持续运行或按计划运行的代理
  • 设置定期触发的自动化工作流
  • 构建一个跨会话记住上下文的个人 AI 助手
  • 用户说“每天运行这个”、“定期检查这个”、“持续监控”
  • 希望复制 Hermes、AutoGPT 或类似自主代理框架的功能
  • 需要计算机使用与计划执行相结合

架构

┌──────────────────────────────────────────────────────────────┐
│                    Claude Code 运行时                         │
│                                                              │
│  ┌──────────┐  ┌──────────┐  ┌──────────┐  ┌─────────────┐ │
│  │  定时任务 │  │  远程调度 │  │  记忆存储 │  │  计算机使用  │ │
│  │  调度器   │  │  代理    │  │          │  │             │ │
│  └────┬─────┘  └────┬─────┘  └────┬─────┘  └──────┬──────┘ │
│       │              │             │                │        │
│       ▼              ▼             ▼                ▼        │
│  ┌──────────────────────────────────────────────────────┐    │
│  │              ECC 技能 + 代理层                        │    │
│  │                                                      │    │
│  │  skills/     agents/     commands/     hooks/        │    │
│  └──────────────────────────────────────────────────────┘    │
│       │              │             │                │        │
│       ▼              ▼             ▼                ▼        │
│  ┌──────────────────────────────────────────────────────┐    │
│  │              MCP 服务器层                             │    │
│  │                                                      │    │
│  │  memory    github    exa    supabase    browser-use  │    │
│  └──────────────────────────────────────────────────────┘    │
└──────────────────────────────────────────────────────────────┘

核心组件

1. 持久化内存

使用 Claude Code 的内置内存系统,并通过 MCP 内存服务器增强以处理结构化数据。

内置内存(~/.claude/projects/*/memory/):

  • 用户偏好、反馈、项目上下文
  • 存储为带有前置元数据的 Markdown 文件
  • 在会话启动时自动加载

MCP 内存服务器(结构化知识图谱):

  • 实体、关系、观察
  • 可查询的图结构
  • 跨会话持久化

内存模式:

# 短期:当前会话上下文
使用 TodoWrite 进行会话内任务追踪

# 中期:项目记忆文件
写入 ~/.claude/projects/*/memory/ 以实现跨会话回忆

# 长期:MCP 知识图谱
使用 mcp__memory__create_entities 创建永久结构化数据
使用 mcp__memory__create_relations 进行关系映射
使用 mcp__memory__add_observations 添加关于已知实体的新事实
2. 计划操作(定时任务)

使用 Claude Code 的计划任务创建定期代理操作。

设置定时任务:

# Via MCP tool
mcp__scheduled-tasks__create_scheduled_task({
  name: "daily-pr-review",
  schedule: "0 9 * * 1-5",  # 工作日上午9点
  prompt: "Review all open PRs in affaan-m/ECC. For each: check CI status, review changes, flag issues. Post summary to memory.",
  project_dir: "/path/to/repo"
})

# Via claude -p (程序化模式)
echo "Review open PRs and summarize" | claude -p --project /path/to/repo

有用的定时任务模式:

模式计划用例
每日站会0 9 * * 1-5审查 PR、问题、部署状态
每周回顾0 10 * * 1代码质量指标、测试覆盖率
每小时监控0 * * * *生产健康、错误率检查
夜间构建0 2 * * *运行完整测试套件、安全扫描
会前准备*/30 * * * *为即将到来的会议准备上下文
3. 调度 / 远程代理

远程触发 Claude Code 代理以进行事件驱动的工作流。

调度模式:

bash
# Trigger from CI/CD
curl -X POST "https://api.anthropic.com/dispatch" \
  -H "Authorization: Bearer $ANTHROPIC_API_KEY" \
  -d '{"prompt": "Build failed on main. Diagnose and fix.", "project": "/repo"}'

# Trigger from webhook
# GitHub webhook → dispatch → Claude agent → fix → PR

# Trigger from another agent
claude -p "Analyze the output of the security scan and create issues for findings"
4. 计算机使用

利用 Claude 的计算机使用 MCP 进行物理世界交互。

能力:

  • 浏览器自动化(导航、点击、填写表单、截图)
  • 桌面控制(打开应用、输入、鼠标控制)
  • 超越 CLI 的文件系统操作

在框架内的用例:

  • Web UI 的自动化测试
  • 表单填写和数据录入
  • 基于截图的监控
  • 多应用工作流
5. 任务队列

管理一个跨会话边界的持久化任务队列。

实现:

# 通过记忆实现任务持久化
将任务队列写入 ~/.claude/projects/*/memory/task-queue.md

# 任务格式
---
name: task-queue
type: project
description: 用于自主操作的持久化任务队列
---

## 活跃任务
- [ ] PR #123: 审查并在CI通过后批准
- [ ] 监控部署:每30分钟检查一次 /health,持续2小时
- [ ] 调研:在AI工具领域寻找5个潜在客户

## 已完成
- [x] 每日站会:审查了3个PR,2个问题

替换 Hermes

Hermes 组件ECC 等效组件如何实现
网关/路由器Claude Code 调度 + 定时任务计划任务触发代理会话
内存系统Claude 内存 + MCP 内存服务器内置持久化 + 知识图谱
工具注册表MCP 服务器动态加载的工具提供者
编排ECC 技能 + 代理技能定义指导代理行为
计算机使用计算机使用 MCP原生浏览器和桌面控制
上下文管理器会话管理 + 内存ECC 2.0 会话生命周期
任务队列内存持久化任务列表TodoWrite + 内存文件

设置指南

步骤 1:配置 MCP 服务器

确保这些在 ~/.claude.json 中:

json
{
  "mcpServers": {
    "memory": {
      "command": "npx",
      "args": ["-y", "@anthropic/memory-mcp-server"]
    },
    "scheduled-tasks": {
      "command": "npx",
      "args": ["-y", "@anthropic/scheduled-tasks-mcp-server"]
    },
    "computer-use": {
      "command": "npx",
      "args": ["-y", "@anthropic/computer-use-mcp-server"]
    }
  }
}
步骤 2:创建基础定时任务
bash
# Daily morning briefing
claude -p "Create a scheduled task: every weekday at 9am, review my GitHub notifications, open PRs, and calendar. Write a morning briefing to memory."

# Continuous learning
claude -p "Create a scheduled task: every Sunday at 8pm, extract patterns from this week's sessions and update the learned skills."
步骤 3:初始化内存图谱
bash
# Bootstrap your identity and context
claude -p "Create memory entities for: me (user profile), my projects, my key contacts. Add observations about current priorities."
步骤 4:启用计算机使用(可选)

授予计算机使用 MCP 浏览器和桌面控制所需的权限。

示例工作流

自主 PR 审查员
Cron: 工作时间内每30分钟执行一次
1. 检查关注仓库的新PR
2. 对每个新PR:
   - 在本地拉取分支
   - 运行测试
   - 使用代码审查代理审查变更
   - 通过GitHub MCP发布审查评论
3. 更新审查状态到记忆库
个人研究代理
Cron: 每天上午6点执行
1. 检查内存中保存的搜索查询
2. 对每个查询运行Exa搜索
3. 总结新发现
4. 与昨日结果进行对比
5. 将摘要写入内存
6. 标记高优先级项目供晨间审阅
会议准备代理
触发条件:每个日历事件前30分钟
1. 读取日历事件详情
2. 搜索记忆中关于参会者的背景信息
3. 提取与参会者近期的邮件/Slack讨论记录
4. 准备谈话要点和议程建议
5. 将准备文档写入记忆

约束

  • 定时任务在隔离的会话中运行——除非通过内存,否则它们不与交互式会话共享上下文。
  • 计算机使用需要明确的权限授予。不要假设可以访问。
  • 远程调度可能有速率限制。设计定时任务时使用适当的间隔。
  • 内存文件应保持简洁。归档旧数据,而不是让文件无限增长。
  • 始终验证计划任务是否成功完成。在定时任务提示中添加错误处理。

© affaan-m, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in docs/zh-CN/skills/autonomous-agent-harness of affaan-m/ECC.

Open the folder on GitHubat commit 4eb71d9

Compare with similar skills

Autonomous Agent Harness next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Autonomous Agent Harness compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Autonomous Agent Harness this skillaffaan-m/ECC276k—~1.5kAutomated safety check: PassMIT
agtx One-Shot Project Runnerfynnfluegge/agtx1.7k—~3.8kAutomated safety check: PassApache-2.0
Plugin CreatoruseLexora/Lexora569—~1kAutomated safety check: PassAGPL-3.0
Ouroboros Evolve LoopQ00/ouroboros6.2k—~3.2kAutomated safety check: PassMIT
Hermes Mission ControlTh0rgal/sandboxed.sh524—~8.6kAutomated safety check: PassNone
Agent Native Architecturesandgardenhq/sgai137—~2kAutomated safety check: PassCustom licence

Similar skills

  • Runs a whole project unattended on an agtx kanban board, decomposing the goal, starting tasks, unblocking workers and merging each result.

    1.7k GitHub stars~3.8k tokensUpdated 9 days ago
    Agent WorkflowsAuto-check passed
  • Plugin Creator

    useLexora/Lexora

    创建、修改并验证可安装的 Lexora 桌面插件,包括多主题配色包、工作台装饰、导航与面板、文件阅读工具、控件样式、网络查询、通知和定时命令。也响应 $plugin-creator。普通任务执行、使用现有插件、其他产品的插件开发不属于此技能。

    569 GitHub stars~1k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Starts, monitors or rewinds an evolutionary development loop that refines an ontology and acceptance criteria generation by generation until it converges, using the Ouroboros MCP tools.

    6.2k GitHub stars~3.2k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check passed
  • Hermes Mission Control

    Th0rgal/sandboxed.sh

    Teaches Hermes to monitor and steer long-running sandboxed.sh missions: spot where a model is stuck, switch backends or models between turns, and send targeted hints.

    524 GitHub stars~8.6k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Agent Native Architecture

    sandgardenhq/sgai

    Build AI agents using prompt-native architecture where features are defined in prompts, not code.

    137 GitHub stars~2k tokensUpdated 20 days ago
    Agent WorkflowsAuto-check passed
  • Lexora Buddy Animation

    useLexora/Lexora

    A skill your agent uses when the user asks Lexora Buddy to move, emote, celebrate, rest, or perform a visible desktop-pet action.

    569 GitHub stars~232 tokensUpdated today
    Agent WorkflowsAuto-check passed

More from affaan-m/ECC

All 682 skills in this repo
  • Skill Stocktake

    affaan-m/ECC

    Audits your installed Claude skills and commands for quality, with a quick mode for recently changed skills and a full mode that evaluates all of them through subagents.

    277k GitHub starsUsed in 5 repos~3.1k tokens
    Auto-check passed
  • Ingests, indexes, searches, edits and monitors video, audio and live streams through the VideoDB Python SDK, returning stream links, clips and timestamps.

    277k GitHub starsUsed in 3 repos~3.5k tokens
    Auto-check: notes
  • Docs Governance

    affaan-m/ECC

    Route broad documentation-governance requests to existing ECC skills and run an opt-in, read-only audit of mapped documentation roles, links, ADR indexes, and evidence references.

    277k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Rules Distillation

    affaan-m/ECC

    Scans installed skills for principles that recur across them and proposes rule-file changes: append, revise, add a section, create a file or leave as covered.

    277k GitHub starsUsed in 2 repos~2.3k tokens
    Auto-check passed
  • Builds DRAFT counterparty agreements from one markdown template and a small JSON spec per party, with clauses picked by the party's role.

    277k GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • Set an ECC-specific frontend design direction for production UI work.

    277k GitHub starsUsed in 1 repo~2.2k tokens
    Auto-check passed

Categories

Questions about Autonomous Agent Harness

What does Autonomous Agent Harness do?

将 Claude Code 转变为具有持久记忆、定时操作、计算机使用和任务队列的完全自主代理系统。通过利用 Claude Code 的原生定时任务、调度、MCP 工具和记忆,取代独立的代理框架(Hermes、AutoGPT)。当用户需要持续自主操作、定时任务或自我导向的代理循环时使用。. Autonomous Agent Harness is an agent skill from affaan-m/ECC.

When should I use Autonomous Agent Harness?

Autonomous Agent Harness fits situations like: tasks that involve Autonomous loops.

How do I install Autonomous Agent Harness in Claude Code?

Run `npx skills add affaan-m/ECC --skill autonomous-agent-harness -a claude-code`. Or copy the skill folder (docs/zh-CN/skills/autonomous-agent-harness in affaan-m/ECC) into .claude/skills/autonomous-agent-harness in your project. Claude Code loads it when a task matches its description.

How do I install Autonomous Agent Harness in Codex?

Run `npx skills add affaan-m/ECC --skill autonomous-agent-harness -a codex`. Or copy the skill folder (docs/zh-CN/skills/autonomous-agent-harness in affaan-m/ECC) into .agents/skills/autonomous-agent-harness in your project. Codex loads it when a task matches its description.

Can I use Autonomous Agent Harness in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add affaan-m/ECC --skill autonomous-agent-harness -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/autonomous-agent-harness, .gemini/skills/autonomous-agent-harness, .github/skills/autonomous-agent-harness and .opencode/skills/autonomous-agent-harness in your project.

What does Autonomous Agent Harness need to run?

Going by SKILL.md and its folder, Autonomous Agent Harness needs the command-line tools its instructions call (claude and curl) and credentials named ANTHROPIC_API_KEY. Our summary lists: A credential in ANTHROPIC_API_KEY.

Does Autonomous Agent Harness access the network?

SKILL.md names 1 domain. In commands or code: api.anthropic.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Autonomous Agent Harness safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Autonomous Agent Harness use?

Autonomous Agent Harness is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Autonomous Agent Harness use?

About 1.5k tokens (SKILL.md is roughly 6.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Autonomous Agent Harness?

Skills that share tags, products or a category with Autonomous Agent Harness: agtx One-Shot Project Runner (fynnfluegge/agtx, 1.7k stars), Plugin Creator (useLexora/Lexora, 569 stars), Ouroboros Evolve Loop (Q00/ouroboros, 6.2k stars) and Hermes Mission Control (Th0rgal/sandboxed.sh, 524 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Autonomous Agent Harness?

affaan-m (a GitHub user) maintains it in affaan-m/ECC, which has 276,111 GitHub stars. The repository holds 683 skills in this directory. The repository was last updated on October 10, 2026.

Source: affaan-m/ECC on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.