← 返回 Skills 市场
🔌

Full run checklist.md tasks in Claude Code skill

作者 lightconsen · GitHub ↗ · v1.0.2 · MIT-0
cross-platform ⚠ suspicious
106
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install fullrun
功能描述
Automatically execute tasks from checklist.md with state management and scheduled checking
使用说明 (SKILL.md)

Fullrun Skill

Overview

This skill implements a task execution system with the following features:

  1. State Management: Uses .claude-status.txt file to track execution state

    • 0 = Idle, ready to execute (or file doesn't exist)
    • 1 = Claude is currently executing tasks
    • 2 = All tasks completed, monitoring should exit
  2. Task List: Reads pending tasks from checklist.md

  3. Scripts: Executable scripts in the scripts/ directory

Requirements

  • jq - Required for install/uninstall scripts
    • macOS: brew install jq
    • Linux: apt install jq or yum install jq

File Structure

project/
├── SKILL.md                  # This skill definition file
├── checklist.md              # Task list file (create in your project)
├── .claude-status.txt        # Execution state file (auto-generated)
├── .fullrun.log              # Execution log (auto-generated)
├── .monitor.pid              # Monitor process PID (auto-generated)
├── .claude/
│   └── fullrun/
│       └── scripts/          # Installed scripts (auto-generated)
│           ├── main.sh       # Main entry point
│           ├── fullrun.sh    # Task execution script
│           └── cron-manager.sh # Cron job management script
└── scripts/
    ├── main.sh               # Main entry point (source)
    ├── fullrun.sh            # Task execution script (source)
    ├── cron-manager.sh       # Cron job management script (source)
    ├── install.sh            # Installation script
    └── uninstall.sh          # Uninstallation script

Usage

Installation (run once per project)

The installer creates project-local configuration in ./.claude/ - no global settings are modified.

# In your project directory, run:
./scripts/install.sh

What the installer does:

  1. Creates .claude/ directory in your project
  2. Copies scripts to .claude/fullrun/scripts/
  3. Creates or updates .claude/settings.local.json with:
    • Permission rule for project scripts
    • SessionStart hook for auto-monitoring

Scope: Configuration is project-local only. Other projects are not affected.

Uninstall

./scripts/uninstall.sh

This removes:

  • The .claude/fullrun/ directory
  • Fullrun permission rule from .claude/settings.local.json
  • Fullrun hook from SessionStart (preserves other hooks)
  • .claude/settings.local.json if it becomes empty

Start scheduled monitoring (recommended)

./.claude/fullrun/scripts/main.sh start

Manually execute tasks

./.claude/fullrun/scripts/main.sh run

Check status

./.claude/fullrun/scripts/main.sh status

Stop monitoring

./.claude/fullrun/scripts/main.sh stop

Execution Rules

  1. If .claude-status.txt does not exist or contains 0, start executing unfinished tasks from checklist.md
  2. When executing tasks, set .claude-status.txt to 1
  3. When all tasks are completed, set .claude-status.txt to 2
  4. Scheduled task checks every 1 minute:
    • If status = 0 or file doesn't exist + pending tasks = start execution
    • If status = 1 = Claude is running, continue waiting
    • If status = 2 = All tasks completed, exit monitoring
  5. Monitoring automatically exits when all tasks are completed (status=2)

Task Marking Format

In checklist.md, tasks use the following format:

  • [ ] indicates incomplete
  • [x] indicates completed

Example:

# Checklist

- [ ] Task 1: Complete a feature
- [ ] Task 2: Write tests
- [x] Task 3: Completed task

Notes

  • Scheduled monitoring is session-level, stops when the current terminal session ends
  • For persistent monitoring, use system cron or launchd
  • The SessionStart hook checks for checklist.md in the current working directory at runtime
  • Configuration is project-local via .claude/settings.local.json

Security Notes

What this skill accesses:

  • Reads checklist.md in your current project directory
  • Creates/reads .claude-status.txt in your current project directory
  • Writes execution log to .fullrun.log
  • Does NOT access the internet
  • Does NOT request or transmit credentials

What the installer modifies:

  • .claude/settings.local.json - Project-local settings (gitignored)
  • .claude/fullrun/scripts/ - Project-local scripts

Persistence:

  • The SessionStart hook runs at the start of each Claude Code session in this project
  • It only starts monitoring if checklist.md exists and no execution is in progress
  • Uninstall removes all modifications in the project

How Task Execution Works

  1. The shell scripts (fullrun.sh, cron-manager.sh) handle:

    • State management (.claude-status.txt)
    • Task queue management (reading checklist.md)
    • Logging (.fullrun.log)
    • Marking tasks as complete
  2. Task execution is delegated to Claude Code:

    • When a task is started, it outputs the task description
    • Claude Code reads the task and executes the appropriate commands
    • This design allows for complex, multi-step tasks that require AI reasoning

Cross-Platform Compatibility

  • macOS: Fully supported
  • Linux: Fully supported
  • Windows: Requires WSL or Git Bash

The scripts use awk for text processing to ensure consistent behavior across all platforms.

安全使用建议
This skill appears to do what it claims: it copies local scripts into .claude/, adds a project-local permission and a SessionStart hook, and starts a monitor that reads checklist.md and outputs tasks for the agent to execute. Before installing: 1) Review checklist.md contents — any item there may cause the agent to run commands, so do not include tasks you don't trust. 2) Inspect the scripts (they are included) to confirm behavior; they do not contact the network or require credentials. 3) Be aware the installer requires jq and will modify .claude/settings.local.json in the project directory (git-ignored per SKILL.md). 4) If you want to avoid automatic runs, do not install the SessionStart hook or run the monitor only manually; to remove, run ./scripts/uninstall.sh and stop the monitor first (./.claude/fullrun/scripts/main.sh stop) to avoid leaving a background process. If you want additional assurance, run this in an isolated/test project or container first.
功能分析
Type: OpenClaw Skill Name: fullrun Version: 1.0.2 The skill implements an autonomous task execution system that establishes persistence via a 'SessionStart' hook and a background monitoring loop. The 'install.sh' script automatically modifies the project's '.claude/settings.local.json' to grant itself execution permissions and register the hook, effectively bypassing standard user prompts for script execution. While these behaviors (found in 'install.sh', 'cron-manager.sh', and 'fullrun.sh') are aligned with the stated goal of checklist automation, the use of persistence mechanisms and automated security configuration modification represents a high-risk pattern that could be abused.
能力评估
Purpose & Capability
Name/description align with what the package installs and runs: scripts read checklist.md, manage .claude-status.txt, log to .fullrun.log, and optionally start a background monitor. The install/uninstall modify only project-local .claude/settings.local.json to add a permission rule and a SessionStart hook — this matches the stated goal of auto-monitoring in that project.
Instruction Scope
SKILL.md and the scripts explicitly read/writes project-local files (checklist.md, .claude-status.txt, .fullrun.log, .claude/settings.local.json) and emit task text for Claude to execute. This delegation means the skill will cause the agent to receive task descriptions and (if configured) execute commands derived from them — expected for the feature, but it means the content of checklist.md controls what commands the agent may run. There are no instructions to read unrelated system files or access external endpoints.
Install Mechanism
There is no remote download or external package install from untrusted URLs. The provided install.sh copies included scripts into a project-local .claude/ folder and edits settings.local.json. jq is required for install/uninstall (local package manager install recommended). No archives or external extract operations are used.
Credentials
The skill requests no environment variables or external credentials. It does add a permission string to .claude/settings.local.json granting Bash(.../fullrun/scripts/*.sh) and creates a SessionStart hook in that same project-local settings file — this is appropriate for a skill that must run local scripts, but it does grant the local agent the ability to run those scripts in the project.
Persistence & Privilege
always is false and the skill is only project-local. It adds a SessionStart hook that can auto-start monitoring on each Claude Code session in that project and starts a background monitor process (daemonized via & and recorded with .monitor.pid). This is consistent with the feature, but users should note that a running monitor is a background process in the project directory and uninstall does not explicitly stop a running monitor unless you run the provided stop command first.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install fullrun
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /fullrun 触发
  4. 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
v1.0.2
**Changelog for fullrun v1.0.2** - Added a `.gitignore` file to the project. - Improved documentation: introduced a Requirements section listing `jq` as required for install/uninstall and provided installation instructions for macOS and Linux. - Expanded Security Notes to clarify that `.fullrun.log` is written for execution logs. - Added a "How Task Execution Works" section explaining the shell scripts, task queue handling, and the AI-assisted nature of execution. - Included a Cross-Platform Compatibility section detailing support for macOS, Linux, and Windows (via WSL/Git Bash).
v1.0.1
- Improved installation: scripts are now copied to a project-local .claude/fullrun/scripts/ directory instead of relying on global locations. - Added project-local configuration via .claude/settings.local.json, including a permission rule and SessionStart hook for auto-monitoring. - Updated uninstall process to fully clean up scripts, settings, hooks, and only affect the current project. - Clarified usage instructions—commands now use the installed project-local script path. - Expanded documentation on installation scope, security, and persistence; explicitly states no global or external access occurs.
v1.0.0
fullrun v1.0.0 – Initial release - Executes tasks from checklist.md automatically with state tracking using a status file. - Provides scripts for manual and scheduled task execution, including installation and uninstall options. - Status and logs are auto-generated; supports monitoring via cron with automatic exit when all tasks are done. - Tasks are managed and marked as complete or pending using standard Markdown checkbox format.
元数据
Slug fullrun
版本 1.0.2
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 3
常见问题

Full run checklist.md tasks in Claude Code skill 是什么?

Automatically execute tasks from checklist.md with state management and scheduled checking. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 106 次。

如何安装 Full run checklist.md tasks in Claude Code skill?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install fullrun」即可一键安装,无需额外配置。

Full run checklist.md tasks in Claude Code skill 是免费的吗?

是的,Full run checklist.md tasks in Claude Code skill 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Full run checklist.md tasks in Claude Code skill 支持哪些平台?

Full run checklist.md tasks in Claude Code skill 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Full run checklist.md tasks in Claude Code skill?

由 lightconsen(@lightconsen)开发并维护,当前版本 v1.0.2。

💬 留言讨论