security-scan
Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-08
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- tasks
- description
- Coordinate dependency-aware project tasks across independent Codex, Claude Code, Kimi and human sessions using Beads. Use for shared plans, claiming work, task handoffs, acceptance and agent monitoring snapshots.
02 资源文件 7
- 参考文档prompt.md5.4 KB
- 参考文档references/monitoring.md2.4 KB
- 参考文档references/plan.json1.2 KB
- 参考文档references/service.md8.7 KB
- 脚本scripts/maintenance.py28.6 KB
- 脚本scripts/service.py7.2 KB
- 脚本scripts/tasks.py25.2 KB
03 SKILL.md 正文
Shared tasks
Run the workflow in prompt.md using this skill's scripts/tasks.py.
Beads holds task state; Git holds code; Markdown explains decisions and context.
The helper does not launch agents or models. Each runtime uses it directly.
- For first setup or moving to a server, read service setup.
- For planning, use the plan example.
- For Web monitoring integration, read the observation contract.
Use one live backend per project. Give each independent execution a fresh session ID. Readiness and claims come from Beads; a Markdown checkbox, local Git branch or old handoff is not a current ownership grant.
Task acceptance and Git publication are separate. Preserve existing repository verification, review and delivery authority. Only record checks actually run.
04 同仓库更多 Skills
remotion-video-creation
Best practices for Remotion - Video creation in React. 29 domain-specific rules covering 3D, animations, audio, captions, charts, transitions, and more.
hotcook-recipes
暂无简介
code-helper
Code review and assistance skill
research-assistant
Web research assistant skill using Brave Search MCP
x-api
X/Twitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.
workspace-surface-audit
Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows. Use when the user wants help setting up Claude Code or understanding what capabilities are actually available in their environment.