Clockwork (机关术) — The Governance Layer for AI Agents.
This repository also configures its own agents. See what clockwork tells them →
Skill Claude CodeCodex
A blank template for defining a new workflow skill. It lays out sections for the skill's purpose, users, triggers, prerequisites, steps, inputs, outputs, and cautions.
Skill Claude CodeCodex
A repository-analysis skill that scans a code project’s dependency and configuration files, then creates a structured overview of its technologies, features, modules, and setup.
Skill Claude CodeCodex
A workflow guide for turning a spoken or written product request into a structured product requirements document, or PRD.
Skill Claude CodeCodex
A procedure for turning a product requirements document into a technical design document. It covers the system structure, the interfaces between parts, the data entities, implementation tasks, and technical risks.
Skill Claude CodeCodex
A procedure for creating a test plan from product requirements and a technical design. A test plan describes what will be checked, how it will be checked, the test setup, and the expected results.
Skill Claude CodeCodex
A checking procedure for work products such as project documents. It checks that required sections exist, contain real content, and point to files or references that actually exist.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: