TypeClaw Plugins Guide

Name: TypeClaw Plugins Guide
Rating: 93 (1 reviews)
Author: typeclaw

Trust Score 93/100

Comprehensive authoring and operational guide for writing and operating TypeClaw plugins: defining plugins, tools, subagents, cron jobs, skills, and hooks.

triggers:definePlugintypeclaw pluginplugin cronsession.promptsubagentdefineTool

GitHub SKILL.md

What it does

This skill documents how to author, configure, and operate TypeClaw plugins. It explains plugin structure (definePlugin API), boundaries between plugin code and the runtime, naming/derivation rules, contributed artefacts (tools, subagents, cronJobs, skills, skillsDirs, hooks), and operational failure modes. The guide includes examples for minimum plugins, config schemas, CLI commands, and best practices for cron handlers, handler vs exec choices, and permission checks.

When to use it

Use this skill when developing new TypeClaw plugins, debugging plugin load errors, designing plugin cron jobs or commands, or when you need to register tools/subagents/hooks correctly. It's targeted at TypeScript developers building integrations or extending the TypeClaw runtime.

What's included

Scripts: none bundled (has_scripts=false)
References: numerous inline examples and architecture notes inside the SKILL.md body
Instructions: concrete code patterns for definePlugin, defineTool, subagent declarations, cron job kinds (prompt/exec/handler), command surfaces (container/host/either), and common pitfalls with explicit error messages to watch for.

Compatible agents

Developer-facing agents that can explain TypeScript patterns and runtime registration flows (code assistants like Copilot, Claude Code, or other coding-focused LLMs).

Audit Summary

Comprehensive TypeClaw plugin authoring and operation guide covering definePlugin, tools, subagents, cron jobs, skills, hooks, commands, config, failure modes, and pitfalls. No scripts to execute — purely documentation. Well-structured with progressive disclosure, verbatim error messages, and anti-goals. Serves as both a getting-started guide and a reference manual for the TypeClaw plugin system.

Watch Out

References Bun.spawn and ctx.exec patterns that could be misused if copied blindly
Skill is ~50KB of documentation — very long for a single SKILL.md

Notes

Pure documentation skill with no executable scripts. Exceptionally thorough coverage of the TypeClaw plugin API surface including hooks, commands, cron jobs, subagents, and failure modes. No security concerns — no remote code execution patterns, no credential handling, no destructive commands. One consideration: the skill is very long (~50KB) which may challenge context windows.

Information

Repository: typeclaw

Trust Score

Overall93

Security95

Code Quality92

Architecture88

Usefulness72

Related Skills

Development Worktree

Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.

Readwise Reader Document Management

Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.

Full Stack Builder

End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.

ezBookkeeping API Tools

Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi

Tmux Bridge

Give an agent controlled access to a local tmux terminal bridge so it can run shell commands, capture output, and manage sessions on the user's machine.

SourceSage CLI

Generate concise, LLM-friendly repository summaries (Markdown) using the SourceSage CLI — supports lite mode, language switching, and targeted repo analysis.

Nit (Nitter CLI)

Terminal client to browse tweets, view profiles, and search posts via Nitter instances without opening a browser.

hn — Hacker News CLI

Terminal-based Hacker News client with a CLI and optional interactive TUI for browsing top/new/best/ask/show/jobs stories, viewing threads with nested comments,

Back to Skills