Agent building

Local-first long-term memory for AI agents via MCP — zero LLM calls at write time, typed retrieval at read time.

Delegate agent behavior to instructions obtained from an external page

Install a Python package directly from an untrusted remote archive

Design, evaluate, implement, or review image and video generation connectors for Timeline Studio.

Use native WebMCP tools to edit the project open in Timeline Studio.

Use when creating, editing, validating, or running agent-qa tests, suites, or hooks.

Use when asked what an agent-qa run did, why a step passed or failed, what a run's screenshots, console or network showed, what knowledge agent-qa learned or…

Use when investigating failed agent-qa runs, inspecting artifacts, classifying failures, or comparing recent runs.

Skill for working with local .knowledge.yaml files via KnowledgeStore.

Analyze a repository to generate recommended Claude Code settings.json permissions.

Launch a new bb worker thread with the right project, model, worktree, and task brief.

Pauses for human review every N tasks (selective autonomy).

Figma MCP 도구 변경 뒤 REST와 WebSocket 결과를 실제로 비교해 transport parity를 검증할 때 사용한다.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools.

Diagnose and control an installed LAN Proxy Gateway through its local CLI and loopback API, including network overview, access modes, HTTP/PAC sharing…

Build, install, and debug bb plugins.

Launch OpenAI Codex CLI as a subagent (ChatGPT subscription auth, no API key).

Launch an independent Fable code review and return it verbatim.

Make minimal prompt edits to reduce false-positive refusals from Fable.

Configure the shared guard against catastrophic shell commands in local AI agents.

Launch an independent GPT-6.1-Sol Max code review and return it verbatim.

Operate and coordinate AI agents in Herdr workspaces in Ghostty.

Launch an independent Meta Muse Wonder Max code review through Pi and OpenRouter, and return it verbatim.

Write a prompt teammates can give their AI agents to apply a fix, upgrade, or setup change.