422 boosters for "tool" — open source, verified from GitHub, ready to install
You are a CLI development specialist focused on building excellent command-line tools. You understand terminal conventions, argument parsing, and creating tools that feel native to the shell environment. 1. Define interface - Commands, flags, arguments 2. Implement core logic - Business functionalit
Use this agent when documentation in the `architecture/` directory needs to be updated or created for a specific file after implementing a feature, fix, refactor, or behavior change. Launch one instance of this agent per file that needs updating. This agent maintains the *contents* of architecture documentation files — it does not decide which files exist or how the directory is organized.\n\nExamples:\n\n- Example 1:\n Context: A developer just finished implementing OPA policy evaluation in the sandbox system.\n user: "I just finished implementing the OPA engine in crates/openshell-sandbox/src/opa.rs. Update architecture/sandbox.md to reflect the new policy evaluation flow."\n assistant: "I'll launch the arch-doc-writer agent to update the sandbox architecture documentation with the new OPA policy evaluation details."\n <uses Task tool to launch arch-doc-writer with instructions to update architecture/sandbox.md>\n\n- Example 2:\n Context: A refactor changed how the HTTP CONNECT proxy handles allowlists.\n user: "The proxy allowlist logic was refactored. Please update architecture/proxy.md."\n assistant: "Let me use the arch-doc-writer agent to synchronize the proxy documentation with the refactored allowlist logic."\n <uses Task tool to launch arch-doc-writer with instructions to update architecture/proxy.md>\n\n- Example 3:\n Context: After implementing a new CLI command, the assistant proactively updates docs.\n user: "Add a --rego-policy flag to the CLI."\n assistant: "Here is the implementation of the --rego-policy flag."\n <implementation complete>\n assistant: "Now let me launch the arch-doc-writer agent to update the CLI architecture documentation with the new flag."\n <uses Task tool to launch arch-doc-writer with instructions to update architecture/cli.md>\n\n- Example 4:\n Context: A user wants high-level overview documentation for a non-engineering audience.\n user: "Update architecture/overview.md with a non-engineer-friendly explanation of the sandbox system."\n assistant: "I'll launch the arch-doc-writer agent to create an accessible overview of the sandbox system for non-technical readers."\n <uses Task tool to launch arch-doc-writer with audience=non-engineer directive>\n\n- Example 5:\n Context: Multiple files need updating after a large feature lands.\n user: "I just landed the network namespace isolation feature. Update architecture/sandbox.md and architecture/networking.md."\n assistant: "I'll launch two arch-doc-writer agents — one for each file — to update the documentation in parallel."\n <uses Task tool to launch arch-doc-writer for architecture/sandbox.md>\n <uses Task tool to launch arch-doc-writer for architecture/networking.md>
Heuristic scoring (no AI key configured).
Refactor $ARGUMENTS to improve: 2. Maintainability 4. Modern Patterns
A debugging assistant that systematically analyzes errors, identifies root causes, and implements minimal fixes with verification for TypeScript and UI components. Ideal for developers working in Claude Code who need structured guidance on troubleshooting and fixing bugs.
Quoroom is an experimental open-source framework for building local AI agent systems with a Queen-Workers-Quorum architecture, designed for researchers and developers exploring multi-agent AI patterns with Claude and other LLMs.
A planning-first agent that generates structured task breakdowns before execution, helping developers clarify scope and avoid missteps on complex code operations. Ideal for teams using Claude in agentic workflows.
Comprehensive guide for Claude Code CLI tool, extensibility (agents/skills/output styles), and CLAUDE.md architecture. 1. Task verbs: create, build, debug, fix, deploy 2. Problem descriptions: slow, broken, failing
Guide users through the capabilities of this workspace setup. Use AskUserQuestion to guide the user: Based on response, show relevant tools:
Control tmux windows programmatically: create windows, send commands, capture output, and manage processes. Each window gets full screen space for easier output tracking. Window names are visible in the tmux status bar for easy identification. For commands that write to a file (cleaner than capturin
"description": "AI-native job queue for Bun — skills, MCP server (73 tools), custom agent, SQLite persistence, cron, priorities, retries, DLQ, webhooks", "name": "egeominotti" "homepage": "https://github.com/egeominotti/bunqueue",
This skill documents how to run the Parchi relay daemon, connect the browser extension as an agent, and use the CLI to drive browser automation. 1. Build everything: 2. Start the relay daemon (terminal A):
Custom codegen'd CDP SDK (every method from browserprotocol.json + jsprotocol.json gets a typed wrapper) plus a tiny HTTP server that holds one persistent CDP . The CLI auto-starts the server on first use and forwards JS snippets to it. The SDK lives in the skill's directory. In the rest of this d
A Chrome extension that integrates a PHP/Laravel console directly into Windsurf DevTools via Spatie's web-tinker package, enabling developers to execute PHP commands without leaving their IDE.
"name": "claudeforge", "description": "CLAUDE.md lifecycle toolkit: initialise, enhance, sync, and modularise CLAUDE.md files with a 150-line cap, automatic chaining, and Karpathy behavioural guardrails.", "name": "Alireza Rezvani",
"name": "shopify-plugin", "description": "Shopify developer tools for Claude Code — search Shopify docs, generate and validate GraphQL, Liquid, and UI extension code. Skill scripts send usage telemetry (queries, code, model/client identifiers) to shopify.dev by default; set OPTOUTINSTRUMENTATION=tru
Accessible workspace directory: !!<<<<||||workspace_dir||||>>>>!! When processing tasks, if you need to read/write local files and the user provides a relative path, you may choose to combine it with the above workspace directory to get the complete path. If you believe the task is completed, you ca
Since you are an expert, be definitive about recommendations.
<example type="invalid"> npm install --save-dev eslint npm uninstall lodash
Run this right after installing the Well plugin, or whenever the Well tools aren't responding. Walk the user through it conversationally — do not dump all steps at once if a step is already done. Installing the plugin auto-adds the MCP server (it is bundled in the plugin manifest). If the user just
"description": "Tidy3D simulation tools for Claude Code via tidy3d-mcp.", "name": "Flexcompute", "email": "support@flexcompute.com"
"name": "firefox-devtools-plugins", "name": "firefox-devtools-mcp", "source": "./plugins/firefox-devtools-mcp/",
AgentRecall is a persistent memory system. Default surface: 5 tools (two verbs + three essentials). Full surface: 18 tools via . This guide describes how and when to use them. AgentRecall requires the MCP server to be running. If tool calls fail with "unknown tool", the human needs to install it fir
A Python SDK for building production-ready agentic AI applications with Claude, featuring agents, handoffs, and guardrails for complex multi-agent workflows. Developers building AI agents and multi-tool systems will benefit from this lightweight, easy-to-learn framework.
