437 boosters for "agents" — open source, verified from GitHub, ready to install
"name": "@paretools/jvm", "version": "0.16.1", "mcpName": "io.github.Dave-London/pare-jvm",
PSI is a structured Plan-Spec-Implement workflow that guides developers through documentation-first development with test-driven implementation. It benefits teams wanting disciplined, traceable development processes with clear artifact generation.
"description": "A curated skills plugin for practical AI-era craft, judgment, and delivery.", "name": "lynxlangya", "email": "lynxlangya@gmail.com"
Use this skill when you need to run commands with network isolation, restrict network access to approved domains, or execute AI agents in a sandboxed environment with controlled network access. AWF is a network firewall for agentic workflows that provides: The separator divides firewall options fro
MCP Server that enables AI agents to analyze and auto-optimize Linux kernel schedulers using eBPF, helping systems engineers improve performance through intelligent workload profiling and optimization strategies.
Process MCP Server enables AI agents to execute system commands with structured output, timeouts, and signal handling across Cursor, Claude, and Copilot. Developers building AI-powered tools and automations benefit from token-efficient command execution with safety controls.
Swift MCP Server provides structured access to Swift build, test, and package manager data for AI agents, enabling seamless integration with Claude, Cursor, and Copilot for iOS/macOS development workflows.
Claude Agent SDK for Elixir enables developers to build AI agents with subagents—specialized agent instances that isolate context, run tasks in parallel, and apply focused instructions. Elixir developers building intelligent applications benefit from this native SDK integration.
31 specialized agents covering every department from solo founder Day 0 to IPO. 22 frameworks with tactical playbooks, compliance guides, and process maps. Before loading any agent files, consult . It contains:
You are an expert research engineer. Produce evidence-grounded, testable proposals. 1. Decompose the problem into concrete technical sub-problems and constraints. 2. Survey broadly, then go deep on high-potential directions.
"name": "claude-code-cat", "owner": { "name": "cowwoc" }, "source": "./plugin",
ClawdChat analyzes Moltbook (an AI agents social network) to extract core problems, solutions, and community insights, generating visual reports. It helps AI developers and researchers understand what the AI community is collectively focused on and discover reusable problem-solving patterns.
"name": "claudekit", "description": "Comprehensive toolkit for Claude Code — 44 skills, 20 agents, and an interactive setup wizard for rules, modes, hooks, and MCP servers.", "url": "https://github.com/duthaho"
Persistent local memory for AI agents. Save, recall, and search project decisions as local JSON. Zero cloud, zero infrastructure.
rtfmbro-mcp provides AI coding agents with always-up-to-date, version-specific package documentation to prevent outdated knowledge errors. Developers and teams using Claude/Copilot for agentic coding tasks benefit from accurate, real-time API references.
Run AI agents in parallel. Create agents with roles, trigger them on demand or on a schedule, and collect results. If this succeeds, skip to Step 3. If npm is not available, build from source:
CamoFox cheat sheet (ultra-compact). Canonical details: AGENTS.md. WORKFLOW (snapshot-first) 1) open/create tab -> 2) snapshot -> 3) pick refs (eN) -> 4) click/type/fill/press -> 5) snapshot again after DOM/nav changes.
"name": "@apitap/core", "version": "1.10.1", "description": "Intercept web API traffic during browsing. Generate portable skill files so AI agents can call APIs directly instead of scraping.",
Brain in the Fish evaluates documents (essays, policies, contracts, clinical reports, surveys) against evaluation criteria using a panel of AI agents. Each agent's mental state exists as OWL ontology. Scoring is grounded in an Evidence Density Scorer (EDS) that makes hallucination mathematically det
The team can't find existing standards. Help them build a rubric. Ask: what does the output look like when it's right? Get specific, measurable answers. File sizes, response times, value ranges, visual correctness, behavioral expectations. If the user or team can't quantify it, ask what they'd check
anyclaw turns any API, website, or CLI tool into agent-ready commands. Use it to search for packages, install them, and run commands directly from the terminal. Common packages you can install: Run or to discover more.
Turkey-build is a multi-agent orchestration system for building production-ready applications across 7 modes (greenfield, iteration, bugfix, refactor, UI polish, migration, audit), with PM-driven coordination and runtime verification for teams that need structured, quality-gated development workflows.
"name": "harness-mcp-v2", "description": "Give AI agents full access to the Harness.io platform — manage pipelines, deployments, cloud costs, chaos engineering, feature flags, SEI, and 125+ resource types through 11 MCP tools", "main": "build/index.js",
"mcpName": "io.github.sverklo/sverklo", "version": "0.29.2", "description": "Local-first repo-memory MCP for coding agents. Best for relationship-heavy edits: symbols, callers, dependencies, diff review, and git-pinned decisions before code changes. Start with a no-write proof receipt; use grep/ripg
