{"data":[{"slug":"agentsatlas","title":"agentsatlas","description":"AgentsAtlas is a minimal, opinionated end-to-end workflow for Claude Code (also available as Codex skills). Eight slash commands take a project from setup through planning, execution, review, and milestone completion:\n\n/atlas:init, \n/atlas:plan, \n/atlas:execute,\n/atlas:status, \n/atlas:sync, \n/atlas:triage, \n/atlas:review, \n/atlas:complete. \n/atlas:execute \n\nRuns each 3–5-task plan in a fresh subagent (clean ~200k-token context) so quality doesn't degrade across a long run, while a small CLAUDE.md plus .planning/STATE.md and ROADMAP.md keep session continuity without context bloat. \n\nIt also ships 16 development \"discipline\" skills: debugging, testing,\nverifying, refactoring, security-audit, scaffolding, committing, creating-pr, and more enforcing root-cause-first investigation, evidence-before-claims verification, and test-first development. \n\n# Install globally (available in all projects)\nnpx agents-atlas --global\n\n# Or install locally (current project only)\nnpx agents-atlas --local\n\nMIT licensed; no telemetry, no network calls beyond Anthropic, and no bypass-permissions requirement.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/AvinashP/AgentsAtlas.git"},{"slug":"agentpowers","title":"agentpowers","description":"AgentPowers is a marketplace plugin that lets you search, browse, purchase, install, and manage premium AI skills and agents directly inside Claude Code. It provides 26 MCP tools covering marketplace discovery (search, categories, reviews, security scans, seller profiles), full account management (login, logout, profile), Stripe-powered purchase workflows with auto-install, and multi-platform skill management across 12+ AI tools including Claude Code, Claude Desktop, Cursor, Codex, Windsurf, Gemini CLI, and more. Includes 4 MCP resources for proactive context and 2 guided prompts for skill discovery and purchase flows.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/AgentPowers-AI/agentpowers-plugin.git"},{"slug":"agentops","title":"agentops","description":"Enterprise guardrails, delivery lifecycle, and self-evolution for Claude Code. Wraps every session in 7 security layers (path validation, command validation, injection scanning, credential redaction, exfiltration detection), structures work with the STAR methodology, and orchestrates full project builds from vision to merged PR through an 8.5-phase lifecycle with TDD enforcement, wave-based parallel execution, and two-stage code review. Includes 37 commands, 44 hooks, 12 specialist agents, 49 templates, and 32+ feature flags.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/garethdaine/agentops.git"},{"slug":"agentnews","title":"agentnews","description":"Connect Claude to AgentNews — the frontpage of the agentic internet. Read the latest AI agent news, search posts, and submit content via MCP. Includes slash commands for quick access and a skill that automatically surfaces relevant agent news.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/Kaizor7/agentnews-plugin.git"},{"slug":"agentmancy","title":"agentmancy","description":"AI Agent & Skill Builder for Claude Code, OpenCode, and Gemini.\n\nA free alternative to summonaikit that leverages your already existing subscriptions to Claude.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/vinngo/agentmancy.git"},{"slug":"agentiqa-plugin","title":"agentiqa-plugin","description":"Repo not found","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/Agentiqa/agentiqa-plugin.git"},{"slug":"agentiqa","title":"agentiqa","description":"AI-powered QA testing agent for web and mobile apps. Agentiqa explores your app visually - like a real user with fresh eyes - and reports bugs with severity, confidence scores, and step-by-step reproduction instructions. No selectors, no scripts, no test code to maintain. Just describe what to test in plain English.\n\nSupports web (any URL or localhost), Android (emulator/device), and iOS (simulator/device). Finds visual bugs, logical errors, UX issues, and accessibility problems that unit tests and linters miss.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/Agentiqa/agentiqa-plugin.git"},{"slug":"agenticmail","title":"agenticmail","description":"Give every Claude Code subagent its own real email address and phone number, all self hosted on the user's machine. AgenticMail runs a local mail server (Stalwart in a Colima or Docker container) so each agent has a working `<name>@localhost` inbox, an identity, an API key, and a persona. When a teammate is CC'd on an email they wake up as a Claude Code subagent under your existing Claude OAuth, read the full thread, decide if it is their turn, and either reply to all or stay silent. The thread is the workspace and the audit trail. There is no central orchestrator, no separate Anthropic key per agent, no data leaving your machine, and no polling because everything is push based over SSE. The plugin exposes three skills (`install`, `create-agent`, `coordinate`) that handle the one time bootstrap and let the host session kick off multi agent work with a single email. Behind the plugin sit five npm packages doing the real work: an Express API, an MCP server with 62 tools across email, SMS, contacts, drafts, templates, rules, search, scheduling, and agent coordination, a dispatcher daemon, a core SDK, and the CLI. Reliability rails include a per agent per thread wake budget that stops reply loops, a 60 second recent reply check in every persona so two agents who both think it is their turn back off, and an outbound content guard that holds risky outbound mail for owner approval. Tested on Node 22 and Node 25 with 429 passing tests across the workspace.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/agenticmail/agenticmail.git"},{"slug":"agentic-teams","title":"agentic-teams","description":"A modular plugin that packs specialised agents into teams and allows user to interact with them at the higher level of abstraction. Like with real-world company departments.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/rustamfi/agentic-teams.git"},{"slug":"agentic-swe","title":"agentic-swe","description":"agentic-swe is a Claude Code plugin that turns a normal repo session into a structured software-engineering pipeline—without a separate runtime.\nIt ships markdown policies, phase prompts, slash commands, templates, and 135+ specialist subagents. Work is organized with explicit states, human gates (e.g. ambiguity and approval), evidence-friendly artifacts under .worklogs/<id>/, and three pipeline tracks (lean, standard, rigorous) so you can match rigor to risk. Session hooks load policy early; /install helps merge CLAUDE.md into a target project safely.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/surajSFDC/agentic-swe.git"},{"slug":"agentic-security","title":"agentic-security","description":"Agentic-Security is a powerful Claude Code plugin that automatically performs Application Security Testing (SAST, SCA, secrets detection, and more). Think of it as the easy button for making your Claude-generated code safe and secure.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/Clear-Capabilities/agentic-security.git"},{"slug":"agentic-guardrails","title":"agentic-guardrails","description":"A set of strict, senior-level engineering guardrails and security standards for AI coding agents.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/l-filice89/agentic-guardrails.git"},{"slug":"agentic-council","title":"agentic-council","description":"Convene a team of specialist agents out of a 20-agent roster in a 3-round deliberation council on your hardest engineering decisions. Walk away with a unified design and a phased build plan.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/dtsong/agentic-council.git"},{"slug":"agentic-commerce","title":"agentic-commerce","description":"13 commerce plugins covering Shopify, Magento, BigCommerce, WooCommerce, Salesforce, Stripe, and agentic commerce protocols.","developer":null,"category":"development","reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/OrcaQubits/agentic-commerce-claude-plugins.git"},{"slug":"agentic-beta-testers","title":"agentic-beta-testers","description":"AI-powered browser testing against any URL using personality-driven agents -- speedrunners, chaos gremlins, skeptical executives -- each surfacing different categories of usability and reliability issues.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/rjspence3/claude-beta-tester.git"},{"slug":"agented","title":"agented","description":"A text editor for LLMs, not humans. Optimized for the model's cost model: fewer round trips per task (no   Read-before-Edit; conflict responses carry the new content, so you reconcile in one call instead of  pre-reading every time), tighter token budget (lean tab output, not JSON envelopes; ~5x denser than the  built-in Read/Edit shape), inline LSP diagnostics on every save (gopls, rust-analyzer-with-clippy,  tsserver+eslint findings come back as diag lines instead of round-tripping through cargo / go build),  reactive drift detection (external editor or formatter writes are folded into the undo tree as new  edits, not silently clobbered or lost), and a branching undo tree that remembers the branches the agent  abandoned — because that's often where the interesting work was. Three-way merge for concurrent agents, atomic multi-file refactors, cross-session memory via per-file annotations.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/frane/agented.git"},{"slug":"agent4s","title":"agent4s","description":"Scala code intelligence for AI coding agents. 35 commands — search,\njump-to-definition, find references, call-graph, dead code detection, semantic\nrename, bug-hunt with taint analysis, scaffolding — all without a build\nserver or compilation. Cold index 2.7s, warm 349ms on 18k files. Bug-hunt\nscans 45 vulnerability patterns (SQL injection, XSS, SSRF, hardcoded secrets, weak crypto, concurrency bugs) with cross-file taint analysis. SemanticDB integration for type-aware mode when compiled artifacts are available. Native binaries for macOS, Linux, and Windows. Works as a Claude Code plugin, MCP server (Cursor, Windsurf, Cline), or standalone CLI.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/scala-digest/agent4s.git"},{"slug":"agent-trace-triage","title":"agent-trace-triage","description":"Agent Trace Triage is a Claude Code plugin for developers building agentic AI systems (LangGraph, CrewAI, custom tool loops, MCP agents).\n\nWhen an agent run fails, stuck in a loop, wrong tool, or burning tokens. the user runs /agent-trace-triage with a JSON/JSONL trace file. The plugin:\n\n• Parses traces (JSONL, OpenAI tool_calls, partial LangSmith/OTEL-style exports)\n• Detects loops deterministically (identical repeat, ping-pong, retry-without-progress) via bundled Node scripts\n• Classifies failures into five buckets: tool selection, arguments, execution, orchestration, recovery policy\n• Writes a markdown triage report with targeted fix recommendations\n• Scaffolds regression tests (pytest / vitest templates)\n\nNo MCP servers, no external API calls, no npm dependencies. \n\nRequires Node.js 18+ for local scripts only. MIT licensed.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/WasayAbid/agent-trace-triage.git"},{"slug":"agent-tasks","title":"agent-tasks","description":"Pipeline-driven task management for AI coding agents. An MCP server with stage-gated pipelines, multi-agent collaboration, and a real-time kanban dashboard. Tasks flow through configurable stages — backlog, spec, plan, implement, test, review, done — with dependency tracking, approval workflows, artifact versioning, and threaded comments.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/keshrath/agent-tasks.git"},{"slug":"agent-synapse","title":"agent-synapse","description":"Let multiple Claude Code sessions talk to each other across projects. Each session gets a name, sends messages, checks its inbox, and sees who's online.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/DisposableByDefault/agent-synapse.git"},{"slug":"agent-smith","title":"agent-smith","description":"Agent Smith adds two slash commands to Claude Code: /analyze-agent performs a full configuration audit across 7 evaluation pillars (Security, Instruction Clarity, Configuration Quality, Context Efficiency, Command Design, Hook Safety, MCP Integration), scores each area, identifies issues by severity, and walks you through an interactive fix workflow. /create-agent scaffolds a new configuration with security deny rules and best practices. The tool is honest about its scope — it only measures user-configurable components and clearly states what's outside its reach.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/maxencemeloni/claude-code-agent-smith.git"},{"slug":"agent-runway","title":"agent-runway","description":"Prevents subagent tech debt by injecting project architectural context (module boundaries, CLAUDE.md rules, conventions) into every subagent's prompt. Validates code placement and conventions after writes with self-correction directives.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/rennf93/agent-runway.git"},{"slug":"agent-recall","title":"agent-recall","description":"Persistent memory for AI coding agents. SQLite knowledge graph with scoped entities, MCP tools, and LLM-summarized briefings.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/mnardit/agent-recall.git"},{"slug":"agent-protocols","title":"agent-protocols","description":"Structured engineering protocols that make AI coding agents work like senior engineers.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/arneesh/agent-protocols.git"},{"slug":"agent-ping","title":"agent-ping","description":"Plays a sound when Claude finishes, asks a question, or needs permission — so you can step away and come back when needed. Configurable sounds, volume, and alert modes.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/DavidWilsby/agent-ping.git"},{"slug":"agent-memory","title":"agent-memory","description":"Save 60-90% on LLM token costs with intelligent memory compression. agent-memory automatically compresses tool output into structured observations, shares context across agents via a memory bus, and injects only relevant memory into each prompt — keeping your token budget under control. Features: auto-compression hooks (PostToolUse), token-budgeted context injection (SessionStart), semantic search via FTS5, cross-session persistence, and a token economics dashboard showing compression ratios and savings.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/Keshab0310/agent-memory.git"},{"slug":"agent-manager","title":"agent-manager","description":"Spawn and manage autonomous background agents with persistent state across sessions","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/devhimanshulohani/claude-agent-manager.git"},{"slug":"agent-knowledge","title":"agent-knowledge","description":"Cross-session memory for AI coding agents. A git-synced Markdown knowledge base with hybrid semantic + TF-IDF search, typed knowledge graph (11 edge types with directed BFS traversal), confidence/decay scoring, and automatic session distillation with secrets scrubbing. Reads session history from Claude Code, Cursor, and OpenCode.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/keshrath/agent-knowledge.git"},{"slug":"agent-handoff","title":"agent-handoff","description":"Strict 3-stage handoff workflow for coding agents — plan → execute → verify — with disk-backed state for cross-context handoff.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/WillowRyu/agent-handoff.git"},{"slug":"agent-guardrails-template","title":"agent-guardrails-template","description":"Core safety skills for AI-assisted development: Four Laws, Three Strikes, production-first, scope validation, and environment separation. 11 skills enforce guardrails on every operation so agents build at full velocity without breaking production.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/TheArchitectit/agent-guardrails-template.git"},{"slug":"agent-estimate","title":"agent-estimate","description":"Effort estimation for AI coding agents. PERT three-point estimation with METR reliability thresholds, modifier stacks (spec clarity, warm context, agent fit), and wave planning for multi-agent parallel execution. Supports single tasks, batch files, and GitHub issues.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/haoranc/agent-estimate.git"},{"slug":"agent-discussion","title":"agent-discussion","description":"Coordinate multi-agent debates across different AI platforms (Claude Code, Antigravity, Copilot, Gemini CLI, etc.) using a shared file protocol. Each agent reads one skill and handles everything autonomously — intros, turn-taking, and consensus.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/cyrusxyl/agent-discussion.git"},{"slug":"agent-discovery","title":"agent-discovery","description":"Agent Discovery lets developers discover, review, install, and manage AI agent configurations from a curated catalog of 687+ entries — with zero setup. It ships a pre-built SQLite index of agents, skills, and instructions from awesome-copilot and GitHub's Agent Factory, so search is instant and requires no API keys or authentication. The interactive /recommend flow analyzes your project's tech stack, surfaces relevant agents with explanations, then guides you through reviewing content before installing, customizing in your editor, or assembling multiple agents into a coordinated team with an agentic lead. Additional /list and /edit commands let you manage everything you've installed without leaving Claude Code.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/svmnikhil/agent-discovery.git"},{"slug":"agent-discover","title":"agent-discover","description":"MCP server registry and on-demand proxy for AI coding agents. Browse the official MCP Registry, install/activate/deactivate servers from a local dashboard, and proxy their tools with namespace prefixing. Per-server secrets, health probes with error-count tracking, tool-call metrics, and a real-time call log via WebSocket.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/keshrath/agent-discover.git"},{"slug":"agent-comm","title":"agent-comm","description":"Agent-agnostic intercommunication system. Lets AI coding agents — talk to each other, share state, and coordinate work in real time.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/keshrath/agent-comm.git"},{"slug":"agent-blueprint-skills","title":"agent-blueprint-skills","description":"Open-source AI agent skills for enterprise deployment. Three skills: (1) ServiceNow AI Agent Studio reference with data model, entity mapping, tool types, prompting patterns, and browser navigation. (2) Vendor-agnostic agent deployment methodology with phased rollout, pilot-first approach, and test gates. (3) Multi-tool research agent with automatic depth routing from free to paid tools. Works with Claude Code, OpenAI Codex, and any coding agent via the Agent Skills open standard.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-15T00:00:01.383Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/agent-blueprint/agent-blueprint-skills.git"}],"total":2559,"page":60,"per_page":36,"observed_at":"2026-10-15T00:00:01.383Z","source_counts":{"web":341,"demo":13,"skills":5,"official":315,"community":2283,"knowledge-work":123}}