3,273 tagged ai-agents, measured the same way as everything else here.
Browse within: agentic-ai 236claude-code-plugin 217LLM 190cursor 176cli 131prompt-engineering 111agents-md 107Science 99agents 87ai-coding 80agentic-coding 62ai-tools 62skills 60ai-governance 54
Plugin Claude Code
Bundles 20 skills, 4 commands, 9 agents, 1 hook · 1,250 tokens together
Feature-delivery workflow engine: workspace → design → decisions → planning → implementation → review → refactoring → validation → documentation → propose → integrate. Phase skills with per-repo declination via .claude/workflow.md.
Plugin Claude Code
Bundles 3 skills, 7 agents · 563 tokens together
Swarm-orchestrated code refactoring and feature development with specialist agents. Supports multi-instance parallel agent spawning, blackboard context sharing, and interactive development gates.
Kokai-Data/japan-business-data
Plugin Claude Code
Bundles 19 skills, 8 commands, 7 agents, 1 MCP server · 2,259 tokens together
A connector for Japanese public business data, including company records, grants, tax information, financial filings, laws, government contracts, and trade data. It lets an AI agent quote these sources with citations.
Plugin Claude Code
Bundles 5 skills · 292 tokens together
Local-first codebase memory for coding agents: AST-aware context, durable decisions, failure records, review packs, and a local graph GUI. Twenty tools are advertised by default; writefile, patchfile, prompt compression, and bash are opt-in. Discipline protocols ship as MCP prompts rather than tools. Pre-2.0 tool nam.
salingnh/android-reverse-engineering-mcp
Plugin Claude Code
Bundles 1 skill, 1 command, 1 MCP server · 56 tokens together
Sandboxed Android reverse engineering with semantic program indexing, XREF/CFG queries and structured network evidence through MCP.
Plugin Claude Code
Bundles 1 skill, 1 command, 1 MCP server · 0 tokens together
Human-in-the-loop review interface for Claude Code - request structured feedback on plans, PRs, and implementations via browser UI.
Plugin Claude Code
Closes the memory loop mechanically: recall before changing code, recall before storing, and a turn that cannot end with an unmade decision left silent. Requires Node >= 23.6 (the hooks run TypeScript directly).
Plugin Claude Code
Bundles 2 skills · 273 tokens together
Operate and improve SCP governance for multi-agent teams: self-bootstrap and teardown of federated pods, generic role topology, EXEC PM / TEAM PM / ODIN separation, boot receipts, terminal locator identity, delegation receipts, terminal/CMUX delivery proof, heartbeat cadence, branch-visible claims, adversarial QA…
Plugin Claude Code
Bundles 2 commands · 0 tokens together
CHEF command and graph-first policy bundle for Claude.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 66 tokens together
Ariadne sensemaking for Claude Code — bundles the Ariadne MCP server and an analyst-workup skill so you can produce cited analytic notes for a target entity across graph, relational, full-text, and semantic stores.
Plugin Claude Code
Bundles 3 commands, 1 MCP server · 31 tokens together
Bridge Claude Code and Codex for second-opinion and brainstorming workflows.
Plugin Claude Code
Bundles 3 skills, 1 MCP server · 93 tokens together
A2A Mesh workflows for endpoint validation, approved task operations, and security-bounded MCP consumption.
Plugin Claude Code
Bundles 1 skill · 93 tokens together
Remove background noise, hiss, and static from speech recordings locally with Yaps.
Plugin Claude Code
Agent skills for pyenv-native — MCP-first Python version management.
contactandrewchl-wq/turtle-mcp
Plugin Claude Code
Bundles 26 skills · 1,660 tokens together
Memoria persistente y coordinación multi-agente para agentes de IA, eficiente en tokens.
Plugin Claude Code
Bundles 1 skill · 152 tokens together
Supports first-pass investigation for Japanese real-estate disclosure documents (Article 35 of the Building Lots and Buildings Transaction Business Act). Organizes checklists, public source references, PDF highlights, and xlsx-style reports when supported by the user environment.
Plugin Claude Code
Bundles 23 skills, 21 commands · 1,391 tokens together
Structured workflows that make LLMs think instead of just respond. Skills for verification, exploration, architecture, risk, feasibility, synthesis, and more.
Plugin Claude Code
Bundles 9 skills, 1 command · 698 tokens together
Full-lifecycle grant writing engine: org profile setup, opportunity discovery, RFP intake, evidence-driven research, professional drafting, budgets, mock-scorer review, and pipeline tracking. Produces submission-ready applications that read like a seasoned grant writer wrote them.
Plugin Claude Code
Bundles 2 skills · 102 tokens together
Governance layer for engineering-os: canonical policies, skills, and lifecycle hooks for an infrastructure engineer's AI working environment.
Plugin Claude Code
The human-in-the-loop for AI coding: verify every turn against the real diff, then make the agent run/screenshot/test and self-fix before finishing.
lucasyhzhu-debug/higgsfield-brief-to-pipeline
Plugin Claude Code
Bundles 1 skill · 103 tokens together
Turns a brief plus a folder of reference images into an optimal, credit-aware Higgsfield pipeline. Shows an HTML process preview as a mandatory approval gate before spending any credits, then executes stage-by-stage with auto-verification, human gates, and zero-credit deterministic text/dimension overlays.
Plugin Claude Code
Bundles 1 skill, 2 agents, 5 hooks · 197 tokens together
Agentic loop çekirdeği: append-only log, deterministik riskli-komut gate'i, confidence eşik makinesi (0.7/0.85 kodda sabit), critic zorunluluğu, review kuyruğu, kill-criteria, echo/critic ajanları, /start-project skill'i (PRD ingestion + drift-detection çıpası) ve main-edit dedektörü (disiplin dışı kod düzenlemesini…
Plugin Claude Code
Bundles 1 command · 10 tokens together
Persistent, cross-agent session handoff. Captures what you do in each project and keeps a lossless, human-readable handoff doc so the next session — in Claude Code or Cursor — resumes exactly where you left off.
Plugin Claude Code
Bundles 1 skill, 8 hooks · 63 tokens together
Plugin for the kbtz task tracker: command reference and hooks.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: