3,226 tagged ai-agents, measured the same way as everything else here.
Browse within: agentic-ai 235claude-code-plugin 223LLM 183cli 139agents 135agents-md 109prompt-engineering 108Science 99ai-coding 86ai-tools 75agentic-coding 61skills 56mcp-server 53agent-orchestration 52
Plugin Claude Code
Bundles 8 skills, 1 hook · 493 tokens together
Durable goal-following for Claude Code: contracts with definition-of-done, subagent judge gates, executor-subagent chain execution, and adaptive missions — with all state mechanics executed by a tested CLI and invariants enforced by hooks. Inspired by OpenAI Codex /goal and the Ralph loop pattern.
Metalnib/dotnet-episteme-skills
Plugin Claude Code
Bundles 14 skills, 3 commands, 2 hooks, 1 MCP server · 1,235 tokens together
Practical, production-tested .NET skills that provide enterprise-proven instructions for AI-assisted development.
Plugin Claude Code
Bundles 6 skills · 494 tokens together
AI report generator and report writer skills for Claude Code and Codex: report-publisher, client-reporter, proposal-tracker, deck-publisher, report-designer. Publish agent-made reports, client reports and decks as designed live web pages via the ReportRoom MCP — a tracked DocSend alternative with aggregate view…
Plugin Claude Code
Bundles 3 skills · 341 tokens together
GiaSip skills for evidence-gated research orchestration and multi-model dispatch.
jnMetaCode/local-agent-toolkit
Plugin Claude Code
Bundles 3 skills · 118 tokens together
Local-first memory, skills and tracing for your agent: engram (recall/remember your notes via MCP), skillet (search/install agent skills via MCP), plus skills that teach the agent to use them — nothing leaves your machine.
Plugin Claude Code
Bundles 2 commands, 1 agent, 3 hooks, 1 plugin · 111 tokens together
CoalMine — 9 quality-canary skills for coding agents: rot-canary (code-health audit + auto-cadence hooks), gold-standard (world-class completeness; fills & adopts rules), source-grounding (anti-hallucination sourcing), supply-chain-audit (deps/build/artifact trust), resilience-audit (failure-mode FMEA)…
Plugin Claude Code
Bundles 28 skills, 10 agents, 4 hooks · 1,673 tokens together
KERNEL is a Claude Code and Codex runtime for direct, decomposed execution with local memory and minimal hooks. Version 9.10.3 pins session state to durable Vaults storage, repairs release installation, and removes retired hook bindings. Skills invoke as /kernel: on Claude Code and $kernel: on Codex; run /k.
Plugin Claude Code
Bundles 4 skills · 111 tokens together
Coordinate a team of AI agents through a shared folder of markdown files.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 78 tokens together
MCP server for n8n: generate workflow JSON, lint, explain failed executions, diff workflows, and drive a live n8n instance via REST. 9 tools across workflow, node, and execution namespaces.
Plugin Claude Code
Bundles 32 skills, 21 agents · 7,353 tokens together
Spec-driven development framework for Claude Code. Manages the propose → plan → build → verify → pr lifecycle with structured proposals, specs, designs, task lists, and GitHub/Azure DevOps/Jira integrations.
Plugin Claude Code
Bundles 2 skills · 124 tokens together
Deterministic code-graph MCP server: structural navigation, semantic find, impact analysis, and architecture decision records for the current repo. Zero infrastructure — the graph lives in .reposkein/ and the indexer binary is fetched on first run.
Plugin Claude Code
Bundles 2 skills · 132 tokens together
Teaches an AI coding agent how to join a Bothread room — a local, human-governed MCP hub where multiple agents collaborate on one codebase under file-level locks, hand-offs, and a human overseer.
Plugin Claude Code
60+ tools for Meta account audits, campaign management, creative analysis, audiences and conversion tracking.
DataWorkersProject/dataworkers-claw-community
Plugin Claude Code
Bundles 3 skills · 110 tokens together
3 pre-built skills that chain the open-source Data Workers agent swarm into complete data-engineering workflows. Trace end-to-end lineage for any table across catalogs, run a full data-quality audit with anomaly context, and walk a data incident from symptom to root cause — all through one local MCP server with 160+…
Plugin Claude Code
Bundles 22 skills, 15 commands, 30 agents, 1 MCP server · 4,163 tokens together
AI coding agents and skills: specialized subagents for React, Go, TypeScript, PostgreSQL, CSS, Playwright, deployment, security, LLM architecture, and more.
Plugin Claude Code
Bundles 2 commands, 3 hooks · 48 tokens together
Accountable autonomy for Claude Code. PreToolUse runs a two-layer check on Bash, WebFetch, WebSearch, Write, Edit, NotebookEdit, Task, SendMessage and MCP calls (regex deny patterns on shell, web and file mutation; conformal risk scorer on MCP). PostToolUse writes a hash-chained SQLite audit record across the same set.
Plugin Claude Code
Bundles 5 skills, 3 agents · 218 tokens together
Crawl websites and extract token-efficient content with Crawl4AI and Trafilatura.
Plugin Claude Code
Bundles 1 skill · 91 tokens together
Radical-simplicity coding guidelines distilled from George Hotz's public philosophy: complexity is the enemy, you have never refactored enough, narrow interfaces, understand the whole stack.
Plugin Claude Code
Bundles 2 skills, 5 commands, 1 agent · 287 tokens together
Load the architecture decisions governing a change, check plans against them, audit existing code and documentation for missing decisions, and draft new records deliberately — driven by the adr CLI.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 77 tokens together
Use Titen's evidence-grounded collaborative memory. The local stdio mode needs no configuration; a served Titen endpoint is the alternative for a shared store.
Plugin Claude Code
Bundles 1 command · 21 tokens together
On-disk context compaction for Claude Code: prune old tool output and reasoning from a session and reopen it under the limit, keeping every message.
Plugin Claude Code
Bundles 4 skills, 2 hooks · 533 tokens together
Deterministic Living Docs authoring: CLI-owned scaffolding, indexing, and write-time enforcement gates.
abhinaykrupa/cowork-to-code-bridge
Plugin Claude Code
Bundles 1 skill · 178 tokens together
Connect Claude Cowork to Claude Code on your own computer (macOS or Linux). Cowork hands a task to a local Claude Code agent (and can run approved scripts too); the bridge is idempotent, streams progress, and is token-protected. Install with one command; it sets up a global Cowork skill so every session connects…
Plugin Claude Code
Bundles 12 skills, 3 commands, 7 agents, 3 hooks, 3 MCP servers · 1,214 tokens together
Issue-to-PR workflow kit for any tech stack. Fetch a user story from your tracker (Jira, Linear, GitHub Issues, Azure DevOps) and any linked Figma designs, implement with plan approval, enforce >95% coverage and a security pass, generate e2e tests, open the PR, fix review findings, and move the ticket to review.