ai-agents plugins

104,110 tagged ai-agents, measured the same way as everything else here.

Browse within: agentic-coding 61agents-md 48agentskills 48agent-memory 47prompt-engineering 47agent-orchestration 44coding-agents 44Multi-Agent 41antigravity 40claude-plugins 40ai-skills 39cyanheads 39agentic-workflow 36local-first 36

omni-inference

121

diegosouzapw/OmniRoute

Skill Claude CodeCodex

The core OpenAI-compatible inference endpoints: chat completions, embeddings, images, audio (TTS/STT), moderations, rerank, and the Responses API. The primary integration surface for AI agents.

60k +1.3k changed today A 47 tokens original MIT

omni-providers

122

diegosouzapw/OmniRoute

Skill Claude CodeCodex

Manage provider connections, API keys, OAuth flows, and connection tests via the REST API. List, add, update, remove, and test AI provider integrations across OmniRoute's 327-provider catalog.

60k +1.3k changed today A 45 tokens original MIT

omni-settings

123

diegosouzapw/OmniRoute

Skill Claude CodeCodex

Read and update global application settings: system prompts, thinking budget, IP filters, payload rules, combo defaults, and require-login configuration.

60k +1.3k changed today A 31 tokens original MIT

bridge-check

124

diegosouzapw/OmniRoute

Command Claude Code

Exercise the isolated Claude-to-Devin agentic bridge.

60k +1.3k today A 10 tokens original MIT

PreToolUse

125

diegosouzapw/OmniRoute

Hook Claude Code

Runs before the agent uses a tool for Skill, Read, Edit and Bash tool calls, executing log-tool.mjs via node. From diegosouzapw/OmniRoute.

60k +1.3k today A tokens not measured original MIT

OmniRoute

126

diegosouzapw/OmniRoute

Settings file Claude Code

Agent settings declaring 1 hook event (PreToolUse).

60k +1.3k today A tokens not measured original MIT

crewAI AGENTS.md

127

crewAIInc/crewAI

Instructions file CodexOpenCode

AGENTS.md instructions for crewAIInc/crewAI, covering agent instructions for crewai oss, key guidelines, message content and changing docs.

58k +132 today A 452 tokens original MIT

Invalid--Name

128

crewAIInc/crewAI

Skill Claude CodeCodex

This skill has an invalid name.

58k +132 today A 11 tokens original MIT

minimal-skill

129

crewAIInc/crewAI

Skill Claude CodeCodex

A minimal skill with only required fields.

58k +132 today A 12 tokens original MIT

valid-skill

130

crewAIInc/crewAI

Skill Claude CodeCodex

A complete test skill with all optional directories.

58k +132 today A 13 tokens original MIT

aaif-goose/goose

Instructions file GitHub Copilot

Copilot instructions for aaif-goose/goose, covering github copilot code review instructions, review philosophy, priority areas (review these), security & safety and correctness issues.

54k +112 today A 1,077 tokens original Apache-2.0

goose AGENTS.md

132

aaif-goose/goose

Instructions file CodexOpenCode

AGENTS.md instructions for aaif-goose/goose, covering agents instructions, contribution workflow, github communication, agent loop migration and setup.

54k +112 today A 1,230 tokens original Apache-2.0

goose CLAUDE.md

133

aaif-goose/goose

Instructions file

Claude Code instructions for aaif-goose/goose, a project described as: an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM.

54k +112 today A 5 tokens copy · 100% Apache-2.0

compare-tasks

134

aaif-goose/goose

Skill Claude CodeCodex

Compare how two harbor benchmark runs performed on a single shared task.

54k +112 today A 16 tokens original Apache-2.0

SessionStart

135

aaif-goose/goose

Hook

Runs when a session starts, executing announce.sh. From aaif-goose/goose.

54k +112 today A tokens not measured original Apache-2.0

UserPromptSubmit

136

aaif-goose/goose

Hook

Runs when you submit a prompt, before the agent sees it, executing announce.sh. From aaif-goose/goose.

54k +112 today A tokens not measured original Apache-2.0

PostToolUse

137

aaif-goose/goose

Hook

Runs after a tool call finishes for developer__shell and developer__text_editor tool calls, executing announce.sh. From aaif-goose/goose.

54k +112 today A tokens not measured original Apache-2.0

check-understanding

138

rohitg00/ai-engineering-from-scratch

Skill Claude CodeCodex

Phase quiz for AI Engineering from Scratch. Trigger with "quiz me", "test phase", "check my understanding", "do I know phase 3", or /check-understanding .

52k +644 3d ago A 44 tokens original MIT

claude-certification

139

rohitg00/ai-engineering-from-scratch

Skill Claude CodeCodex

AI-native tutor and onboarding workflow for the four independent Claude certification tracks in AI Engineering from Scratch. Use when a learner wants to choose a Claude certification, prepare for CCAO-F, CCDV-F, CCAR-F, or CCAR-P, resume a certification path, learn the next lesson interactively, run and verify…

52k +644 3d ago A 109 tokens original MIT

find-your-level

140

rohitg00/ai-engineering-from-scratch

Skill Claude CodeCodex

Interactive quiz that maps your AI/ML knowledge to a starting point in the 523-lesson, 20-phase AI Engineering from Scratch curriculum. Trigger phrases: "where should I start", "find my level", "what do I know", "which phase", "assess my knowledge", "placement test", "skip ahead".

52k +644 3d ago A 71 tokens original MIT

nanobot AGENTS.md

142

HKUDS/nanobot

Instructions file CodexOpenCode

AGENTS.md instructions for HKUDS/nanobot, covering project overview, development commands, python: run single test / lint, strict type checking (matches ci) and gateway.

48k +85 today A 1,289 tokens original MIT

nanobot CLAUDE.md

143

HKUDS/nanobot

Instructions file

Claude Code instructions for HKUDS/nanobot, a project described as: Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps.

48k +85 today A 5 tokens copy · 100% MIT

skill-creator

144

HKUDS/nanobot

Skill Claude CodeCodex

Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.

48k +85 today A 28 tokens original MIT

At most 3 mods per repository are shown here — the rest are on their repository pages: