ai-agents plugins

3,275 tagged ai-agents, measured the same way as everything else here.

Browse within: agentic-ai 236claude-code-plugin 213LLM 190cursor 177cli 133prompt-engineering 111agents-md 107Science 99agents 87ai-coding 80agentic-coding 62ai-tools 62skills 61ai-governance 54

powerbi-agent

2065

HamadYMarafi/powerbi-agent-mcp

Plugin Claude Code

Bundles 3 skills · 317 tokens together

Power BI dashboard building for AI agents: the powerbi-agent MCP server (list workspaces and items, model schema, read-only DAX, download/validate/deploy PBIR reports with guardrails, date-filter pins, page captures, refresh history) and three skills (build, review, verify). Needs Python 3.11+, pip install -r requirem.

not rated 1 16d ago A tokens not measured original MIT

coordharness

2067

0marm0/COORD-Harness

Plugin Claude Code

Bundles 1 skill, 5 commands · 171 tokens together

A coordination control plane for fleets of AI coding agents: claim without colliding, hand off bounded context, and finish only when the declared proof exists.

not rated 1 4d ago A tokens not measured original MIT

write-like-me

2068

jzfgo/agents

Plugin Claude Code

Bundles 1 skill · 202 tokens together

Write, rewrite, review and correct text in your own voice, from a profile extracted from your own writing.

not rated 1 11d ago A tokens not measured original MIT

whitepact

2069

Guruprasath-Annadurai/Whitepact

Plugin Cursor

Bundles 1 MCP server

AI governance for agent tool calls: trust scoring, PII/harmful-content guardrails, hallucination detection, and compliance checks (NIST AI RMF, EU AI Act, ISO 42001) via 27 read-only MCP tools.

not rated 1 yesterday A tokens not measured original MIT

shield-kya

2070

The-Pixel-Boys/shield-kya

Plugin Cursor

Bundles 1 skill, 1 MCP server · 41 tokens together

Know Your Agent: fail-closed eval (ALLOW | DENY | REQUIREAPPROVE), dual-plane host=ide|runtime, human approval. This plugin is a thin MCP gate — the control plane is the sole PEP.

not rated 1 yesterday A tokens not measured original MIT

decide-policy-notaries

2071

decidefyi/decide

Plugin Cursor

Bundles 1 skill · 48 tokens together

A Krafthaus support-policy app powered by Decide, with source-backed refund, cancellation, return, and trial checks.

not rated 1 yesterday A tokens not measured

major-ai-skills

2073

alivirgo/Major-AI-Skills

Plugin Gemini CLI

412+ installable agent skills (SKILL.md) for professional apps, token efficiency, and common-sense prompting. Compatible with Gemini CLI skills discovery.

not rated 1 changed today A tokens not measured original MIT

samedaydesk-extract

2074

epistemedeus/x402-url-extractor

Plugin Claude Code

Bundles 2 skills, 1 MCP server · 163 tokens together

Self-contained Claude Code plugin that binds the canonical SameDayDesk MCP, one web-extract skill for single-page GET or bounded 1–5 URL batch POST, and one offline explicit-record skill. Unpaid discovery only. Mapping does not fetch or pay. No wallet, no second paywall, no installer.

not rated 1 changed 5d ago A tokens not measured original MIT

postlake

2075

PostLake/postlake-mcp

Plugin Claude Code

Bundles 8 skills, 2 MCP servers · 364 tokens together

Hosted MCP and skills so an agent can publish, schedule, reply, and measure social posts across connected networks.

not rated 1 +1 6d ago A tokens not measured original MIT

unblockingapi

2077

unblockingapi/mcp

Plugin Claude Code

Bundles 1 skill, 1 command, 1 hook, 1 MCP server · 99 tokens together

Give Claude a real browser: fetch bot-protected and JavaScript-heavy pages through UnblockingAPI, with structured JSON for any site a published template covers. Replaces the built-in web fetch.

not rated 1 changed 3d ago A tokens not measured original MIT

matcha

2078

plumpslabs/matcha

Plugin Gemini CLI

Engineering philosophy ruleset — simple, efficient, deliberate. Never twice.

not rated 1 3d ago A tokens not measured original MIT

fulcru

2081

gsmmediaro/fulcru

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 0 tokens together

Get named by AI search engines. Finds the questions where ChatGPT, Gemini and Perplexity name a competitor instead of you, writes the page that closes the gap, and measures what publishing it did.

not rated 0 1mo ago A tokens not measured AGPL-3.0

ag-bash

2082

sairam0424/ag-bash

Plugin Claude Code

Bundles 1 MCP server

Sandboxed AI-native bash for Claude Code: 70 MCP tools backed by the @ag-bash/bash engine — runbash with a full unix toolkit (grep/sed/awk/jq), surgical code edit/diff/analyze, WASM Python & JavaScript, semantic search, and agent task/worktree management. Defense-in-depth sandbox on by default.

not rated 0 2d ago A tokens not measured original Apache-2.0

verve

2083

dbhq-uk/verve-skill

Plugin Claude Code

Bundles 1 skill · 225 tokens together

Strip AI tells from prose and put a human voice back, in British or American English, pitched at the reader it is for. A catalogue of tells across content, language, style, assistant artefacts, filler, condescension and overshare, four tone presets, three strength levels, a two-way politeness check that catches both…

not rated 0 +4 changed 2d ago A tokens not measured original MIT

mycelium

2085

dihannahdi/mycelium

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 200 tokens together

A bio-inspired context protocol for DataHub agents: budgeted foraging over the lineage graph, three-level semantic zoom, working memory that prunes itself, and reflex answers that never call a model. Extends the DataHub skills rather than replacing them.

not rated 0 1mo ago A tokens not measured original Apache-2.0

dmfaster

2087

dmfaster/agents

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 142 tokens together

Plan campaigns, prepare private drafts, inspect live sales activity, and run authorized campaign controls through DM Faster Agent 1.0.

not rated 0 changed 5d ago A tokens not measured original Apache-2.0

hindsight-memory

2088

Holetron-lab/fleet-memory

Plugin Claude Code

Bundles 4 hooks

Automatic long-term memory for Claude Code via Hindsight. Recalls relevant memories before each prompt and retains conversation transcripts after each response.

not rated 0 17d ago A tokens not measured original MIT

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: