ai-agents plugins

3,273 tagged ai-agents, measured the same way as everything else here.

Browse within: agentic-ai 236claude-code-plugin 215LLM 191cursor 177cli 130prompt-engineering 111agents-md 107Science 99agents 87ai-coding 81agentic-coding 62ai-tools 62skills 60ai-governance 54

assist

1657

edloidas/skills

Plugin Claude Code

Bundles 5 skills · 275 tokens together

External opinion, assistance, Q&A, and plain restatement tools including Codex CLI integration.

not rated 2 changed 7d ago A tokens not measured original MIT

rate-my-code

1658

AmsonntagChow/rate-my-code

Plugin Claude Code

Bundles 1 skill · 251 tokens together

Audits AI-built and vibe-coded apps from product, systems, frontend, user, and venture perspectives, then optionally records authorized fixes and independent retests in a durable audit ledger.

not rated 2 1mo ago A tokens not measured original MIT

codebase-to-portfolio

1659

jasonChen0604/codebase-to-portfolio

Plugin Claude Code

Bundles 6 skills · 442 tokens together

Turn your entire codebase history into a portfolio-ready tech profile — scan projects, generate per-project docs, and roll them up into a bilingual tech profile (Markdown + JSON) for your personal site.

not rated 2 2mo ago A tokens not measured original MIT

tempest

1662

mtthsnc/tempest

Plugin Claude Code

Bundles 8 skills, 9 commands · 838 tokens together

A software factory for AI coding agents: opinionated plan -> build -> review -> test -> ship -> reflect workflows, shipped as portable Agent Skills that run identically on Claude Code and pi.

not rated 2 2mo ago A tokens not measured original MIT

ppgp

1663

Fatboy-coder/ppgp

Plugin Claude Code

Bundles 1 skill · 53 tokens together

Portable continuity protocol for long-running coding agents.

not rated 2 15d ago A tokens not measured original MIT

cavuno-skills

1664

wollemiahq/skills

Plugin Claude Code

Bundles 2 skills · 142 tokens together

Agent skills from the team behind Cavuno and Himalayas — evidence-first performance optimization and a PR review loop that only fixes what it can demonstrate.

not rated 2 16d ago A tokens not measured original MIT

cutweight

1665

brenbuilds1/cutweight

Plugin Claude Code

Bundles 5 skills · 456 tokens together

Cut your agent's token weight: weigh in, read the bill, cut the output, cap the thinking, keep sessions lean.

not rated 2 2mo ago A tokens not measured original MIT

news-reviewer

1666

mertcanciy/news-reviewer

Plugin Claude Code

Bundles 1 skill · 27 tokens together

Turn a news item into a research briefing: verified facts with source cross-checks, historical parallels, and unanswered devil's-advocate questions.

not rated 2 1mo ago A tokens not measured original MIT

skillforge

1667

yvzhou1111/skillforge

Plugin Claude Code

Bundles 2 skills · 139 tokens together

Intelligent Agent-Skill dependency butler: discover, security-audit, and install Agent Skills into your project. Scans tech stack, plans a vetted combination, audits each skill, and installs per-agent.

not rated 2 3mo ago A tokens not measured original MIT

watch-local

1669

PBNZ/watch-local

Plugin Claude Code

Bundles 1 skill, 4 commands, 1 hook · 313 tokens together

Let Claude watch a video -- fully local. Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, ALWAYS transcribes with faster-whisper and compares against creator-provided captions. Auto-detects your NVIDIA GPU: uses it for video decode (NVDEC) and whisper when present, falls back to a fully working CPU-only.

not rated 2 1mo ago A tokens not measured

pre-flight-check

1670

mirekondro/The-Pre-Flight-Check

Plugin Claude Code

Bundles 1 skill · 45 tokens together

Fail-fast quality gate (Typecheck → Lint → Test → Security Audit) that runs before any task is declared done or code is committed. Auto-detects Node.js and Python projects.

not rated 2 3mo ago A tokens not measured original MIT

swarmgpt

1671

Vallykrie/swarmGPT

Plugin Claude CodeCodex

Bundles 2 skills, 2 commands, 1 agent · 404 tokens together

Make Codex your default writer and image generator: your agent plans and reviews while parallel codex exec (GPT-5.6) sessions do the writing, plus a codex-imagegen skill that generates real images through Codex's built-in imagegen tool.

not rated 2 1mo ago A tokens not measured original MIT

skillrot

1672

mishanefedov/skillrot

Plugin Claude Code

Bundles 2 skills · 159 tokens together

Audit agent skills for CLI drift — finds skills that call external tools with flags or subcommands the installed version no longer accepts.

not rated 2 3mo ago A tokens not measured original MIT

urd

1674

krzysztofdudek/UrdSkill

Plugin Claude Code

Bundles 1 skill · 50 tokens together

Skill that makes your coding agent stop and ask instead of silently resolving spec ambiguity, picking up workarounds, or shipping 'close enough'. Accuracy over autonomy.

not rated 2 2d ago A tokens not measured original MIT

brownspec

1675

yknnv/brownspec

Plugin Claude Code

Bundles 4 skills, 4 commands · 327 tokens together

Spec-driven development for existing codebases. Reads your repo's conventions, interviews you about a change, and writes spec, design and tasks to disk, with blast-radius analysis. Regulatory policy profiles are optional and off by default.

not rated 2 17d ago A tokens not measured original MIT

claude-code-pm

1677

hunterg325/claude-code-pm

Plugin Claude Code

Bundles 3 skills, 1 agent · 196 tokens together

Autonomous Project Manager for Claude Code. Orchestrates parallel worker sessions to execute Linear tasks through a structured lifecycle: fetch, assign, implement, verify, review, merge.

not rated 2 5mo ago A tokens not measured original MIT

cys

1679

bacsystem/parallel-plan-executor

Plugin Claude Code

Bundles 5 skills, 2 commands · 326 tokens together

Development methodology skills with parallel plan execution: design, plan, run, check, ship. Named after the author's twin daughters, Cielo y Sophia.

not rated 2 1mo ago A tokens not measured original MIT

rot-moe

1680

Nova-Violet-Role/RoT-MoE

Plugin Claude Code

Bundles 5 commands, 10 agents, 33 hooks · 941 tokens together

RoT MoE - a nine-lens Mixture-of-Experts router with a measured R/s+ divergence gauge, specified in Lean 4 and bound to the shipped hooks by an executable checker. 1813 machine-checked theorems, zero sorry, kernel re-verified.

not rated 2 14d ago A tokens not measured AGPL-3.0

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: