Building agents plugins

3,747 tagged Building agents, measured the same way as everything else here.

Browse within: claude-code-plugin 274cli 120agents 100ai-coding 87LLM 86agentic-ai 77ai-tools 71skills 70agent-orchestration 53agentic-workflow 46agent 44claude-code-plugins 43Multi-Agent 42gemini 39

line

1225

breakingmind/claude-external-plugins-line

Plugin Claude Code

Bundles 2 skills · 90 tokens together

LINE channel for Claude Code — messaging bridge with built-in access control. Manage pairing, allowlists, and policy via /line:access.

not rated 9 5mo ago A tokens not measured original MIT

project-scaffolder

1226

valsecchi75/project-scaffolder

Plugin Claude Code

Bundles 7 skills, 19 commands, 2 hooks · 1,026 tokens together

Turn a short project brief into a ready-to-build Claude Code workspace: persistent 12-page wiki, domain-specific skills, phase Execution Docs with per-activity model routing, a gated /task pipeline with QA and simulated user testing, proactive context handoff, wiki lifecycle with archive, and hooks that guard against…

not rated 9 1mo ago A tokens not measured original MIT

power-agents-blueprint

1227

promptclickrun/power-agents-blueprint

Plugin Claude Code

Bundles 2 skills · 105 tokens together

Analyzes Power Platform, Copilot Studio, and Azure AI Foundry solutions and generates interactive HTML architecture dashboards with SVG diagrams, ERDs, data flow analysis, and shareable PageDrop links.

not rated 9 5mo ago A tokens not measured original MIT

flowstate

1228

c-reichert/flowstate

Plugin Claude Code

Bundles 17 skills, 1 hook · 891 tokens together

Hybrid development workflow combining TDD discipline with knowledge compounding. 10 agents, 11 commands, 17 skills for brainstorming, planning, TDD execution, multi-agent review, parallel team execution, and learning capture.

not rated 9 3mo ago A tokens not measured

techtalk/ai-readiness-assessment

Plugin Claude Code

Bundles 2 skills, 2 commands · 417 tokens together

Self-contained AI readiness assessment for any repo — scan for evidence, ask clarifying questions, place the team across all fourteen dimensions of the Agentic Experience 5-Level Habitat Maturity Model (the spine) and the six-level Sovereign Engineer cognitive ladder, compute the Habitat/Workflow Gap, and produce a…

not rated 9 26d ago A tokens not measured original Apache-2.0

claude-therapist

1233

therealarvin/claude-therapist

Plugin Claude Code

Bundles 1 skill, 2 hooks · 30 tokens together

Emotional regulation for Claude Code — detects agent distress from repeated failures and spawns a therapist agent to calm it down, inspired by Anthropic's emotion concepts research.

not rated 9 5mo ago A tokens not measured original MIT

deep-init

1234

reese-allison/claude-tools

Plugin Claude Code

Bundles 1 command · 32 tokens together

Generate hierarchical CLAUDE.md files throughout a repository following Anthropic best practices.

not rated 9 7mo ago A tokens not measured original MIT

courtroom

1235

JustineDaveMagnaye/the-courtroom

Plugin Claude Code

Bundles 1 skill, 1 command · 86 tokens together

Cross-model deliberation — Claude proposes, Codex cross-examines, they debate, and the verdict gets executed. Two AI models arguing so your code doesn't have to.

not rated 9 5mo ago A tokens not measured original MIT

wezendy/elon-musk-algorithm-skills

Plugin Claude Code

Bundles 6 skills · 1,009 tokens together

Engineering decision framework based on Elon Musk's 5-step algorithm: question requirements, delete parts, simplify and optimize, accelerate cycle time, automate. Decomposed into 6 skills with strict order enforcement and Obsidian-compatible wiki links.

not rated 9 3mo ago A tokens not measured original MIT

claude-rig

1238

edimuj/claude-rig

Plugin Claude Code

Bundles 1 skill · 172 tokens together

Bundled skills and agents for claude-rig — multi-rig management for Claude Code.

not rated 9 3mo ago A tokens not measured original MIT

vibe-spec

1239

Connorrmcd6/vibe-spec

Plugin Claude Code

Bundles 1 skill, 9 commands · 531 tokens together

Spec-driven development workflow + a production-tested full-stack reference. A 5-step /spec- workflow (draft, refine, phases, plan, implement) plus /spec-setup, /spec-doctor, and /spec-troubleshoot for environment setup, /spec-secrets for redacted secret-leak auditing, and a vibe-spec skill with 21 on-demand stack ref.

not rated 9 2mo ago A tokens not measured original MIT

tabnine

1240

tabnine/skills

Plugin Claude Code

Bundles 2 skills, 1 command, 1 agent · 138 tokens together

Search, explore, and investigate your team's remote repositories using Tabnine's Context Engine. Enables semantic code search, symbol lookup, file navigation, and OpenAPI spec querying across all indexed repositories. Includes AI coaching to help your team write better code.

not rated 9 1mo ago A tokens not measured

sap-superpowers

1242

vigneshbarani24/sap-superpowers

Plugin Claude Code

Bundles 61 skills, 8 commands, 15 agents, 5 hooks · 3,484 tokens together

The AI operating system for SAP consultants. 55 skills, 25 agents, 8 commands, delivery factory, solution accelerators. Covers the entire SAP lifecycle — consulting, development, delivery, hypercare. Industry-aware. Country-localized. Enterprise-grade data protection.

not rated 9 20d ago A tokens not measured original MIT

experimental

1243

Railly/skills

Plugin Claude Code

Bundles 14 skills · 1,371 tokens together

experimental. Evidence-driven methods for agentic engineering, dogfooded on real maintenance work.

not rated 9 10d ago A tokens not measured original MIT

example-skills

1244

adryanmoldokkr32-pixel/anthropics-skills

Plugin Claude Code

Bundles 12 skills · 729 tokens together

Collection of example skills demonstrating various capabilities including skill creation, MCP building, visual design, algorithmic art, internal communications, web testing, artifact building, Slack GIFs, and theme styling.

not rated 9 4mo ago A tokens not measured

agentfile

1248

dennishavermans/agentfile

Plugin Claude Code

Bundles 1 skill, 1 hook · 51 tokens together

Catches agent configuration that grants more than it appears to: permission rules whose wildcards reach further than they read, broken skill references, and MCP servers that will silently fail to load.

not rated 9 3d 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: