Building agents plugins

3,986 tagged Building agents, measured the same way as everything else here.

Browse within: claude-code-plugin 237cli 123cursor 117agents 115LLM 97skills 84ai-coding 81ai-tools 75agentic-ai 73agent 56agent-orchestration 49agentic-workflow 48claude-code-plugins 45mcp-server 42

prompt-improver

73

severity1/claude-code-prompt-improver

Plugin Claude Code

Bundles 1 skill, 3 hooks · 42 tokens together

Intelligent prompt optimization: injects the right context at the right moment so Claude lands a better first output. Clarifies vague prompts with research-based questions, plus targeted nudges for approach selection, plan readability, workflow routing, background execution, subagent routing, output readability…

not rated 2.0k +10 changed 16d ago A tokens not measured original MIT

agents-meet-rl

74

thinkwee/AgentsMeetRL

Plugin Claude Code

Bundles 1 skill · 220 tokens together

Troubleshooter + machine-readable corpus for reinforcement-learning training, evaluation, and experiment design on LLM agents (single/multi-agent, multi-turn, tool-augmented). Distilled from the AgentsMeetRL awesome list (378 projects).

not rated 1.9k +3 changed 7d ago A tokens not measured

beacon

75

Asymptote-Labs/agent-beacon

Plugin Claude Code

Bundles 5 skills, 1 MCP server · 515 tokens together

Cross-harness memory from Beacon traces: recall reviewed project lessons, distill agent sessions into approved memory, promote memory to Agent Skills, build dashboard lenses, and share sessions to beacon.sh.

not rated 1.8k +17 changed 6d ago A tokens not measured original MIT

reflexion

76

NeoLabHQ/context-engineering-kit

Plugin Claude Code

Bundles 2 hooks

Collection of commands that force LLM to reflect on previous response and output. Based on papers like Self-Refine and Reflexion. These techniques improve the output of large language models by introducing feedback and refinement loops.

not rated 1.8k +27 1mo ago A tokens not measured GPL-3.0

open-prose

77

openprose/prose

Plugin Claude Code

Bundles 1 skill · 133 tokens together

State what an agent must accomplish and which requirements it must satisfy. Reuse and combine Markdown contracts.

not rated 1.8k +4 changed 16d ago A tokens not measured original MIT

ai-devkit

78

codeaholicguy/ai-devkit

Plugin Claude Code

Bundles 29 skills, 1 hook · 1,388 tokens together

Make AI coding agents follow a repeatable engineering workflow with memory, verification, skills, and multi-agent setup.

not rated 1.6k +5 changed 5d ago A tokens not measured original Apache-2.0

cc-thinking-skills

79

tjboudreaux/cc-thinking-skills

Plugin Claude Code

Bundles 28 skills · 1,028 tokens together

28 eval-informed mental models and critical-thinking skills for Claude Code, GitHub Copilot, Codex, Cursor, and other Agent Skills-compatible tools.

not rated 1.6k +30 2mo ago A tokens not measured original MIT

hephaestus

80

agentlas-ai/Agentlas-OS

Plugin Claude Code

Bundles 4 agents, 6 hooks · 135 tokens together

Open Agent OS for Claude Code, Codex, and Cursor: meta-agent builder, A2A Hub routing, local ontology, memory/security gates.

not rated 1.6k +24 changed today A tokens not measured original Apache-2.0

agmsg

81

fujibee/agmsg

Plugin Claude Code

Bundles 1 skill · 39 tokens together

Cross-agent messaging via SQLite. Send messages between CLI AI agents. No daemon, no network.

not rated 1.6k +8 changed 12d ago A tokens not measured original MIT

humanize

82

PolyArch/humanize

Plugin Claude Code

Bundles 6 skills, 5 commands, 4 agents, 4 hooks · 344 tokens together

Humanize - An iterative development plugin that uses Codex to review Claude's work. Creates a feedback loop where Claude implements plans and Codex independently reviews progress, ensuring quality through continuous refinement.

not rated 1.5k +34 1mo ago A tokens not measured

ralphex

84

umputun/ralphex

Plugin Claude Code

Bundles 4 skills · 106 tokens together

Autonomous plan execution with Claude Code - task execution, monitoring, and plan creation.

not rated 1.5k +7 4d ago A tokens not measured original MIT

daymade-claude-code

86

daymade/claude-code-skills

Plugin Claude Code

Bundles 22 skills · 2,343 tokens together

Claude Code operations suite that bundles cross-project prior-work retrieval across code, docs, Skills, meetings, WeChat archives, and conversation history; provider-separated Claude Code and Codex history readers; identity- and lineage-gated continuation workflows; plugin/skill troubleshooting; CLAUDE.md progressive…

not rated 1.5k +21 changed today A tokens not measured original MIT

skill-codex

87

skills-directory/skill-codex

Plugin Claude Code

Bundles 1 skill · 38 tokens together

Claude Code skill to delegate prompts to OpenAI Codex CLI for code analysis, refactoring, code review, and automated editing.

not rated 1.5k +5 1mo ago A tokens not measured original MIT

cao

88

awslabs/cli-agent-orchestrator

Plugin Claude Code ✓ vendor

Bundles 4 skills, 1 MCP server · 187 tokens together

Drive CLI Agent Orchestrator multi-agent sessions from any Agent-Plugins-compatible client. Prerequisites: the uv toolchain must be on PATH (the MCP server is launched via uvx), and a CAO API server must be running locally at http://127.0.0.1:9889 (cao-server). All communication is localhost-only.

not rated 1.4k +38 changed 9d ago A tokens not measured original Apache-2.0

wiki

89

nvk/llm-wiki

Plugin Claude Code

Bundles 1 skill, 28 commands · 1,018 tokens together

LLM-compiled knowledge base with Project Knowledge Checkpoints Export, personal specialist skills, trusted adapters, Idea-to-Project workflows, compact queries, inventory, datasets, ingestion, audits, sessions, research, and outputs.

not rated 1.4k +23 changed 15d ago A tokens not measured original MIT

project-starter

90

CloudAI-X/claude-workflow-v2

Plugin Claude Code

Bundles 14 skills · 731 tokens together

Universal Claude Code workflow with specialized agents, skills, hooks, and mode commands for any software project. Includes orchestrator, code-reviewer, debugger, docs-writer, security-auditor, refactorer, and test-architect agents.

not rated 1.4k +2 changed 15d ago A tokens not measured original MIT

nopua

91

wuji-labs/nopua

Plugin Claude Code

Bundles 3 skills, 3 commands, 3 agents · 554 tokens together

The anti-PUA. Drives AI with wisdom, trust, and inner motivation instead of fear and threats. Based on Dao De Jing philosophy. 7 languages, 7 platforms.

not rated 1.4k +2 19d ago A tokens not measured original MIT

mirobody

92

thetahealth/mirobody

Plugin Claude Code

Bundles 2 skills · 267 tokens together

Translate raw health data into LOINC/UCUM/ICPC-3 coded rows and read lab reports against an offline resolver; self-host Mirobody and connect an agent over MCP.

not rated 1.4k +9 3d ago A tokens not measured original Apache-2.0

open-steps

93

kharmanskyi/open-steps

Plugin Claude Code

Bundles 8 skills, 1 command, 2 hooks · 1,296 tokens together

Plain-language skills for coding agents, for the person running development who does not read code: session reports, decisions, next steps and the whole picture.

not rated 1.4k +83 changed 12d ago A tokens not measured original MIT

oma

94

first-fluke/oh-my-agent

Plugin Claude Code

Bundles 33 skills · 993 tokens together

Portable multi-agent harness for .agents-based skills and workflows.

not rated 1.3k +8 changed 7d ago A tokens not measured original MIT

skills

96

AI-Builder-Club/skills

Plugin Claude Code

Bundles 11 skills · 1,225 tokens together

Build loop engineers: a file-based knowledge base your agents read/write (loops), plus a codebase harness (dev-local stack, e2e gate, an isolated cloud box per agent via crabbox, and verify-before-ship) so loops can run, test, and ship code autonomously. Plus an SEO growth playbook distilled from two production…

not rated 1.3k +5 1mo ago A tokens not measured

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: