Building agents plugins

3,745 tagged Building agents, measured the same way as everything else here.

Browse within: claude-code-plugin 274cli 120agents 100ai-coding 88LLM 86agentic-ai 78ai-tools 70skills 70agent-orchestration 53agentic-workflow 46agent 44claude-code-plugins 43Multi-Agent 42gemini 39

intent-engineering

1826

davidteren/intent-engineering

Plugin Claude Code

Bundles 6 skills, 5 agents · 739 tokens together

Enforce intent engineering: software that behaves the way a reasonable developer or user expects. Principle- and architecture-grounded lenses for planning, plan validation, code review, and codebase audit, with project-level .intense config.

not rated 3 4d ago A tokens not measured original MIT

agent-levers

1827

fmind/agent-levers

Plugin Claude Code

Bundles 4 skills · 170 tokens together

Levers for AI coding agents — multiply the agent's force, divide the human's effort.

not rated 3 3mo ago A tokens not measured copy · 92% MIT

ganvil

1828

superduke/ganvil

Plugin Claude Code

Bundles 6 skills, 6 agents, 1 MCP server · 672 tokens together

Long-running autonomous coding harness with Planner-Generator-Evaluator architecture and Sprint decomposition. Builds complete applications from simple descriptions.

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

nen

1829

rlaope/nen

Plugin Claude Code

Bundles 9 skills · 1,179 tokens together

Installable agent skills mapped to the Nen system: performance, refactoring, launch, reverse engineering, reliability, orchestration, hatsu (forge new skills), en — auto-routing that reads the problem shape and engages the right abilities — and vow, pre-commitments declared before work and audited before done.

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

fable-runner

1832

rellyholdem/fable-runner

Plugin Claude Code

Bundles 1 skill · 193 tokens together

Vetted playbook for delegating heavy/deep/boundary work to the Fable 5 model as a background subagent: avoid the silent Fable→Opus keyword fallback, verify the subagent's real model, handle Fable's slowness and mid-run latch, decompose big jobs, and verify Fable's output. Includes a fable-check.sh model verifier.

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

quasar-graph

1833

o-samoilov/quasar-graph

Plugin Claude Code

Bundles 8 skills · 538 tokens together

Maps your projects into a living architecture graph: scan a directory of repos, sync the graph to the quasar-graph backend, then use it as a map — graph-aware context, cross-repo research, one-command stack cloning, and in-place graph editing.

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

ralph-x

1834

kangraemin/ralph-x

Plugin Claude Code

Bundles 2 skills · 49 tokens together

AI development loop generator — build multi-stage claude -p loops via conversation.

not rated 3 4mo ago A tokens not measured original MIT

subagent-mcp

1835

Heretyc/subagent-mcp

Plugin Claude Code

Bundles 8 skills, 3 hooks, 1 MCP server · 620 tokens together

Launches and manages local Claude Code and Codex CLI sub-agents, plus orchestration-mode hooks for per-turn directives and deterministic Claude tool gates.

not rated 3 yesterday A tokens not measured original Apache-2.0

grok

1839

okisdev/claude-code-fusion

Plugin Claude Code

Bundles 3 skills, 2 agents · 169 tokens together

Local Grok CLI delegation: task, review, resumable history, background jobs, stats, and setup health checks.

not rated 3 changed 8d ago A tokens not measured original MIT

cursor

1840

Armert-Labs/cursor-plugin

Plugin Claude Code

Bundles 3 skills, 7 commands, 1 agent, 3 hooks · 215 tokens together

Use Cursor's CLI (cursor-agent) from Claude Code to delegate coding tasks and review code, choosing the model per call. Shells out to your locally installed, authenticated cursor-agent (no data is sent to the plugin author). Registers session-lifecycle hooks and an optional, off-by-default stop-time review gate.

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

wyx

1843

jlifyio/wyx

Plugin Claude Code

Bundles 5 skills, 3 hooks · 338 tokens together

Architecture guardrails for Claude Code — automatically injects declared module boundaries into Claude's context when it edits files near a spec.

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

skill-review

1844

mindbox-cloud/agent-skills

Plugin Claude Code

Bundles 1 skill · 141 tokens together

Quick AI reviewer for Agent Skills: checks structure, workflow, references, and links. Clear report without jargon, with a summary from an exhausted data scientist.

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

install-labs

1848

phazurlabs/install-labs

Plugin Claude Code

Bundles 12 skills, 10 commands · 1,307 tokens together

Turn your AI agents and automations into installable plugins and packages — 12 skills, 10 commands across 3 phases (ASSESS → PACKAGE → SHIP). Covers every major framework (LangChain, CrewAI, AutoGen, Pydantic AI, LlamaIndex, n8n, Flowise, Dify, ComfyUI, browser agents) and every distribution target (MCP servers…

not rated 3 1mo ago A tokens not measured original Apache-2.0