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 88LLM 86agentic-ai 78ai-tools 71skills 70agent-orchestration 53agentic-workflow 46agent 44claude-code-plugins 43Multi-Agent 42gemini 39

cli-agents

1441

richfrem/agent-plugins-skills

Plugin Claude Code

Bundles 14 skills, 13 agents · 1,761 tokens together

Multi-LLM Task Router Suite. runagent.py routes bounded tasks to six backends: Claude CLI, GitHub Copilot, Gemini CLI, Antigravity (Agy), Codex/OpenAI-compatible, and direct local Gemma 4 12B via llama-server (2s, no proxy). 11 expert agent personas covering adversarial patterns (red-team, debate synthesis, output va.

not rated 6 changed 2d ago A tokens not measured original MIT

skills-board

1442

TommyBez/skillsboard

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 141 tokens together

Search your team's Skills Board library over MCP and get the install command for a saved skill or a published collection.

not rated 6 +1 yesterday A tokens not measured original MIT

wcode

1443

francis-du/wcode

Plugin Claude Code

Bundles 1 skill · 66 tokens together

wcode Software Intelligence skill with safe skill-only, local stdio, and remote HTTP connection profiles.

not rated 6 changed yesterday A tokens not measured original Apache-2.0

boom

1444

NanoBoom/nano-claude-code-plugins

Plugin Claude Code

Bundles 3 skills, 2 commands, 11 agents, 1 hook · 569 tokens together

Cost-first delegation control for Claude Code: L0-L4 task budgets, role-to-model routing, a Fable critical-worker gate, bounded worker agents, and a PreToolUse hook that denies model inheritance on Agent, Workflow, and SendMessage dispatches.

not rated 6 changed 3d ago A tokens not measured

token-pilot

1448

Digital-Threads/token-pilot

Plugin Claude Code

Bundles 3 skills, 25 agents, 5 hooks, 1 MCP server · 1,774 tokens together

Saves 60-90% tokens on AI code reading. AST-aware lazy reads, symbol navigation, findusages, structural git diff/log, edit-safety guard, Task-routing matcher, cross-session telemetry (errors + diagnostics), 25 tp- subagents tiered to haiku/sonnet/opus with budget watchdog.

not rated 5 changed 2d ago A tokens not measured

archsteer

1449

einvoice-dev1/archsteer

Plugin Claude Code

Bundles 1 skill, 2 commands, 1 MCP server · 121 tokens together

Architecture governance for AI coding agents — derive the real architecture from any repo, enforce declared rules with a net-new ratchet, and stop agents drifting off pattern before code ships.

not rated 5 1mo ago A tokens not measured original MIT

agy

1450

Vit129/agy-plugin-cc

Plugin Claude Code

Bundles 1 skill, 4 commands, 1 agent, 2 hooks, 1 plugin · 189 tokens together

Delegate coding tasks to Google's Antigravity (agy) CLI / Antigravity IDE from Claude Code (Google Agy) — full rescue, resume, background execution, code review, and stop-time review gate.

not rated 5 20d ago A tokens not measured original MIT

agent-comm

1451

keshrath/agent-comm

Plugin Claude Code

Bundles 1 MCP server

Agent-to-agent messaging for AI coding agents — sessions, direct/broadcast/channel messages, shared state, real-time feed, and a file-coordination hook for parallel edits.

not rated 5 4mo ago A tokens not measured original MIT

styx

1452

timmx7/styx

Plugin Claude Code

Bundles 1 skill, 2 commands, 1 agent · 82 tokens together

MCP-native AI API gateway. Route, manage, and observe LLM traffic across providers with built-in MCP server support.

not rated 5 3mo ago A tokens not measured original Apache-2.0

wiff

1453

xxxoooxoxo/wiff

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 70 tokens together

Deterministic, resumable multi-agent workflows that orchestrate Codex, Claude, Cursor, and Kimi agents — five MCP tools plus the workflow-authoring skill.

not rated 5 changed 3d ago A tokens not measured original MIT

agentic-skills

1454

theagenticguy/agentic-plugins

Plugin Claude Code

Bundles 1 skill, 7 MCP servers · 237 tokens together

Flagship skills for AI coding agents. Includes workbench-builder: disposable localhost Bun.serve + bun:sqlite + React 19 + Astryx workbenches with a two-way human↔agent loop over SSE — eval viewers, PR review rooms, document-redline surfaces, grid/spreadsheet editors, multi-surface triage queues, and trace replays…

not rated 5 1mo ago A tokens not measured original MIT

goal-driven

1456

MAX0MAX/goal-driven

Plugin Claude Code

Bundles 3 skills · 132 tokens together

Contract-first skill package for Claude Code. Public goal-contract-writer produces canonical Goal Contracts with paired fresh-subagent verifier and progress tracker runtime skills.

not rated 5 3mo ago A tokens not measured original MIT

contextdocs

1458

littlebearapps/contextdocs

Plugin Claude Code

Bundles 4 skills, 3 commands, 2 agents · 529 tokens together

Your AI agent maintains its own context files — a Claude Code plugin with an AGENTS-first model that covers Codex, Copilot, Cursor, Gemini, and 3 more tools. Signal Gate filtering, Context Guard hooks, health scoring, and MEMORY.md promotion.

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

completely

1459

23ag1/completely

Plugin Claude Code

Bundles 8 skills, 1 agent, 3 hooks · 710 tokens together

Quality-first harness for autonomous AI coding agents: deterministic gates + a default-FAIL evaluator in the close path of the loop, over a Beads task spine. Done is earned, not asserted. Unifies GSD + Beads; stack-agnostic.

not rated 5 3mo ago A tokens not measured original MIT

hmd

1460

randomittin/heimdall

Plugin Claude Code

Bundles 6 skills, 19 commands, 16 agents, 7 hooks, 1 MCP server · 2,354 tokens together

Nothing ships unproven. Heimdall is an autonomous multi-agent orchestrator for Claude Code that turns one prompt into a finished project — and keeps moving the bar on what counts as done: every plan wires an external, falsifiable oracle so the implementation can never grade its own homework, and the merge stays…

not rated 5 changed 4d ago A tokens not measured original MIT

wakeflow

1463

GxFn/Wakeflow

Plugin Claude Code

Bundles 3 skills, 7 commands, 1 MCP server · 285 tokens together

A disciplined control loop for multi-window Claude Code work: a controller window dispatches scoped task packages across a tmux-resident fleet, collects immutable target results, obtains independent Test validation, reviews the evidence, and decides the next step. Explicit on-disk state roots keep the run auditable…

not rated 5 yesterday A tokens not measured original MIT

compounded

1464

ankitkr3/compounded

Plugin Claude Code

Bundles 5 skills, 9 commands, 1 agent, 3 hooks · 759 tokens together

Turns your agent into a trainable employee. Learns rules from your corrections (with your approval), and skills earn autonomy through demonstrated reliability — proposed → verified → trusted → autonomous. No daemon. No cloud.

not rated 5 2mo 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: