Building agents

38,494 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

headsign

6745

meganemura/headsign

Plugin Claude Code

Bundles 3 skills, 3 hooks · 276 tokens together

A tiny phase gate for coding agents: your shell checks decide pass/fail (never the LLM), your workflow routes the agent (advance / retry / escalate / done). The agent drives, headsign holds the state.

not rated 1 changed 4d ago A tokens not measured original MIT

didvc/claude-chrome-multi-instance-warn

Plugin Claude Code

Bundles 1 hook

An agent driving a browser tends to start a new one rather than use the one already open, and to size its work off the core count. This warns once per session when a tool payload is about to do either. Never blocks.

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

mstack

6749

romerma/mstack

Plugin Claude Code

Bundles 12 skills, 5 agents, 5 hooks · 878 tokens together

Rigorous, verifiable agent workflows for Claude Code. A router over playbooks, an opt-in spec path, durable state on disk, and gates that are code rather than prose.

not rated 1 27d ago A tokens not measured original MIT

cursor-rules

6750

Jack-infinity420/three-mechanisms-plugin

Cursor rule Cursor

A set of rules for an AI coding agent built around three work areas: reports and requests, follow-up checks, and information services.

not rated 1 4mo ago A 530 tokens

10CG/aria-plugin

Plugin Claude Code

Lists 1 plugin

A plugin marketplace package built around AI-driven domain-driven design, a way to organise software around the business concepts it models. Its description lists 42 skills, 11 agents, and hooks, including a default secret-protection hook.

not rated 1 changed 7d ago A tokens not measured

superpowers-graph

6752

RonMizrahi/superpowers-graph

Plugin Claude Code

Bundles 1 skill, 1 agent · 247 tokens together

The Superpowers software-development methodology executed as a guarded state machine: 21 typed nodes, 96 total exit guards, 9 bounded retry loops, durable run state that survives compaction, and a ledger recording every step that could not run.

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

auto-develop

6754

aminry/auto-claude-plugins

Plugin Claude Code

Bundles 2 commands · 29 tokens together

Creates custom auto-develop loops for any feature in any codebase — analyzes features, builds capability specs, and generates autonomous iterative development skills that add new functionality.

not rated 1 4mo ago A tokens not measured original MIT

affirm

6755

nullphase-net/enfurbish

Plugin Claude Code

Bundles 1 skill, 1 hook · 50 tokens together

Approval gate for instruction files. Surfaces new or modified CLAUDE.md, .claude/rules/ files (project and user-global) and the files they @import at session start; the user explicitly affirms them before Claude treats them as trusted.

not rated 1 changed yesterday A tokens not measured original MIT

advisor-strategy

6756

aivsomkar/advisor-strategy-skill

Plugin Claude Code

Bundles 1 skill · 88 tokens together

Advisor Strategy skill for Claude Code — spawns a stronger model (Opus) as a strategic advisor for architecture, security, debugging, and performance decisions.

not rated 1 5mo ago A tokens not measured

self-improvement

6757

sh5623/self-improvement

Plugin Claude Code

Bundles 3 skills, 1 agent, 1 hook · 265 tokens together

When a convention bites you, fix the convention — an evidence-gated repair loop (detect → classify → verify → codify → propagate → record) plus budgets, demotion and archiving that keep rule docs from growing without bound. Stack-agnostic.

not rated 1 changed 13d ago A tokens not measured original MIT

cantos

6758

ne11nn/cantos-plugin

Plugin Claude Code

Bundles 25 skills, 2 commands, 11 agents, 2 hooks · 1,808 tokens together

The full Cantos system as a one-command install: a self-improving, multi-agent assistant orchestrator for Claude Code. /cantos:init scaffolds the whole writable system into a project; /cantos:start runs it for one session. Bundles the orchestrator, specialist assistants, sub-agents, workflows, references, and a…

not rated 1 today A tokens not measured original MIT

skills

6759

vimoxshah/skills

Plugin Claude Code

Bundles 10 skills, 1 command, 18 agents · 2,185 tokens together

Skills and agents for Claude Code — visual verification, shareable HTML artifacts, arXiv research intake, model routing, deck and theme systems, and specialist advisor agents.

not rated 1 21d ago A tokens not measured original MIT

silicon-circle

6760

txw842lkj-cmd/silicon-circle-skill

Plugin Claude Code

Bundles 1 skill · 136 tokens together

Explore earning with AI through task trading and Skill commerce: find paid work, sell Agent Skills, deliver results, and buy or run Skills. Check live opportunities, fees and Circle Credits terms. No guaranteed income.

not rated 1 changed 13d ago A tokens not measured original MIT

ringmaster

6761

raghatatepiyush/ringmaster

Plugin Claude Code

Bundles 5 skills, 1 command, 3 agents, 3 hooks · 1,431 tokens together

Turns Claude Code into a disciplined engineering team: it frames the goal, plans behind an approval gate, routes each step to the best specialist plugin (with built-in fallbacks), and runs a bundled Test Architect, an adversarial Security Gate, a two-axis code review, and an ownership review that makes sure a…

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

cloudone

6762

pcvelz/cloudone

Plugin Claude Code

Bundles 3 commands · 191 tokens together

Spawn separate zero-token Claude Code sessions against a local model (llama-swap / llama.cpp) for long-running or simple side tasks — keep your main session in its prime context.

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

exolvra-genesis

6763

Evolvlabsai/Exolvra-Genesis

Plugin Claude Code

Bundles 1 skill, 3 commands, 3 agents · 359 tokens together

Minimal Exolvra Genesis loop orchestrator for Claude Code: a lead agent iterates builder subagents against blind, fresh-context critics comparing real output to a concrete quality bar, until the assembled work wins twice in a row.

not rated 1 changed yesterday A tokens not measured original MIT

relay

6764

spacegrowth/claude-relay

Plugin Claude Code

Bundles 20 skills, 1 agent, 4 hooks · 1,269 tokens together

Delegate work packets from a lead Claude Code session to executor sessions in their own iTerm tabs, with session reuse instead of always spawning fresh.

not rated 1 changed today A tokens not measured original MIT

conjure

6766

john-farina/claude-plugins

Plugin Claude Code

Bundles 7 commands · 311 tokens together

Build Claude Code skills, agents, hooks, and MCP servers from plain-language descriptions. Generate, validate, and ship plugins without writing boilerplate.

not rated 1 4mo ago A tokens not measured original MIT

brigade

6767

ushibo/brigade

Plugin Claude Code

Bundles 10 skills, 9 commands, 15 agents, 3 hooks · 2,375 tokens together

Your AI dev brigade for Claude Code. A chef (sprint planner) coordinates specialist agents (frontend, designer, nodejs, golang, devops) through wave-based execution with fan-out review, Bug Council for hard bugs, and sprint learnings between iterations. Zero dependencies.

not rated 1 2mo ago A tokens not measured copy · 86% MIT

oh-my-harness

6768

IISweetHeartII/oh-my-harness

Plugin Claude Code

Bundles 2 skills, 3 commands, 1 hook · 513 tokens together

The team-architecture factory for Claude Code — a meta-skill that turns a domain description into an agent team and the skills they use. Three native execution modes (Workflow orchestration, persistent named-agent collaboration, sub-agent delegation), six team-architecture patterns, and workflow-native quality…

not rated 1 23d ago A tokens not measured original Apache-2.0