Building agents agents

2,814 tagged Building agents, measured the same way as everything else here.

Browse within: agents 167claude-code-plugin 165agentic-ai 130ai-coding 115LLM 114cli 99agent 80agent-orchestration 63skills 57github-copilot 56spec-driven-development 55prompt-engineering 53Multi-Agent 51ai-tools 48

architect

386

alaminut/claude-orhcestrator

Agent Claude Code

Deep systems design, architectural blueprints, and cross-subsystem planning before coding.

not rated 2 1mo ago A 18 tokens

dsys-rules-agent

387

jamesbtlr/dsys

Agent Claude Code

Reads design-system.json and writes CLAUDE.md enforcement rules and .dsys/STYLE-GUIDE.md.

not rated 2 6mo ago A 28 tokens

framework-reviewer

388

Carchaloneo22/creador-de-frameworks-agenticos

Agent Claude Code

QA specialist subagent that audits a completed agentic framework before packaging — checks CLAUDE.md completeness, agent/skill consistency, hook safety, MCP credentials hygiene, link integrity, and applies the Swiss Cheese evaluation model (deterministic checks + state assertions + LLM-as-judge). Invoked by…

not rated 2 3mo ago A 74 tokens

cyclops

389

yelaco/claude-xmen

Agent Claude Code

Live field coordinator for Cerebro agent teams; owns the shared task list, assigns work to teammates via TaskUpdate and SendMessage, verifies results directly, and reports completion to Cerebro.

not rated 2 3mo ago A 40 tokens

orchestrator

390

jy315189/everything-cursor

Agent Claude CodeCursor

Agent "orchestrator" from jy315189/everything-cursor, covering agent — ai project manager, identity, thinking process, step 1: classify the task and step 2: announce the plan.

not rated 2 7mo ago A 0 tokens original MIT

sdlc-orchestrator

391

mcku/ai-sdlc-orchestrator

Agent Claude Code

Subagent that runs the AI-SDLC framework end-to-end in an isolated context. Use when delegating a full SDLC session to keep the main conversation lean. The subagent boots from .ai-sdlc/ENTRY.md and executes phases sequentially, returning a summary on completion.

not rated 2 2mo ago A 67 tokens

Info-Sentry Feedback

392

HariEshwar-J-A/info-sentry

Agent Claude Code

Supergroup interaction agent for Info-Sentry. Listens in the Feedback forum topic, processes inline button callbacks from Main-News and Predictions, and lets the user manage their tracked interests through natural language. Runs on DeepSeek V3.2.

not rated 2 1mo ago A 53 tokens original MIT

jg-benchmarker

393

JahnelGroup/multi-agents

Agent Claude Code

Utility agent for pulling benchmark data, evaluating cost vs performance, and recommending which models to use for which agents. Use on-demand for model assignment reviews.

not rated 2 2mo ago A 35 tokens

base-skill-engineer

394

LSRabbit6/cursor-genesis

Agent Claude Code

You are the Base Skill Engineer, a specialized Subagent responsible for expanding the capabilities of the Cursor Project.

not rated 2 24d ago A 38 tokens

agy

395

squall-chua/skills

Agent Claude Code

Delegate a task to the agy CLI and report back what it produced. Use when the user asks to run something with agy, or wants a task handled by a non-Claude model such as Gemini or GPT-OSS. BEFORE dispatching, if the user did not name a model, run agy models and ask them to pick one with AskUserQuestion. List the CLI's…

not rated 2 9d ago A 148 tokens original MIT

worker-coder

396

a1f/agent-templates

Agent Claude Code

Implements exactly one scoped task in one of three modes the architect names — GREEN (minimal code to pass one named failing test), REFACTOR (behavior-preserving restructure, tests stay green), or NON-BEHAVIORAL (an exact config/rename/docs edit) — then commits. Scope-locked: never exceeds the single task it was…

not rated 2 9d ago A 82 tokens original MIT

implementer

397

Mico-rstar/code-agent

Agent Claude Code

An implementation agent that writes code and performs self-checks from instructions given by a Leader. It works only within the assigned scope and reports when finished.

not rated 2 2mo ago A 33 tokens

{{AGENT}}

399

eristoddle/agent-skills

Agent Claude Code

You execute the active task for {{PROJECT}}. The planning thread has already made the design decisions; your job is to build exactly what {{TASKDOC}} specifies — no more, no less.

not rated 2 15d ago A 61 tokens original MIT

gemini-rescue

400

quytu-persefoni/claude-plugin-psfn

Agent Claude Code

Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass from Gemini, needs a deeper root-cause investigation, or should hand a substantial coding task to Google Gemini through the CLI.

not rated 2 5d ago A 45 tokens

agent-creator

401

BrainDAO/iq-claude-config

Agent Claude Code

Agent "agent-creator" from BrainDAO/iq-claude-config, covering agent created: [identifier], configuration, file created, how to use and next steps.

not rated 2 2mo ago A 0 tokens

plugin-agent-reviewer

402

ToshikiImagawa/unity-claude-code-tools

Agent Claude Code

A design reviewer checks Claude Code plugin sub-agents against guidelines written in AGENTS.md. A sub-agent is a helper agent that performs a focused task inside a larger plugin.

not rated 2 8mo ago A 65 tokens original MIT

ThiagoGuislotti/copilot-instructions

Agent Claude Code

Secondary repository-owned Copilot controller profile for the same Super Agent lifecycle used by the canonical /super-agent starter. Use this workspace-controller alias when you specifically need the repo-owned Copilot agent profile without creating a second visible /super-agent entry.

not rated 2 2mo ago A 55 tokens original MIT

README

404

krzemienski/shannon-mcp

Agent Claude Code

A comprehensive collection of specialized AI subagents for Claude Code, designed to enhance development workflows with domain-specific expertise.

not rated 2 9mo ago A 0 tokens

architect

405

95gabor/agentic-workflow

Agent Claude CodeCursor

System architect. Use proactively when designing cross-cutting features, API or schema changes, auth flows, or recording technical decisions before FE/BE implementation.

not rated 2 +1 1mo ago A 32 tokens

orchestrator

406

sanchitnis/SrujanaSangama

Agent Claude Code

The top-level routing brain for the AI agent system. Reads every user message, loads relevant memory context, dispatches to the right specialist agent(s), and runs post-processing to update memory and logs. Always active — never bypassed. Triggers on every user message. Synthesises multi-agent responses into a single…

not rated 2 28d ago A 69 tokens

gsd-debugger

407

Lua2147/claude-toolkit-catalog

Agent Claude Code

Investigates bugs using scientific method, manages debug sessions, handles checkpoints. Spawned by /gsd:debug orchestrator.

not rated 2 4mo ago A 30 tokens

goap-agent

408

d-o-hub/github-template-ai-agents

Agent Claude Code

Invoke for complex multi-step tasks requiring intelligent planning and multi-agent coordination. Use when tasks need decomposition, dependency mapping, parallel/sequential/swarm/iterative execution strategies, or coordination of multiple specialized agents with quality gates and dynamic optimization.

not rated 2 yesterday A 51 tokens 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: