Building agents agents

marcusgoll/Spec-Flow

Agent Claude Code

Is this a workflow phase (spec, plan, tasks, optimize, ship)? ├── Yes → Use PHASE AGENT (spec-agent, plan-agent, etc.) └── No → Continue...

ThendCN/ai-team-skills

Agent Claude Code

A worker role that receives coding tasks, runs Codex CLI to perform them, reviews the results, and reports back.

LonelyHerbivore/Trellis-Herbivore

Agent Claude Code

Architecture sparring partner for Trellis. Pre-design boundary, contract, migration, release, and blast-radius review. Demands concrete file paths, command shapes, compatibility analysis, and rejected alternatives. NOT an implementer.

arpitnath/claude-capsule-kit

Agent Claude Code

PROACTIVELY use this agent when developing or debugging mini-agents, understanding agent patterns, or troubleshooting MCP integrations. Read-only agent for production safety.

automagik-dev/forge

Agent Claude Code

Autonomous wish coordinator with Genie orchestrator validation.

ruvnet/sublinear-time-solver

Agent Claude Code

Sub-agent definitions organized by type and purpose with specific capabilities and tool restrictions.

ThomasMoreAI/legal-skills-open

Agent Claude Code needs its repo

Extract legal skills from a public marketplace into the local ./lawve/ quarantine for curator review. Initially handles lawve.ai (Next.js RSC). Applies the repo license whitelist at write time — AGPL/Proprietary/no-license skill bodies are NOT saved, only logged in INDEX.md. Use when asked to harvest skills from…

fitlab-ai/agent-infra

Agent Claude Code

Execute exactly one agent-infra lifecycle stage in a fresh context.

MikeCodeur/killer-saas

Agent Claude Code

Implements a planned story in an isolated context. Invoked by /ks-execute.

sverklo/sverklo

Agent Claude Code

Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…

gutomec/nirvana-os-engine

Agent Claude Code

Layer 2 of the dispatch-quality plan. Runs between targetplancommitted and the actual dispatch. Single responsibility: verify dispatch integrity before the maestro pays for execution. Reads: the brief (verbatim) the target plan (mind-clones / squads / businesses chosen) the system prompt(s) about to be sent to the…

timpara/opencode-academic-research

Agent Claude Code

Orchestrates the full multi-skill academic research pipeline and manages agent handoffs across phases.

roundpilot/superpowers-antigravity

Agent Claude Code

Implements one task from an approved implementation plan - writes tests and code, verifies, commits, self-reviews, and reports status. Dispatch with the full task text; do not use for review work.

danielmeppiel/genesis

Agent Claude Code

Use this agent to design or critique agentic primitive modules (skills, persona scoping files, scope-attached rule files, orchestrator workflows). Activate BEFORE drafting any natural-language primitive content, when refactoring existing modules, or when assessing whether a primitive change adheres to PROSE, Agent…

naveedharri/benai-skills

Agent Claude Code

Eval Agent for AutoResearch. Designs the scoring system — receives user-confirmed criteria and the target prompt, then generates eval.py + testcases.json (deterministic mode) or rubric.md + testcases.json (AI judge mode). The main agent never sees the eval artifacts in detail.

kinncj/Heimdall

Agent Claude Code

Primary orchestrator agent. Controls the entire 8-phase pipeline. Never writes code — delegates all implementation to specialist agents. Manages GitHub issues, quality gates, and escalation.

GregorBiswanger/featherspec

Agent Claude Code

Evidence scout used only by /sdd-reverse-specify. Reads the code behind one capability and writes its report to .sdd-reverse/reports/. Not for general tasks.

amalik/convoke-agents

Agent Claude Code

Model Curator - Contextual capabilities model generation and curation.

thaitype/chief

Agent Claude Code

Goal-driven Planner/Orchestrator for the Chief Agent Framework. Reads AGENTS.md (highest priority), then .chief/rules, then milestone-specific goals. Produces and maintains milestone plans (plan/todo.md + task specs), delegates execution to builder-agent, delegates verification to tester-agent, and decides next…

cjhyy/codeshell

Agent Claude Code

General multi-step agent with full tools — research, code, and execute.

aidlc-io/aidlc

Agent Claude Code

Coordinator agent that runs the SDLC loop — dispatches workers, handles human gates, and manages phase context. Used by the /advance-epic skill.

joelhooks/joelclaw

Agent Claude Code

Restate PRD story executor for joelclaw with strict scope, coordination, and clean-commit discipline.

evan043/claude-cli-advanced-starter-pack

Agent Claude Code

L1 orchestrator that coordinates multiple phase-dev-plans within a roadmap. Use this agent to decompose roadmap scope into plans and manage cross-plan dependencies.

DenizOkcu/claude-code-ai-development-workflow

Agent Claude Code

Autonomous SDLC orchestrator. Research → Architecture → Plan → Implement → Parallel Expert Review → Documentation → Production Ready. Use for complete feature development.