ai-coding agents

felipefontoura/spec-driven-development-book

Agent Claude Code

Produces requirements.md and design.md from an approved idea or feature request. Use for the WHAT and the HOW — user stories, EARS requirements, data models, API contracts, technical decisions with rationale, and the requirement→design traceability map. Never writes implementation code.

felipefontoura/spec-driven-development-book

Agent Claude Code

Implements one approved task from tasks.md — code plus tests — after checking that .status reads tasks:approved. Follows the spec exactly, stops on ambiguity instead of guessing, and reports verification evidence. Use for the EXEC phase, one task at a time.

felipefontoura/spec-driven-development-book

Agent Claude Code

Reviews an implementation against requirements.md, design.md, tasks.md, and the produced code in a fresh context. Reports coverage gaps and spec violations with verification evidence — not stylistic opinions. Use before treating a feature as done. Reviews only; does not implement fixes.

pangelini777/oh-my-gem

Agent

Taskboard Manager. Tracks stateful progress and manages the project ledger. Use for maintaining the "Source of Truth" for tasks.

pangelini777/oh-my-gem

Agent

Batch Worker. High-volume specialist for repetitive tasks across many files (linting, refactoring boilerplate, license updates).

pangelini777/oh-my-gem

Agent

Code Maker. Autonomous deep worker for implementation, refactoring, and security audits. Use for end-to-end execution of complex coding tasks.

daphnee-ovo/dev-flow

Agent

You are an independent design reviewer. Review BRAINSTORM.md to find issues that main agent and user may have overlooked during discussion.

daphnee-ovo/dev-flow

Agent

You are an independent challenger for task decomposition. Your goal is to find problems in task breakdown.

daphnee-ovo/dev-flow

Agent

The current test execution owner is the dow test CLI. The /test workflow entry invokes that CLI; it does not dispatch a second independent test plan.

xcodethink/open-claude-code-skills

Agent

A read-only quality-audit agent that treats “finished” as something to test rather than assume. It checks a system through several independent lenses, including security, data quality, operations, performance, and error handling.

Aleksacom/claude-code-orchestration-agents

Agent Claude Code

Routes individual planning questions to AUTORESOLVE or ESCALATE. Used when cm-planner surfaces multiple questions and the main agent needs to decide which require human ratification vs which can be auto-resolved with the recommended option. Read-only — produces routing verdicts, not implementations.

Aleksacom/claude-code-orchestration-agents

Agent Claude Code

Architectural authority for all work in this repository. Invoked before responding to ANY user request. Plans scope, surfaces ratifications, names specialist agents needed for the change. Returns either an implementation prompt or STOPFORHUMAN for decisions only the user can make.

Aleksacom/claude-code-orchestration-agents

Agent Claude Code

Audits decision documents under docs/decisions/ for convention compliance. Runs when decision docs touched OR sub-phase declared closed. Checks frontmatter, structure, length, content-sync between docs and metrics, override-block format. Returns ALL CLEAR, OVERRIDES PRESENT, or BLOCK CLOSURE.

shahidshabbir-se/my-pi-setup

Agent

Designs and implements REST and GraphQL APIs with best practices.

shahidshabbir-se/my-pi-setup

Agent

Expert in TypeScript type system, generics, and advanced type patterns.

shahidshabbir-se/my-pi-setup

Agent

Builds React/Next.js UI components with accessibility and responsive design.

rohanmistry231/Claude-Code-Project-Structure-Learning-Repository

Agent Claude Code

Sub-agents are specialist Claude instances that the main Claude agent can spawn to handle a focused, isolated task.

rohanmistry231/Claude-Code-Project-Structure-Learning-Repository

Agent Claude Code

A specialized sub-agent that performs security-focused reviews of the Blog API codebase. It looks for authentication gaps, injection vulnerabilities, data exposure, and insecure configs.

getreka/reka

Agent Claude Code

A code-review agent that checks changes against a project's design patterns, ADRs, and recommended practices. ADRs are short records explaining important architecture decisions.

getreka/reka

Agent Claude Code

A feature-building agent that uses the existing architecture as context when creating new functionality.

getreka/reka

Agent Claude Code

An agent for operating a retrieval-augmented generation system, or RAG system, which lets an AI search stored information before answering. It manages indexing, collections, memory, and system health.

hoangatg/ai-agent-toolkit

Agent

Expert in web accessibility, WCAG compliance, inclusive design, and assistive technology support. Use for accessibility audits, ARIA implementation, and inclusive UX. Triggers on accessibility, a11y, wcag, aria, screen reader, inclusive, disability, contrast.

hoangatg/ai-agent-toolkit

Agent

Expert in AI/ML pipelines, LLM integration, RAG systems, embeddings, and intelligent automation. Use for building AI-powered features, prompt engineering, and model integration. Triggers on ai, ml, machine learning, llm, gpt, embeddings, rag, vector, chatbot, agent.

hoangatg/ai-agent-toolkit

Agent

Expert in system design, architectural decisions, trade-off analysis, and technical strategy. Use for high-level design, ADRs, scalability planning, and technology evaluation. Triggers on architecture, system design, scalability, trade-off, ADR, design decision, tech stack, distributed system.