TDD agents

452 tagged TDD, measured the same way as everything else here.

Browse within: ai-coding 18code-quality 13ai-development 12spec-driven-development 11ai-workflow 10github-copilot 10clean-architecture 9angular 7Code Generation 6agentic-coding 6antigravity 6autonomous-coding 6taskmaster 6yolo 6

stagehand-expert

25

chongdashu/browserbase-claude-code-stagehand

Agent Claude Code

Use this agent when you need executable Stagehand test files for TDD workflow. ALWAYS checks latest Stagehand documentation first, then creates hybrid AI+data-testid tests that work locally and in cloud. Expert in LOCAL vs BROWSERBASE modes, proper API usage (stagehand.page.act/observe), and fallback strategies for…

not rated 52 1y ago A 0 tokens

tdd-guide

26

yi-john-huang/sdd-mcp

Agent Claude Code

Part of sdd-mcp

TDD coaching agent for test-driven development methodology.

not rated 51 1mo ago A 13 tokens original MIT

implementer-agent

27

marconae/speq-skill

Agent Claude Code

Standard implementation worker for spec-driven development spawned by the speq-implement orchestrator. Executes untagged tasks.md tasks via TDD; [expert] tasks route to implementer-expert-agent instead.

not rated 50 1mo ago A 45 tokens original MIT

timothywarner/copilot-dev

Agent

Autonomous feature builder — plans, writes tests first (TDD), implements, runs tests, and iterates until green. Handles frontend + backend + tests end-to-end.

not rated 46 1mo ago A 41 tokens original MIT

code-review

29

YuDefine/nuxt-supabase-starter

Agent Claude Code

A code-review agent for Nuxt 4, Vue 3, TypeScript, and Supabase projects. Code review is the practice of checking proposed changes for problems before they are merged or committed.

not rated 45 changed today A 47 tokens original MIT

dispatch-fallback

30

YuDefine/nuxt-supabase-starter

Agent Claude Code

A fallback agent for carrying out scan, extraction, file-reading, and pattern-matching work when specified model service quotas are exhausted. It follows routing rules that determine when it may take over and which model level to use.

not rated 45 changed today A 123 tokens original MIT

screenshot-review

31

YuDefine/nuxt-supabase-starter

Agent Claude Code

An agent for taking screenshots of a website or app and checking whether its interface looks correct. It returns a report based on the requested visual checks.

not rated 45 today A 73 tokens original MIT

iSerter/laravel-claude-agents

Agent

Part of laravel-claude-agents

Expert in Laravel testing with Pest PHP and PHPUnit, specializing in feature tests, unit tests, database testing, API testing, and TDD practices. Invoked for test creation, test strategy, and quality assurance.

not rated 44 4mo ago A 48 tokens original MIT

feature-implementer

33

DGouron/review-flow

Agent Claude Code

Implement a ReviewFlow feature via TDD inside-out. Receives a validated plan (docs/plans/ .plan.md) and spec (docs/specs/ .md), implements all layers with RED-GREEN-REFACTOR, self-reviews, and persists a report. Triggers when the user says "implement feature", "start implementation", "implement spec", or "run…

not rated 42 20d ago A 89 tokens original MIT

tdd

34

DGouron/review-flow

Agent Claude Code

You drive Test-Driven Development with Double Loop: Acceptance tests (outer) + Unit tests (inner). You operate autonomously.

not rated 42 20d ago A 0 tokens original MIT

implementer

35

streetrace-ai/streetrace

Agent Claude Code

Use this agent when you need to implement features based on design documents, RFCs, or task definitions. This agent follows TDD principles and ensures code quality through comprehensive testing. Examples of when to invoke this agent:\n\n \nContext: The user has a design document and wants to implement a new…

not rated 38 4mo ago A 338 tokens original MIT

planner

36

bish-x/claude-bishx

Agent

Part of bishx

Creates bite-sized, TDD-embedded, one-shot-executable implementation plans for bishx-plan. Produces plans that a fresh Claude session can execute without questions.

not rated 34 4mo ago A 35 tokens

jmanhype/speckit

Agent Claude Code

Specializes in backend API implementation following TDD and contract-driven development. Uses Specmatic for contract testing and validation.

not rated 26 5mo ago A 28 tokens original MIT

jmanhype/speckit

Agent Claude Code

Specializes in React/TypeScript frontend development following TDD and component-driven development. Uses Specmatic for backend mocking during parallel development.

not rated 26 5mo ago A 32 tokens original MIT

executor-v3

39

malakhov-dmitrii/forge

Agent

Part of beast-forge

TDD implementation agent for forge pipeline-v3. Spawned per-stream; enforces RED-GREEN-REFACTOR with retry protocol and phase-2 short-circuit.

not rated 25 1mo ago A 39 tokens original MIT

planner-v3

40

malakhov-dmitrii/forge

Agent

Part of beast-forge

Creates bite-sized, TDD-embedded, one-shot-executable implementation plans with DAG emission, claim verification fan-out, and overlap-matrix self-check. Produces plans that a fresh Claude session can execute without questions.

not rated 25 1mo ago A 48 tokens original MIT

kwb

41

punt-labs/prfaq

Agent Claude Code

You are inspired by Kent Beck — creator of Extreme Programming and Test-Driven Development, co-author of JUnit, and author of Smalltalk Best Practice Patterns (1997), Test-Driven Development: By Example (2002), and Implementation Patterns (2007).

not rated 25 3d ago A 62 tokens original MIT

implementer

42

andyzengmath/quantum-loop

Agent

Part of quantum-loop

Per-story implementation agent. Implements exactly ONE user story from quantum.json following TDD methodology. Spawned fresh for each story with no memory of previous iterations.

not rated 24 2mo ago A 34 tokens original MIT

hive-coder

43

namastexlabs/automagik-hive

Agent Claude Code

End-to-end development specialist handling feature implementation and production bug fixes with TDD discipline.

not rated 24 8mo ago A 22 tokens original MIT

implementer

44

nanparth/ai-skill-hub

Agent

Implement one task from a plan using strict TDD, commit, self-review, and report.

not rated 23 11d ago A 0 tokens original MIT

coder

45

lipingtababa/agents-zone-skillset

Agent

Implements code to make tests pass (TDD Green phase). Reads story + tests, implements, iterates until done.

not rated 22 4mo ago A 27 tokens

tester

46

lipingtababa/agents-zone-skillset

Agent

Writes tests from story file (TDD Red phase). Reads story, writes failing tests, verifies they fail.

not rated 22 4mo ago A 24 tokens

executor

47

datit309/supergraph

Agent

Part of supergraph

Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.

not rated 21 6d ago A 25 tokens original MIT

worker

48

dennisonbertram/claude-coordinator

Agent

Part of claude-coordinator

Strict TDD implementation worker for feature and bugfix tasks. Produces an auditable commit trail (red → green → regression) so the test-first practice is provable from git history.

not rated 21 1mo ago A 44 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: