Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
aws-samples/sample-aidlc-design-reviewer
Agent Claude Code ✓ vendor
Alternatives phase of the AIDLC design review. Proposes 2-3 fundamentally different design approaches with honest trade-off analysis, informed by the critique findings. Returns strict JSON. Invoked by the /design-review skill — not usually run directly.
Agent Claude Code
Reads a review thread and the surrounding document context, then proposes a reply or edit as a message.posted event with commit:null. Never edits the document body and never commits — the principal applies the proposal and creates the git commit. Use proactively when the principal fans out thread review tasks in…
Agent Claude Code
Designs systems, defines technical specifications, and makes high-level architectural decisions.
lovekyrie/claude-code-best-practices
Agent Claude Code
A separate code-review helper that examines a change set or chosen files and returns an organized review.
eliottvalette/Anthropic-Voodoo-Hackathon
Agent Claude Code
Headless browser tester and root-cause diagnostician for the proto-pipeline-m single-file HTML playables. Runs Playwright on the playable, captures the state trajectory and console errors, cross-references symptoms with the source sketches in 04sketches.json and the 04plan.json contract, and returns a structured…
Agent Claude Code
Validates proposed changes follow existing codebase patterns. Use proactively before implementing features or refactoring code.
Agent Claude Code
Writes unit and integration tests for new or modified code. Use this agent when the user asks to add test coverage, test-drive a feature, or when a PR lacks tests.
Agent Claude Code
Use this agent when you need a comprehensive UI/UX audit, design review, or visual refinement of the app's screens and components. This agent focuses exclusively on visual design, layout, spacing, typography, color, motion, accessibility, and responsiveness — it does not touch functionality or application…
Agent Claude Code
Score et classe les sources brutes d'une veille technologique selon 5 critères pondérés.
zacbraddy/ai-software-dev-workbench
Agent Claude Code
Audits a single implemented task for completeness, quality, and alignment with requirements - returns structured findings without user interaction.
michaelcjoseph/agent-coding-setup
Agent Claude Code
Reviews changes for system-level architectural concerns — module boundaries, resource leaks, startup/shutdown correctness, error propagation, and centralization violations.
Agent Claude Code
Use this agent when the user asks anything about Minecraft mod or plugin development - creating mods, adding features, debugging API issues, understanding Forge/Fabric/NeoForge/Paper APIs, or choosing the right approach. This is the primary entry point for Minecraft development tasks. It analyzes requirements…
VictorCostaOliveira/agents-tdd-flow
Agent Claude Code
Code review (SOLID, arquitetura, qualidade). No fluxo TDD — SEMPRE persiste AVALIACAO.md na pasta da feature com TODOS os pontos para o devoso ler e corrigir. Git diff + critérios quando houver. Security: use security-auditor.
Agent Claude Code
Use this agent when you need to clean up and optimize your codebase by removing unused code, eliminating duplication, and updating outdated documentation. Examples: Context: User has just finished implementing a new feature and wants to clean up the codebase before committing. user: "I just finished adding the new…
gmen1057/claude-code-starter-kit
Agent Claude Code
Place your project-specific agent definitions here as .md files.
Agent Claude Code
Implementation agent for complex, multi-step coding tasks. Use proactively when delegating code writing, bug fixing, refactoring, or any task requiring both exploration and modification. Replaces built-in general-purpose for all implementation tasks.
Agent Claude Code
Use this agent when you need to write error types in Rust code. This agent should be invoked for all things relating to writing error types, but not error handling itself. Examples:\n\n \nContext: The user has asked for an existing codebase's error handling to be improved.\nuser: "I've a need for error handling…
Agent Claude Code
A code-review agent that checks changes for working tests, clear intent, repeated code, unnecessary complexity, and Python style issues.
Agent Claude Code
Refactoring agent that improves code quality without changing behavior.
dpanasenko-tech/claude-dev-pipeline
Agent Claude Code
Use after reviewer approves a slice. Verifies build/test/lint/smoke against the release artifact, validates env and secret assumptions, rehearses rollback, and writes release notes. Last gate before merge/deploy.
maurizio100/human-agent-workflow-bundle
Agent Claude Code
Read-only PR review agent. Given a PR number and story/issue ID, reviews the pushed diff against the change's stated intent and the project's own documented conventions (discovered from CLAUDE.md and the docs it points to), applies a security lens when the change touches auth, posts a summary review comment plus…
Fomo-Driven-Development/strategic-claude-base
Agent Claude Code
Pair programming navigator agent that uses Codex to provide strategic guidance, code review, and architectural oversight while the main agent drives implementation. Focuses on big-picture thinking, pattern recognition, and quality assurance without writing files.
maxime-tremblay/APEXLang-Project-Template
Agent Claude Code
Purpose.
lucasandradeb/my-claude-code-config
Agent Claude Code
Revisa uma única PR do GitHub e posta os comentários inline. Projetado para ser disparado em paralelo — um subagente por PR. Requer no brief: número da PR e owner/repo.
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: