The best Claude Code agents :)

Business Systems Analyst - Pattern discovery, spec creation, acceptance criteria definition

safe-agentic-workflow3mo430

@bybren-llcInstall Agent

Data Engineer - Database schema changes and migrations

safe-agentic-workflow3mo430

@bybren-llcInstall Agent

Fresh-context adversarial review of an implementation against its spec and rubrics. Read-only; use for the ADVERSARIAL REVIEW…

metaswarm3d430

@dsifryInstall Agent

Implementation planning and architecture design. Use when a plan must be drafted from research findings.

metaswarm3d430

@dsifryInstall Agent

TDD implementation of features and fixes. Use for the IMPLEMENT phase of a work unit.

metaswarm3d430

@dsifryInstall Agent

You are Alex, the Developer for this AI-run organization.

opengoat7mo428

@marian2jsInstall Agent

Coordinates multi-agent work using Royal Navy squadron patterns with sailing orders, risk-tiered quality gates, and a captain's…

nelson4mo424

@aspegioInstall Agent

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

abu-cowork2d422

@pm-shawnInstall Agent

Compare two outputs WITHOUT knowing which skill produced them.

abu-cowork2d422

@pm-shawnInstall Agent

Evaluate expectations against an execution transcript and outputs.

abu-cowork2d422

@pm-shawnInstall Agent

你是微信小程序反编译专家，负责将小程序包反编译为可读源码，并生成完整的文件资产清单。 **重点**：用户提供的目录下可能有多个子目录（每个子目录对应不同的小程序或子包），你必须对所有子目录逐一检测和反编译，不得遗漏。

wxmini-security-audit7mo422

@sssmmmwwwInstall Agent

你是安全敏感信息分析专家，负责基于 **Python 脚本预扫描的结果**（`raw_secrets.json`），对微信小程序中发现的敏感信息进行**智能分析、误报过滤、上下文判断和风险评级**。

wxmini-security-audit7mo422

@sssmmmwwwInstall Agent

你是微信小程序接口分析专家，负责基于 **Python 脚本预扫描的结果**（`raw_endpoints.json`），对提取到的接口进行**智能关联分析**：BaseURL 与路径片段的语义关联、接口去重与规范化、HTTP…

wxmini-security-audit7mo422

@sssmmmwwwInstall Agent

[Long-running, run synchronously] Use when user says: 'research X', 'learn about X', 'study X', 'build a knowledge tree for X',…

ensue-memory9mo421

@mutable-state-incInstall Agent

Implementation subagent for one decomposed unit of work in the evanflow-coder-overseer pattern. Uses vertical-slice TDD per…

evanflow6mo419

@evanklemInstall Agent

Read-only review subagent for one coder's output (or for cross-coder integration review) in the evanflow-coder-overseer pattern.…

evanflow6mo419

@evanklemInstall Agent

AI/ML research agent — model architecture analysis, training optimization, mechanistic interpretability, safety alignment,…

offensive-claude3w419

@hypnguyen1209Install Agent

Vulnerability research agent — identifies CVEs, finds exploit PoCs, maps attack chains, and develops custom exploitation…

offensive-claude3w419

@hypnguyen1209Install Agent

Blind adversarial checker — given ONLY a finding artifact and its evidence (never the author's reasoning), tries to refute it and…

offensive-claude3w419

@hypnguyen1209Install Agent

Coordinate presentations, color palettes, image sizing and visual consistency for requested architectural communication.

as3d417

@alpacalabsllcInstall Agent

Coordinate furniture and equipment selection, schedule preparation, product evidence cleanup and requested export.

as3d417

@alpacalabsllcInstall Agent

Execute an approved, context-resolved architecture or firm assignment through the relevant Arch Studio owners. Optional host…

as3d417

@alpacalabsllcInstall Agent

MUST BE USED when starting new projects or planning major changes. This agent specializes exclusively in system architecture…

guidance-for-claude-code-with-amazon-bedrock2w412

@aws-solutions-library-samplesInstall Agent

MUST BE USED when creating comprehensive architecture documentation for systems, APIs, or technical designs. This agent…

guidance-for-claude-code-with-amazon-bedrock2w412

@aws-solutions-library-samplesInstall Agent

Use PROACTIVELY during requirements gathering and before technical implementation begins. This agent specializes exclusively in…

guidance-for-claude-code-with-amazon-bedrock2w412

@aws-solutions-library-samplesInstall Agent

Adversarial quality gate that hunts for flaws and returns a formal verdict. Use before shipping an artifact, when a result looks…

lionagitoday412

@ohdearquantInstall Agent

Decomposes a goal into a multi-agent DAG, runs it, and synthesizes the results. Use when work needs several agents in a…

lionagitoday412

@ohdearquantInstall Agent

Deep ABAP code review expert. Analyzes code for best practices, security, performance, and design issues.

vscode-abap-remote-fs4d410

@marcellourbaniInstall Agent

Create new ABAP objects - classes, reports, function groups, etc.

vscode-abap-remote-fs4d410

@marcellourbaniInstall Agent

Query SAP database tables and analyze data.

vscode-abap-remote-fs4d410

@marcellourbaniInstall Agent

You are a research analyst. Your job is to scan project documents and extract information relevant to a specific product idea.

bmalph1d407

@larscoweInstall Agent

CommonMark standards, technical writing best practices, and style guide compliance.

bmalph1d407

@larscoweInstall Agent

You are a strategic advisor reviewing a product brief draft. Your job is to spot untapped potential — value the brief is leaving…

bmalph1d407

@larscoweInstall Agent

Use this agent to commit changes following ATLAS commit conventions. Works autonomously — no approval needed. By default commits…

software-engineer-ai-agent-atlas2w406

@syahiidkamilInstall Agent

Default manual QA runner. Executes written test cases (explicit steps with an expected result each) in a real browser and reports…

software-engineer-ai-agent-atlas2w406

@syahiidkamilInstall Agent

Manual QA runner for exploratory runs, visual judgment ("does this look right"), flaky flows, and cases the haiku runner marked…

software-engineer-ai-agent-atlas2w406

@syahiidkamilInstall Agent

Read-only adversarial contract reviewer. Reviews the full contract set against user scope, inventory, playbook rules, evidence…

zenith2mo403

@intelligent-internetInstall Agent

Engineering scrutiny subagent for a bounded validation-review question. Reviews current implementation, evidence surfaces,…

zenith2mo403

@intelligent-internetInstall Agent

Leaf real-surface validation lane for a bounded subset of engineering assertions. Exercises assigned behavior through a…

zenith2mo403

@intelligent-internetInstall Agent

You are a senior hardware design reviewer with deep experience in embedded systems, power electronics, RF, and production…

nextboard-hardware-solution6mo402

@leokemp223Install Agent

Background analyzer that runs on session start. Reads observations, creates instincts, detects clustering.

homunculus9mo398

@humanplaneInstall Agent

Use this agent for Flutter live-app inspection and live-edit workflows via the Flutter MCP toolkit server (MCP registry key…

mcp-flutter4d397

@arenukvernInstall Agent

Haiku 5.5 decision sampler for the deciding-with-confidence skill. Answers one sample prompt from `decide.py emit --agent…

claude-skillstoday396

@oaustegardInstall Agent

Use this agent when you need to refactor existing code, rewrite a module for better maintainability, decompose a large file into…

harnss5d395

@opensource03Install Agent

Use this agent when you want a comprehensive review of code quality, readability, structure, and maintainability. This agent…

harnss5d395

@opensource03Install Agent

Use this agent when the user needs information from project documentation files, SDK docs, protocol specs, or any `@docs`…

harnss5d395

@opensource03Install Agent

Triggers when Claude needs to find AI-writing patterns or suspect zones in KO/EN/ZH/JA text. Use this agent to run a full…

patina6w388

@devswhaInstall Agent

Triggers to audit whether a patina rewrite preserved meaning versus the original text. Invoke this agent after a rewrite is…

patina6w388

@devswhaInstall Agent

Triggers to re-scan a patina rewrite for residual AI tells and over-editing risk. Invoke this agent after a rewrite is produced…

patina6w388

@devswhaInstall Agent

Deep single-subsystem audit that reasons about state over time (caches, upserts, migrations, concurrent scans) rather than…

tokentelemetry5d387

@vasihemanthInstall Agent

Fast, wide sweep of one audit dimension across the codebase. Returns candidate findings with file:line evidence for the verifier…

tokentelemetry5d387

@vasihemanthInstall Agent

Adversarially verifies one candidate finding from /bug-audit — tries to REFUTE it by reading the code and, where cheap,…

tokentelemetry5d387

@vasihemanthInstall Agent

Scoped source research, verification, or coding through admitted Goal workspace tools only.

pi-workflow3d384

@agwabInstall Agent

Read-only source-backed research agent.

pi-workflow3d384

@agwabInstall Agent

Read-only codebase explorer for repo maps and context.

pi-workflow3d384

@agwabInstall Agent

Full Board of Directors deliberation with 5 expert directors assessing, discussing, and voting.

orchestrator-supaconductor6w384

@ibrahim-3dInstall Agent

Expert CEO advisor with 30 years entrepreneurship experience. Provides strategic guidance, business analysis, and leadership…

orchestrator-supaconductor6w384

@ibrahim-3dInstall Agent

Expert CMO advisor with 30 years of marketing leadership experience. Provides marketing strategy, brand positioning, and growth…

orchestrator-supaconductor6w384

@ibrahim-3dInstall Agent

You are a **Principal Accessibility Engineer** conducting a code review. You bring deep experience in inclusive design, assistive…

open-code-review4d384

@spencermarxInstall Agent

Dynamic topology switching coordinator with self-organizing swarm patterns and real-time optimization

open-code-review4d384

@spencermarxInstall Agent

V3 Architecture Decision Record specialist that documents, tracks, and enforces architectural decisions with ReasoningBank…

open-code-review4d384

@spencermarxInstall Agent

Reviews code for security issues including injection vulnerabilities, auth flaws, and secrets in code.

agent-config7mo380

@brianlovinInstall Agent

Reviews code for security issues including injection vulnerabilities, auth flaws, and secrets in code.

claude-config7mo380

@brianlovinInstall Agent

结构化辩论的正方：Round 1 陈述方案并写明已知局限，Round 3 逐条回应反方质疑。

ai-company2w377

@cronusl-1141Install Agent

结构化辩论的反方：Round 2 逐条挑战正方的前提与边界并给替代方案；也可单独派作对抗审查视角，给方案或设计找风险。

ai-company2w377

@cronusl-1141Install Agent

AI 功能开发：模型接入、提示词、检索与 Agent 工作流的实现和调优。通用 API 与存储层用 backend-architect。

ai-company2w377

@cronusl-1141Install Agent

This file is a durable summary of the current implementation state. It is intentionally concise and should not be used as a…

rosetta3d375

@griddynamicsInstall Agent

Generalized reusable lessons from agent sessions. Root causes converted into preventive rules, not incident-specific notes.…

rosetta3d375

@griddynamicsInstall Agent

Architect solution, transform intent into reliable tech specs, etc. Full subagent.

rosetta3d375

@griddynamicsInstall Agent

Analyzes web content and browser behavior using Chrome DevTools Protocol. Use when you need to inspect cached browser content,…

superpowers-chrome5w374

@obra-2Install Agent

Review the current repository for CodeGuard rule violations and emit SARIF 2.1.0 findings. Use when the user explicitly asks for…

codeguard-security2w371

@cosai-oasisInstall Agent

Provides expert AWS architecture and CloudFormation review capabilities specializing in Well-Architected Framework compliance,…

developer-kit2mo371

@giuseppe-trisciuoglioInstall Agent

Provides expert AWS DevOps engineering capabilities for CloudFormation templates, Infrastructure as Code (IaC), and AWS…

developer-kit2mo371

@giuseppe-trisciuoglioInstall Agent

Provides expert AWS Solution Architecture capabilities for scalable cloud architectures, Well-Architected Framework, and…

developer-kit2mo371

@giuseppe-trisciuoglioInstall Agent

Specialized agent for autonomous task execution planning, monitoring, and daemon management

nights-watch4w369

@aniketkarneInstall Agent

Autonomous end-to-end game creation pipeline. Takes a game concept and engine choice, then runs scaffold, design, audio, deploy,…

game-creator10d367

@playableintelligenceInstall Agent

Automates game deployment to here.now (default), GitHub Pages, Vercel, or itch.io with pre-deploy verification and post-deploy…

game-creator10d367

@playableintelligenceInstall Agent

Runs browser test suites (node --test with Chrome over the DevTools protocol) for browser games, diagnoses failures, fixes game…

game-creator10d367

@playableintelligenceInstall Agent

Design, redesign, analyze or review an architecture using separation-of-concerns skill

claude-skillz7mo364

@ntcodingInstall Agent

Semantic code review using project-specific rules

claude-skillz7mo364

@ntcodingInstall Agent

Detect missing project context and opportunities to build new skills

claude-skillz7mo364

@ntcodingInstall Agent

You are an expert coding engineer working with the user. You produce high quality code and artifacts on behalf of the user. You…

crew445mo360

@getcrew44Install Agent

You are an expert designer working with the user as a manager.

crew445mo360

@getcrew44Install Agent

You are the Partner: the lead of the crew.

crew445mo360

@getcrew44Install Agent

Configure Claude Code statusLine.command for the xurl status line plugin.

xurl7mo359

@xuanwoInstall Agent

Adversarial reader of a nav-deep-research draft. Finds ignored counter-evidence, unsupported claims, verbatim quotes from…

navigator5d356

@alekspetrovInstall Agent

Fetches one disjoint batch of URLs into a nav-deep-research run as fenced source notes. Spawned in parallel waves by the…

navigator5d356

@alekspetrovInstall Agent

Applies critic findings to a nav-deep-research draft as surgical Edit hunks and records a patch log. Tool-locked so it cannot…

navigator5d356

@alekspetrovInstall Agent

Honey hive subagent. Makes a small, surgical code change (≤2 files) under the Honey Lever-1 ladder — minimum code that needs to…

honey4w356

@green-ptInstall Agent

Honey hive subagent. Reviews a diff or file set for correctness bugs, over-engineering, and over-verbosity, then returns the…

honey4w356

@green-ptInstall Agent

Honey hive subagent. Read-only code locator — finds where symbols, callers, configs, or patterns live across the repo and returns…

honey4w356

@green-ptInstall Agent

An expert at creating and refining automated tests using TestDriver.ai

testdriverai7w356

@testdriveraiInstall Agent

Adversarial reader of a nav-deep-research draft. Finds ignored counter-evidence, unsupported claims, verbatim quotes from…

navigator3w355

@qf-studioInstall Agent

Fetches one disjoint batch of URLs into a nav-deep-research run as fenced source notes. Spawned in parallel waves by the…

navigator3w355

@qf-studioInstall Agent

Applies critic findings to a nav-deep-research draft as surgical Edit hunks and records a patch log. Tool-locked so it cannot…

navigator3w355

@qf-studioInstall Agent

Use this agent to run a comprehensive WCAG AA accessibility audit on a design. Trigger when reviewing designs for accessibility,…

naksha4w354

@adityaraj0421Install Agent

Use this agent to run a structured 3-pass UX critique — heuristics, accessibility, and content quality. Trigger when the user…

naksha4w354

@adityaraj0421Install Agent

Use this agent to perform an automated UX heuristic review of Figma screens. Trigger when the user wants feedback on their…

naksha4w354

@adityaraj0421Install Agent

Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and…

claude-night-market1d350

@atholaInstall Agent

Architecture review for system design, ADR compliance, and coupling analysis. Use for major refactors.

claude-night-market1d350

@atholaInstall Agent

Review code changes using blast radius analysis from the code knowledge graph. Reads high-risk affected files and provides…

claude-night-market1d350

@atholaInstall Agent

You are an adversarial security analyst. Your default posture is that all code is insecure, full of PII leaks, and an easy attack…

han2d350

@testdoubleInstall Agent

You are an adversarial validator. Your default posture is pessimistic — assume everything you are given is wrong until proven…

han2d350

@testdoubleInstall Agent

You are a behavioral analyst. Your job is to examine how a specified focus area behaves at runtime — how data flows, how errors…

han2d350

@testdoubleInstall Agent

Review code for quality, patterns, and best practices. Use proactively after code changes.

ai-agent-camp5w349

@minicooheiInstall Agent

Explore and map codebase structure, architecture, and dependencies. Use when navigating unfamiliar code.

ai-agent-camp5w349

@minicooheiInstall Agent

Handle Slack and email communications. Draft replies, extract tasks, manage correspondence.

ai-agent-camp5w349

@minicooheiInstall Agent

System design and implementation planning

the-claude-protocol9mo348

@avivk5498Install Agent

Adversarial code review - verify demos work, then spec compliance, then code quality

the-claude-protocol9mo348

@avivk5498Install Agent

Bug investigation and root cause analysis

the-claude-protocol9mo348

@avivk5498Install Agent

Judge whether a DOX AGENTS.md row is still accurate after its source file changed. Reads the real git diff since the row was last…

pi-agent-dashboard2d348

@blackbelttechnologyInstall Agent

doubt-driven-review fresh-context adversarial reviewer (read-only). Task text = adversarial prompt + ARTIFACT + CONTRACT. No…

pi-agent-dashboard2d348

@blackbelttechnologyInstall Agent

reverse-spec-for-rebuild auditor subagent (hallucination safety net, read-only). Task text = filled prompts/auditor-rebuild.md.

pi-agent-dashboard2d348

@blackbelttechnologyInstall Agent

Архитектор-планировщик. Используй для проектирования новых фич, оценки вариантов реализации и планов крупных изменений ДО…

claude-code-pro-course6w348

@justxorInstall Agent

Senior-ревьюер кода. Используй ПРОАКТИВНО сразу после написания или изменения значимого объёма кода, а также перед созданием PR.

claude-code-pro-course6w348

@justxorInstall Agent

Специалист по отладке ошибок, падающих тестов и неожиданного поведения. Используй при любой ошибке или стектрейсе.

claude-code-pro-course6w348

@justxorInstall Agent