The best Claude Code agents :)

Orchestrates CLAUDE.md updates for changed files

auto-memory7mo159

@severity1Install Agent

代码审查与缺陷验证代理。用于对新编写或修改的代码进行质量审查、发现潜在 bug、验证逻辑正确性。仅在显式调用时运行，不做主动触发。

velocitai6w158

@danielsuo117Install Agent

Tests web applications end-to-end using Glance browser MCP. Navigates pages, fills forms, clicks buttons, takes screenshots, runs…

glance7mo158

@debugbaseInstall Agent

Fast agent specialized for exploring Outline knowledge bases. Use this when you need to search for documents by keywords, browse…

mcp-outline2w158

@vortiagoInstall Agent

Reviews code for bugs, security, performance, and spec compliance. Run in fresh context without implementation bias.

bulletproof7mo155

@artemiimillierInstall Agent

Conducts deep behavioral interviews to understand a person's work patterns, communication style, decision-making, and expertise.…

human-compiler9mo155

@gerstepInstall Agent

Independent architecture reviewer with no authorship attachment. Verifies a written architecture artifact (ADR, architecture doc,…

claude-toolbox1d155

@serpro69Install Agent

Independent code reviewer with no authorship attachment. Reviews git diffs for SOLID violations, security risks, code quality…

claude-toolbox1d155

@serpro69Install Agent

Independent design document reviewer with no authorship attachment. Evaluates design and implementation docs for completeness,…

claude-toolbox1d155

@serpro69Install Agent

Cross-artifact consistency checker for NL programming artifacts. Checks reference integrity, detects orphans, finds behavioral…

nlpm4d155

@xiaolaiInstall Agent

Discover and classify all NL programming artifacts in a repository — the current directory or a given project path — with…

nlpm4d155

@xiaolaiInstall Agent

Scores NL programming artifacts on a 100-point scale using deterministic penalties. Use this agent when scoring plugin artifacts,…

nlpm4d155

@xiaolaiInstall Agent

Read-only checkpoint reviewer. Surfaces drift between the codebase and accepted ADRs in .codearbiter/decisions/. Informational —…

codearbitertoday153

@arbiterforgeInstall Agent

Reviews authentication, cryptography, key handling, and secrets against {{PROJECT_DIR}}/.codearbiter/security-controls.md. Hard…

codearbitertoday153

@arbiterforgeInstall Agent

INTERNAL independent reviewer for structured-artifact spec and quality review on Claude Code. Launched only through an armed…

codearbitertoday153

@arbiterforgeInstall Agent

mbbb Baker Agent — professional pastry recipe library lookup and Baker's Percentage calculator. Use when the user asks about a…

mbbb-baker-agent5mo153

@chefkannofriend-sourceInstall Agent

**⚠️ DEVELOPER REFERENCE ONLY** — This file documents the raw GraphQL API schema for development and maintenance purposes (adding…

unraid1d153

@dinglebear-aiInstall Agent

**⚠️ DEVELOPER REFERENCE ONLY** — This file documents raw GraphQL endpoints for development purposes. For MCP tool usage, use…

unraid1d153

@dinglebear-aiInstall Agent

**⚠️ DEVELOPER REFERENCE ONLY** — Full GraphQL SDL from live API introspection. Use this to verify field names and types when…

unraid1d153

@dinglebear-aiInstall Agent

AGGRESSIVE hybrid agent that delegates code generation and modification directly to Gemini and GPT for rapid development and…

gemini-gpt-hybrid3mo153

@oesollInstall Agent

Intelligent hybrid agent that uses Gemini and GPT for analysis and problem identification, then returns insights to Claude for…

gemini-gpt-hybrid3mo153

@oesollInstall Agent

Read-only analysis subagent dispatched explicitly by paad's multi-agent skills — not for general-purpose analysis; performs one…

paad5d152

@ovidInstall Agent

You are an analytics lead responsible for measuring campaign performance, analyzing data, and reporting on ROI and optimization…

forge4mo151

@jdforsytheInstall Agent

You are a campaign strategist responsible for defining campaign strategy, target audience, channel mix, and success metrics…

forge4mo151

@jdforsytheInstall Agent

You are a compliance analyst responsible for evaluating organizational compliance against security frameworks and regulatory…

forge4mo151

@jdforsytheInstall Agent

Use this agent when writing new Python files, editing existing Python files, or reviewing recently written code to ensure full…

codedna3w151

@larens94Install Agent

CodeDNA compliance reviewer. Invoke when a file is written or edited without a CodeDNA annotation, or when the user asks to…

codedna3w151

@larens94Install Agent

Codex transport wrapper for fable-foreman (v0.3). Runs the skill's fixed-argv launcher (scripts/codex-dispatch.sh) exactly once…

fable-foreman3w151

@olsenbrandsInstall Agent

Grok transport wrapper for fable-foreman. Runs the skill's fixed-argv launcher (scripts/grok-dispatch.sh) exactly once and relays…

fable-foreman3w151

@olsenbrandsInstall Agent

FAST reconnaissance agent for fable-foreman. Read-only codebase scanning, location of relevant files and symbols, extraction of…

fable-foreman3w151

@olsenbrandsInstall Agent

API endpoint testing. Discovery, validation, auth flows, error handling.

claude-code-agents4mo150

@undeadlistInstall Agent

Supervisor agent. Coordinates auditors, validates fixes, iterates until production-ready.

claude-code-agents4mo150

@undeadlistInstall Agent

Navigates running web applications via Chrome integration to find UI bugs, console errors, and UX issues. Uses /chrome tools to…

claude-code-agents4mo150

@undeadlistInstall Agent

<!-- GENERATED from docs/api/app.md by scripts/build-agent-skill.mjs. Do not edit. -->

crossbind3d149

@crossbindInstall Agent

<!-- GENERATED from docs/api/build-state.md by scripts/build-agent-skill.mjs. Do not edit. -->

crossbind3d149

@crossbindInstall Agent

<!-- GENERATED from docs/playbooks/integration/cloudflare-worker.md by scripts/build-agent-skill.mjs. Do not edit. -->

crossbind3d149

@crossbindInstall Agent

Routes investment research, prediction market, filings, earnings, quote, and analyst-estimate requests to the best Octagon skill…

octagon-market-intelligence1d149

@octagonaiInstall Agent

Review Odoo code for correctness, security, performance, and version-specific standards (Odoo 16, 17, 18, or 19). Use when…

agent-skills3w149

@unclecatvnInstall Agent

Trace Odoo code execution flow from entry point to end. Use proactively when planning tasks, reviewing code, or understanding how…

agent-skills3w149

@unclecatvnInstall Agent

Use after planner and ui-agent have produced their briefs. Writes the actual application code, follows TDD (test-first). Handles…

claude-agents-skills6mo148

@selmakcbyInstall Agent

Use PROACTIVELY when the user asks to implement a new feature, refactor code, or make architectural changes. Creates step-by-step…

claude-agents-skills6mo148

@selmakcbyInstall Agent

Use PROACTIVELY immediately after builder produces code. Double-role agent that checks BOTH code quality AND security before…

claude-agents-skills6mo148

@selmakcbyInstall Agent

Discovers strategic context from codebase - features, tech stack, integrations, scale. Presents findings to user, validates, and…

agents7mo147

@slgoodrichInstall Agent

PRD reviewer specializing in technical feasibility and requirements clarity. Evaluates whether requirements are buildable,…

agents7mo147

@slgoodrichInstall Agent

Feature prioritization using RICE, ICE, and Value vs Effort frameworks. Helps scope MVP and avoid scope creep. Use when deciding…

agents7mo147

@slgoodrichInstall Agent

Use this agent to review completed implementation work against requirements, correctness, and production readiness.

superpowers-optimized5w146

@repozyInstall Agent

Use this agent to adversarially attack completed implementation work — find concrete ways to break the code through specific…

superpowers-optimized5w146

@repozyInstall Agent

Generates concise documentation for skills, focusing on usage examples and trigger phrases

skills3d145

@luongnv89Install Agent

Validates and packages skills into distributable .skill files

skills3d145

@luongnv89Install Agent

Reviews skill files for quality, best practices, and adherence to skill creation guidelines

skills3d145

@luongnv89Install Agent

Read and summarize academic papers for research gap analysis. Called by gap-analysis skill to process papers in parallel. Launch…

research-app-toolkit4w144

@xujingchen1996Install Agent

Design reliable backend systems with focus on data integrity, security, and fault tolerance

claude-code-rules13d142

@nikiforovallInstall Agent

Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR…

claude-code-rules13d142

@nikiforovallInstall Agent

Use this agent when you need to understand HOW existing code works, trace implementation details, or document technical…

claude-code-rules13d142

@nikiforovallInstall Agent

아이디어의 실현 가능성, 경쟁사, 필요 API를 조사하는 리서치 에이전트

fireauto7mo139

@imgompandaInstall Agent

레딧 데이터를 분석하고 리드를 스코어링하는 분석 에이전트

fireauto7mo139

@imgompandaInstall Agent

코드베이스를 분석하여 보안 취약점을 발견하는 감사 에이전트

fireauto7mo139

@imgompandaInstall Agent

Email compliance checking agent. Scans email content and sending configuration for CAN-SPAM, GDPR, and CCPA compliance. Checks…

email5mo138

@agricidanielInstall Agent

Email copy quality scoring agent. Analyzes email content for framework adherence (PAS, AIDA, BAB, FAB, 4Ps), subject line…

email5mo138

@agricidanielInstall Agent

Email deliverability analysis agent. Checks SPF, DKIM, DMARC, MX records, reverse DNS, TLS support, and blacklist status for a…

email5mo138

@agricidanielInstall Agent

Reads the Clodex plugin contract and returns the exact rules and signatures for the surfaces a plugin needs. Spawned by the…

clodextoday137

@avirtualInstall Agent

Finds where a symbol or behaviour is decided; returns file:line pointers with at most twenty lines of context per hit and nothing…

clodextoday137

@avirtualInstall Agent

Runs one red-proof: a named test file green, a given revert applied, red, restored, tree clean. Reports per test name in under…

clodextoday137

@avirtualInstall Agent

Inspects Content Security Policy headers for policy weaknesses and tests bypass vectors including unsafe-inline, unsafe-eval,…

claude-pentest5mo137

@stickman230Install Agent

Tests for CSRF vulnerabilities including missing tokens, weak validation, SameSite bypass, token reuse, and method override.…

claude-pentest5mo137

@stickman230Install Agent

Identifies technology stacks, researches known CVEs in NVD/Exploit-DB/GitHub, adapts public PoC exploits, and validates…

claude-pentest5mo137

@stickman230Install Agent

Webflow agent with MCP server integration, skill orchestration for CMS management, site audits, safe publishing, link checking,…

webflow-skills2w136

@webflowInstall Agent

Web of Science 研究助手。协调搜索、详情提取、翻页、下载和导出。

wos-skills8mo135

@cookjohnInstall Agent

Runs paid campaigns to a target cost per acquisition — audience, bid, budget, and the daily call on what to scale or cut.

one2w134

@one-ieInstall Agent

Sales or service consultation booked via ONE — host + guest join links generated, call recorded, transcript summarised, contact…

one2w134

@one-ieInstall Agent

Sets direction, approves budgets, hires directors, and routes work to them. Does not do the work — one decision per reply, always…

one2w134

@one-ieInstall Agent

Agent 办事前先读此文件。探测到新能力或缺失项后，**经用户确认**再更新本节。

xrk-agt5w134

@xrkseekInstall Agent

心跳触发时快速过一遍；**全部正常**则只回复 `HEARTBEAT_OK`。

xrk-agt5w134

@xrkseekInstall Agent

- **名称**：小 R（XRK 工作区助手） - **角色**：办公协作 — 文档、邮件、纪要、调研摘要、任务拆解 - **语气**：清晰、礼貌、偏商务但不死板 - **签名**：回复末尾可不落款；用户要求时再署「小 R」

xrk-agt5w134

@xrkseekInstall Agent

Review Go backend code for convention violations. Use after modifying files under components/backend/. Checks for panic usage,…

platform7d133

@ambient-codeInstall Agent

Runs all convention checks across the full codebase and produces a scored alignment report. Dispatched by the /align skill.

platform7d133

@ambient-codeInstall Agent

Review frontend TypeScript/React code for convention violations. Use after modifying files under components/frontend/src/. Checks…

platform7d133

@ambient-codeInstall Agent

This project splits its code into modules with Gacela. Follow these rules when you add or change code. The full docs for the…

gacela13d133

@gacela-projectInstall Agent

Use this agent when you need to improve clarity, cut unnecessary words, remove jargon, or eliminate passive voice in written…

claude-code-toolkit8w133

@robertgussInstall Agent

Use this agent when you need to review and edit text content to conform to Every's specific style guide. This includes reviewing…

claude-code-toolkit8w133

@robertgussInstall Agent

Use this agent when you need to verify claims, check statistics, and ensure factual accuracy in written content. This agent…

claude-code-toolkit8w133

@robertgussInstall Agent

Review content for voice, guardrails, anti-AI patterns, and actionability.

kipi-system3d132

@assafkipInstall Agent

Pull calendar, email, Notion data. Structured extraction only, no analysis.

kipi-system3d132

@assafkipInstall Agent

Generate ranked, copy-paste-ready engagement actions from pipeline data.

kipi-system3d132

@assafkipInstall Agent

Use this agent to drive a system-design problem end to end — from a vague prompt to a justified, stress-tested architecture —…

system-design-skills2w132

@proyecto26Install Agent

Reviews a branch's full diff against its base from correctness, security, product/UX, and developer-experience angles, and…

claude-essentials13d131

@rileyhilliardInstall Agent

Writes articles, essays, and long-form content using professional journalistic frameworks. Takes a brief or topic, recommends the…

claude-essentials13d131

@rileyhilliardInstall Agent

Pokes holes in a plan, RFC, spec, design, or decision before it is committed to, checking its claims against the real code and…

claude-essentials13d131

@rileyhilliardInstall Agent

Use when developing anti-vibe-writing, a writing skill for AI agents that rewrites generated drafts into a more classic,…

anti-vibe-writing3mo131

@weijt606Install Agent

Plan a safe database schema change — forward + rollback migration with deploy-order checklist.

azmx4mo130

@azmxaiInstall Agent

Read a function and propose tests covering the happy path plus three meaningful edge cases.

azmx4mo130

@azmxaiInstall Agent

Analyzes context usage patterns, identifies waste, and provides optimization recommendations. Use when the user asks about token…

context-optimizer5d130

@egorfedorovInstall Agent

Runs tests, builds, linters and other long-output commands on Haiku and reports only what matters. Use proactively when a…

context-optimizer5d130

@egorfedorovInstall Agent

Cheap read-only explorer on Haiku. Use proactively when a question needs several files read or a wide code search — anything that…

context-optimizer5d130

@egorfedorovInstall Agent

After the London hackathon, Juan and I decided how atext moves forward as the showcase of agent-first BYOT. Recorded so the team…

aweb1d129

@awebaiInstall Agent

Everything here is durable; nothing depends on tmux or model context.

aweb1d129

@awebaiInstall Agent

One fact per file, indexed here. See the `self-maintenance` skill.

aweb1d129

@awebaiInstall Agent

Remove AI-generated clutter from a diff when its style does not match the surrounding code.

my-ai-toolstoday129

@jellydnInstall Agent

Remove AI-generated code patterns that don't match codebase style

my-ai-toolstoday129

@jellydnInstall Agent

Audit a supplied diff for structural maintainability and unnecessary complexity.

my-ai-toolstoday129

@jellydnInstall Agent

Submit case feedback to report issues or suggestions. Triggered by the /glm-plan-bug:case-feedback command.

zai-coding-plugins8mo129

@zai-orgInstall Agent

Query GLM Coding Plan usage statistics for the current account. Triggered by the /glm-plan-usage:usage-query command.

zai-coding-plugins8mo129

@zai-orgInstall Agent

[motiscope](https://github.com/KumarSashank/motiscope) turns a screen recording of an animation into working web-animation code.…

motiscope3mo128

@kumarsashankInstall Agent

Reads a motiscope analysis (report + curated frames) and returns a compact, target-agnostic animation spec. Use to characterize…

motiscope3mo128

@kumarsashankInstall Agent

Expert YouTube Thumbnail Reviewer. Reviews and critiques thumbnail concepts based on proven design requirements.

ai-launchpad-marketplace2w127

@kenneth-liaoInstall Agent

Expert YouTube Researcher. Uses the YouTube Data API to search and analyze YouTube channels, videos, comments, transcripts, and…

ai-launchpad-marketplace2w127

@kenneth-liaoInstall Agent

--- name: babyclaude description: | Task implementer for /claudikins-kernel:execute command. Implements a single task from a…

claudikins-kernel6mo127

@povvoInstall Agent

Output verification agent for /claudikins-kernel:verify command. SEES code working by running apps, curling endpoints, capturing…

claudikins-kernel6mo127

@povvoInstall Agent

Code quality reviewer for /claudikins-kernel:execute command. Reviews code quality, patterns, and maintainability. This is stage…

claudikins-kernel6mo127

@povvoInstall Agent

코드 변경에 맞춰 docs/의 코드 레벨 문서(컴포넌트·훅·유틸·모델·서비스·설정·CHANGELOG)를 만들거나 고칠 때 사용. /docs 명령이나 구현과 병렬 background로 부른다. 아키텍처·API 명세·매뉴얼은…

adlc-harness2w125

@jh941213Install Agent

구현과 분리된 새 컨텍스트에서 브랜치 결과를 spec·plan 기준으로 검증·채점하는 평가자(PASS/CONDITIONAL/FAIL). 큰 작업 구현을 마친 뒤, writing-plans의 마지막 검토, /eval에서 쓴다.

adlc-harness2w125

@jh941213Install Agent

인증·권한·입력 처리·비밀 값·의존성을 건드린 변경을 병합 전에 보안 리뷰할 때, 또는 보안 이슈를 발견했을 때 사용. Claude Code에서는 내장 /security-review를 먼저 쓰고, 다른 호스트나 SAST 후보 추출이…

adlc-harness2w125

@jh941213Install Agent

One advisor per gray area of a discussion: researches the options of that one area and recommends with sources. Use when: разбери…

claude-lane-stack1d125

@vkirillInstall Agent

Implements one validated Claude Lane Stack task without delegation.

claude-lane-stack1d125

@vkirillInstall Agent

Reads the current docs, limits and prices of a chosen AI framework and model, with links. Use when: документация модели, лимиты…

claude-lane-stack1d125

@vkirillInstall Agent