The best Claude Code agents :)

Read-only local and web exploration on its configured economical model.

gentle-shell3d2.3k

@gentleman-programmingInstall Agent

Read-only technical verification for generic ODD work.

gentle-shell3d2.3k

@gentleman-programmingInstall Agent

Scoped package-owned implementation writer for bounded ODD work. Edits code, runs focused tests, and returns review-ready…

gentle-shell3d2.3k

@gentleman-programmingInstall Agent

Single source of truth for the shape of every agent in this pack. One schema, one pool — `agents/index.json` is generated from…

harmonist5mo2.2k

@gammalabtechnologiesInstall Agent

How to write an agent body that is useful, compact, and consistent with the rest of the pack. Follow this when adding a new agent…

harmonist5mo2.2k

@gammalabtechnologiesInstall Agent

Curated list of every tag an agent is allowed to declare. Source of truth: [`tags.json`](tags.json). Linter rejects any tag not…

harmonist5mo2.2k

@gammalabtechnologiesInstall Agent

Deprecated placeholder. Do not use; follow root AGENTS.md and package instructions instead.

happier6d2.2k

@happier-devInstall Agent

Deprecated placeholder. Do not use; follow root AGENTS.md and package instructions instead.

happier6d2.2k

@happier-devInstall Agent

Deprecated placeholder. Do not use; follow root AGENTS.md and package instructions instead.

happier6d2.2k

@happier-devInstall Agent

This document is a reference for implementing a new **agent provider** in Nimbalyst. It is the architectural counterpart to…

nimbalyst1d2.1k

@nimbalystInstall Agent

Status: **STUCK**. Three approaches tried, none reliably solves the pre-edit race for `update`-kind file_change items. This doc…

nimbalyst1d2.1k

@nimbalystInstall Agent

Run E2E tests in a dev container for isolated, reproducible test execution. Use proactively when asked to run Playwright tests,…

nimbalyst1d2.1k

@nimbalystInstall Agent

Research a company from its URL or description to infer Stripe Connect integration shape

aitoday2.1k

@stripeInstall Agent

Search and find previous code agent sessions (Claude-Code or Codex-CLI) for specific work, decisions, or code patterns. Use when…

claude-code-tools9d2k

@pchalasaniInstall Agent

Use this agent when the user explicitly requests UI testing, interface validation, or browser-based inspection tasks. This agent…

claude-code-tools9d2k

@pchalasaniInstall Agent

用于系统设计、可扩展性及技术决策的软件架构专家。在规划新功能、重构大型系统或做出架构决策时请主动（PROACTIVELY）使用。

everything-claude-code8mo2k

@xu-xiangInstall Agent

构建与 TypeScript 错误修复专家。当构建失败或出现类型错误时，请主动（PROACTIVELY）使用。仅修复构建/类型错误，保持最小差异（diff），不进行架构性修改。重点是快速使构建通过（get the build green）。

everything-claude-code8mo2k

@xu-xiangInstall Agent

个人通讯幕僚 (Chief of Staff)，负责分拣电子邮件、Slack、LINE 和 Messenger。将消息分类为 4 个级别 (skip/info_only/meeting_info/action_required)，生成草稿回复，并通过钩子…

everything-claude-code8mo2k

@xu-xiangInstall Agent

Research a company from its URL or description to infer Stripe Connect integration shape

agent-toolkit2w2k

@stripeInstall Agent

Use this agent to verify that a Python Agent SDK application is properly configured, follows SDK best practices and documentation…

awesome-claude-plugins10d2k

@composio-communityInstall Agent

Use this agent to verify that a TypeScript Agent SDK application is properly configured, follows SDK best practices and…

awesome-claude-plugins10d2k

@composio-communityInstall Agent

Use this agent when designing APIs, building server-side logic, implementing databases, or architecting scalable backend systems.…

awesome-claude-plugins10d2k

@composio-communityInstall Agent

Expert skill auditor for Claude Code Skills. Use when auditing, reviewing, or evaluating SKILL.md files for best practices…

taches-cc-resources7mo2k

@glittercowboyInstall Agent

Expert slash command auditor for Claude Code slash commands. Use when auditing, reviewing, or evaluating slash command .md files…

taches-cc-resources7mo2k

@glittercowboyInstall Agent

Expert subagent auditor for Claude Code subagents. Use when auditing, reviewing, or evaluating subagent configuration files for…

taches-cc-resources7mo2k

@glittercowboyInstall Agent

Deep codebase exploration using grepai semantic search and call graph tracing. Use this agent for understanding code…

grepai13d1.9k

@yoanbernabeuInstall Agent

**Role:** Implementation & Fixes **ID:** `automaker-code-generator` **Source:**…

babysitter13d1.9k

@a5c-aiInstall Agent

Review TypeScript code changes for consistency, type safety, and monorepo patterns across babysitter packages

babysitter13d1.9k

@a5c-aiInstall Agent

Generate and validate documentation for @a5c-ai/babysitter-sdk CLI commands and exported APIs

babysitter13d1.9k

@a5c-aiInstall Agent

Analyze alignment between daily activities and long-term goals. Identify gaps, over/under-investment, and suggest rebalancing.…

obsidian-claude-pkm9mo1.9k

@ballredInstall Agent

Process inbox items using GTD principles. Categorize, clarify, and organize captured notes into actionable items. Use for inbox…

obsidian-claude-pkm9mo1.9k

@ballredInstall Agent

Organize and restructure vault notes. Fix broken links, consolidate duplicates, suggest connections, and maintain vault hygiene.…

obsidian-claude-pkm9mo1.9k

@ballredInstall Agent

Überwacht den virtuellen Datenraum (VDR) auf neue Dokument-Uploads und meldet den Status der Closing-Checkliste nach Zeitplan.…

claude-fuer-deutsches-rechttoday1.8k

@klotzketteInstall Agent

Wöchentlicher Agent, der offene Abwesenheiten mit gesetzlichen Fristen überwacht — Mutterschutzgesetz (MuSchG), BEEG…

claude-fuer-deutsches-rechttoday1.8k

@klotzketteInstall Agent

Überwacht den Launch-Tracker (Jira/Linear) auf bevorstehende Markteinführungen, die voraussichtlich rechtliche Prüfung erfordern,…

claude-fuer-deutsches-rechttoday1.8k

@klotzketteInstall Agent

Use this agent when reviewing local code changes or in the pull request to identify bugs and critical issues through systematic…

context-engineering-kit2mo1.8k

@neolabhqInstall Agent

Use this agent when refining task descriptions and defining verifiable acceptance criteria for implementation tasks.

context-engineering-kit2mo1.8k

@neolabhqInstall Agent

Use this agent to rate each changed file based on 2 criteria and output final list of files that require most attention.

context-engineering-kit2mo1.8k

@neolabhqInstall Agent

You are the **Clause Analysis Subagent**, one of 5 parallel subagents launched during `/legal review`. Your specific…

ai-legal-claude7mo1.8k

@zubair-trabzadaInstall Agent

You are the **Compliance Check Subagent**, one of 5 parallel subagents launched during `/legal review`. Your specific…

ai-legal-claude7mo1.8k

@zubair-trabzadaInstall Agent

You are the **Recommendations Subagent**, one of 5 parallel subagents launched during `/legal review`. Your specific…

ai-legal-claude7mo1.8k

@zubair-trabzadaInstall Agent

Optional gallery research helper. Use when a caller wants to find references, explore styles, build a mood board, or needs…

meigen-ai-design-mcp9d1.8k

@jau123Install Agent

Optional image execution helper for callers that choose to delegate. Accepts a complete generation request and returns its result…

meigen-ai-design-mcp9d1.8k

@jau123Install Agent

Optional prompt writing helper. Use only when the caller requests multiple distinct prompts at once — for parallel image…

meigen-ai-design-mcp9d1.8k

@jau123Install Agent

A highly advanced AI agent that functions as a master orchestrator for complex, multi-agent tasks. It analyzes project…

claude-code-sub-agents1y1.7k

@lst97Install Agent

A highly specialized AI agent for designing, building, and optimizing LLM-powered applications, RAG systems, and complex prompt…

claude-code-sub-agents1y1.7k

@lst97Install Agent

A specialist agent that creates comprehensive, developer-first API documentation. It generates OpenAPI 3.0 specs, code examples,…

claude-code-sub-agents1y1.7k

@lst97Install Agent

Comprehensive session analysis and learning capture specialist. Analyzes development sessions to extract patterns, preferences,…

claude-code-settings10d1.7k

@feiskyerInstall Agent

GitHub issue resolution specialist. Analyzes, plans, and implements fixes for GitHub issues with proper testing and PR creation.…

claude-code-settings10d1.7k

@feiskyerInstall Agent

Technical breakthrough documentation specialist. Captures and transforms significant technical insights into actionable, reusable…

claude-code-settings10d1.7k

@feiskyerInstall Agent

Deep-dive a Windows crash dump and return a written verdict. Use when a dump needs more than a first look - several hypotheses to…

mcp-windbg2w1.7k

@svnschaInstall Agent

Research notes on Sourcegraph Amp's configuration, credential discovery, and runtime behavior.

agentstoday1.6k

@rivet-devInstall Agent

Research notes on OpenAI Codex's configuration, credential discovery, and runtime behavior based on agent-jj implementation.

agentstoday1.6k

@rivet-devInstall Agent

Research notes on OpenClaw's architecture, API, and automation patterns for integration with sandbox-agent.

agentstoday1.6k

@rivet-devInstall Agent

Read-only web and registry lookup. Use for Agent Skill / MCP discovery (npx skills find, MCP search), current-usage doc-checks,…

skills3mo1.6k

@javascript-mastery-proInstall Agent

Read-only code exploration and repo scanning. Use for the develop exploration step, the scope brownfield code scan, or any task…

skills3mo1.6k

@javascript-mastery-proInstall Agent

Background agent for fetching arxiv.org web content using **agent-browser CLI**.

actionbook3w1.6k

@actionbookInstall Agent

Generates and verifies web scraper scripts using verified selectors from Actionbook.

actionbook3w1.6k

@actionbookInstall Agent

Background agent for fetching Rust crate information using **agent-browser CLI**.

actionbook3w1.6k

@actionbookInstall Agent

Selects required BitLesson entries for a specific sub-task. Use before execution for every task or sub-task.

humanize2mo1.6k

@polyarchInstall Agent

Checks if a draft document is relevant to the current repository. Use when validating draft content for gen-plan command.

humanize2mo1.6k

@polyarchInstall Agent

Checks plan relevance and compliance before RLCR loop. Use when validating plan files for start-rlcr-loop command.

humanize2mo1.6k

@polyarchInstall Agent

Generic web content fetcher.

rust-skills2mo1.6k

@zhanghandongInstall Agent

Fetch Clippy lint information.

rust-skills2mo1.6k

@zhanghandongInstall Agent

Fetch crate metadata from lib.rs / crates.io.

rust-skills2mo1.6k

@zhanghandongInstall Agent

The brooks-lint verification gate. Runs `npm run validate`, `npm test`, and `npm run evals`, then cross-checks the documents the…

brooks-linttoday1.6k

@hyhmrrightInstall Agent

Authors and maintains the brooks-lint eval suite in evals/evals.json — the benchmark scenarios covering R1–R6 (code decay) and…

brooks-linttoday1.6k

@hyhmrrightInstall Agent

Cuts a brooks-lint release: sets the version in package.json, propagates it across the four plugin manifests and every…

brooks-linttoday1.6k

@hyhmrrightInstall Agent

Software architecture specialist for system design, scalability, and technical decision-making

skillkit5mo1.6k

@rohitg00Install Agent

Build and TypeScript error resolution specialist. Fixes build/type errors with minimal diffs

skillkit5mo1.6k

@rohitg00Install Agent

Expert code review specialist. Reviews code for quality, security, and maintainability

skillkit5mo1.6k

@rohitg00Install Agent

Generic web content fetcher.

rust-skills2mo1.6k

@actionbookInstall Agent

Fetch Clippy lint information.

rust-skills2mo1.6k

@actionbookInstall Agent

Fetch crate metadata from lib.rs / crates.io.

rust-skills2mo1.6k

@actionbookInstall Agent

You are the **Company Research Subagent**, one of 5 parallel subagents launched during `/sales prospect <url>`. Your specific…

ai-sales-team-claude7mo1.5k

@zubair-trabzadaInstall Agent

You are the **Competitive Positioning Subagent**, one of 5 parallel subagents launched during `/sales prospect <url>`. Your…

ai-sales-team-claude7mo1.5k

@zubair-trabzadaInstall Agent

You are the **Contact Intelligence Subagent**, one of 5 parallel subagents launched during `/sales prospect <url>`. Your specific…

ai-sales-team-claude7mo1.5k

@zubair-trabzadaInstall Agent

Weekly movement briefing on the AI agent harness space — what climbed, what entered the radar, what died — from the…

best-of-agent-harnesses6d1.5k

@ryanalbertsInstall Agent

Picks the right AI agent harness for a described task or project. Use when the user asks "what harness/framework/agent tool…

best-of-agent-harnesses6d1.5k

@ryanalbertsInstall Agent

Audits a codebase's AI agent stack against the live best-of-Agent-Harnesses dataset — finds which harnesses the repo uses, flags…

best-of-agent-harnesses6d1.5k

@ryanalbertsInstall Agent

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

claude-code-skills2w1.5k

@daymadeInstall Agent

Compare two outputs WITHOUT knowing which skill produced them.

claude-code-skills2w1.5k

@daymadeInstall Agent

Evaluate expectations against an execution transcript and outputs.

claude-code-skills2w1.5k

@daymadeInstall Agent

Describes video frames as detailed text. Used when frame_mode is "descriptions" to convert visual frames into text, saving tokens…

claude-video-vision4w1.5k

@jordanrendricInstall Agent

Reviews an evo benchmark in two modes. mode=audit -- pre-flight harness audit before the first run (per-task instrumentation,…

evo5w1.5k

@evo-hqInstall Agent

Generates ranked experiment proposals for the evo orchestrator. Runs ONE brief per invocation (`failure_analysis`, `literature`,…

evo5w1.5k

@evo-hqInstall Agent

Read-only audit of one evo experiment for design-time cheating (pre-phase) or result-time validity (post-phase). Catches test-set…

evo5w1.5k

@evo-hqInstall Agent

Builds interactive HTML explorables for Engram threshold concepts under the binding Explorable Contract. Use after encoding a…

engram2mo1.5k

@nagisanzeninInstall Agent

Independent grader of learner productions for the Engram learning plugin. MUST BE USED for /learn verification and /review…

engram2mo1.5k

@nagisanzeninInstall Agent

Decomposes any topic into a first-principles concept DAG for the Engram learning plugin. Use when starting a new learning topic…

engram2mo1.5k

@nagisanzeninInstall Agent

Architecture review and recommendation. Use for system design, module boundaries, ADRs, and tradeoff analysis.

oma1d1.5k

@first-flukeInstall Agent

Architecture review and recommendation. Use for system design,

oma1d1.5k

@first-flukeInstall Agent

Backend implementation. Use for API, authentication, DB migration work.

oma1d1.5k

@first-flukeInstall Agent

Create one installable Agentlas worker package with memory, runtime adapters, and proposal-first self-evolution when useful.

agentlas-os5d1.5k

@agentlas-aiInstall Agent

Use this agent when the user asks for /meta-agent, a single agent builder, multi-agent team builder, or packaging existing agents…

agentlas-os5d1.5k

@agentlas-aiInstall Agent

Convert or repair an existing local/external agent or team into Agentlas architecture and prepare local install, Claude adapter,…

agentlas-os5d1.5k

@agentlas-aiInstall Agent

Reviews code for quality, security, and convention compliance. Use when user asks to review, check, or verify code

sc-agent-skills-files5mo1.4k

@https-deeplearning-aiInstall Agent

Runs tests and generates them if missing for commands or functions. Use when user asks to test, run tests, and/or verify code…

sc-agent-skills-files5mo1.4k

@https-deeplearning-aiInstall Agent

Expert code review specialist. Use PROACTIVELY after writing or modifying code, before commits, when asked to review changes, PR…

project-starter5w1.4k

@cloudai-xInstall Agent

Expert debugging specialist for errors, test failures, crashes, segmentation faults, memory leaks, timeouts, race conditions,…

project-starter5w1.4k

@cloudai-xInstall Agent

Technical documentation specialist. Use for creating README files, API documentation, architecture docs, inline comments, user…

project-starter5w1.4k

@cloudai-xInstall Agent

Kimi K2 CLI + tmux multi-agent parallel dev platform with sengoku military hierarchy

multi-agent-shogun3mo1.4k

@yohey-wInstall Agent

Read-only evidence collector for fan-out audits — doc health sweeps, dead-code hunts, contract-drift checks, multi-file…

openmeld6d1.4k

@amplifthqInstall Agent

Adversarial final reviewer for a completed work order or diff — checks the change against its acceptance criteria and the scoped…

openmeld6d1.4k

@amplifthqInstall Agent

Use this agent when you need to create or update technical documentation that helps developers understand the deep patterns,…

jean6d1.4k

@coollabsioInstall Agent

Use this agent when you need expert guidance on React application architecture, component design, performance optimization, or…

jean6d1.4k

@coollabsioInstall Agent

Use this agent when working with Tauri applications, Rust backend development, Tauri plugins, cross-platform desktop app…

jean6d1.4k

@coollabsioInstall Agent

Update people profiles in 05-knowledge/people/ with new information from brief data, meetings, or Slack

cog-second-brain3w1.4k

@huytieuInstall Agent

Targeted fixes after task-verifier returns FAIL:fixable. Implements only what the verifier flagged; max 2 attempts per…

cog-second-brain3w1.4k

@huytieuInstall Agent

Draft session learnings from harvest staging into lizard-ready adoption notes. Propose-only; never writes durable 05-knowledge…

cog-second-brain3w1.4k

@huytieuInstall Agent

Agent Team 导师角色 — 观察其他 teammate 的执行状态，用智慧引导而非恐惧施压。当 teammate 陷入循环、放弃或被动时，以道德经智慧启发。建议 5+ teammate 的团队使用。

nopua6w1.4k

@wuji-labsInstall Agent

Agent Team Mentor Role — Observe teammate execution status, guide with wisdom rather than fear. When teammates get stuck in…

nopua6w1.4k

@wuji-labsInstall Agent

Agent Team メンター役 — 他のチームメイトの実行状況を観察し、恐怖ではなく知恵で導く。行き詰まり、放棄、受け身に陥ったときは道徳経の知恵で啓発。5人以上のチーム推奨。

nopua6w1.4k

@wuji-labsInstall Agent