Claude Code agents

chenyuxiaojin/cyxj-remotion-starter

Agent Claude Code

A read-only reviewer for Remotion projects, which create videos from code, before an expensive render.

Xipher-Labs/walter-os

Agent Claude Code

Write external-facing DevRel content — Twitter/X threads, LinkedIn posts, YouTube video scripts, podcast outlines, conference talk abstracts, hackathon submission narratives, customer-facing announcements. Use this subagent when the user asks to "draft a thread", "write a script for the video", "outline the talk"…

hamzabellouch/agent-skills

Agent Claude Code

Orchestrates the full multi-skill academic research pipeline and manages agent handoffs across phases.

widnyana/eyay-toolkits

Agent Claude Code

Slim coding worker for the pi-coordinator. Edits exactly the files and lines its prompt names, commits, and reports commit/files/uncommitted. Not for exploration or open-ended tasks.

viknesh20-20/claude-code-tool-kit

Agent Claude Code

Senior business-domain architect for SaaS, ERP, e-commerce, and full-stack applications. Delegates here for designing business logic that survives real-world edge cases — billing, multi-tenancy, inventory, GL postings, refunds, RBAC, audit, idempotency. Knows how Stripe, Linear, NetSuite, Shopify, and similar solve…

memi-design/design-sandbox

Agent Claude Code

Scaffolds shadcn-based React compositions into src/app/sandbox/page.tsx from a spec (from screenshot-decoder) or a plain brief. Use AFTER screenshot-decoder, or directly when the user gives a text-only brief.

steve-magne/hookstack

Agent Claude Code needs its repo

Auteur de hooks agentiques Hookstack (.claude/hooks/.mjs). Utiliser pour créer ou modifier un hook du catalogue. Maîtrise le pattern testable run()+DI, le sync vers registry.json (codesnippet dérivé), le fingerprint @hookstack, le schéma registry et la timeline. Le .mjs sur disque est la source de vérité du code.

taniwhaai/arai

Agent Claude Code

Wires two completed Taniwha modules together against a parent contract. Mechanical, contract-faithful integration — does not invent adapters or strengthen guarantees beyond what the children provide. Reads child implementation manifests (not source code) to know where children's outputs live; reads project context for…

luccapinto/agentic-data-kit

Agent Claude Code

Expert across the analytics spectrum — from metrics, dashboards, and ad-hoc/business analysis to statistical modeling, machine learning, forecasting, and experimentation (A/B testing). Also reviews semantic models for business accuracy. Triggers on analysis, dashboard, metric, KPI, insight, report, semantic model…

slbug/claude-ruby-grape-rails

Agent Claude Code

Analyze observational skill-monitor results and recommend evidence-backed follow-ups. Use after /skill-monitor when contributors want cautious improvement guidance.

NexaDuo/mARC

Agent Claude Code

Correctness/quality review specialist (IRC handle @rev) dispatched to audit pull requests and branch diffs for bugs, regressions, and maintainability issues before code merges, alongside @sec's security pass.

LH8PPL/core-memory-kit

Agent Claude Code

Deep implementation work delegated by the lead — writing kit code, writing tests (five-exit-doors discipline), debugging failures, and the implementer self-review pass on a diff. Use for any coding work bigger than a trivial edit. Runs on Opus.

gosha70/code-copilot-team

Agent Claude Code

Generates a cooldown report — bug fixes shipped + pitches ready for next betting table. Writes specs/retros/cooldown-after-NN.md.

spjoshis/claude-code-plugins

Agent Claude Code

Master Python 3.12+ with modern features, async programming, performance optimization, and production-ready practices. Expert in the latest Python ecosystem including uv, ruff, pydantic, and FastAPI. Use PROACTIVELY for Python development, optimization, or advanced Python patterns.

hatewx/oh-my-ipd

Agent Claude Code

A coding role that turns detailed plans into code, tests the result, and fixes problems found during review.

luca-mastrostefano/agent-native-setup

Agent Claude Code

Reviews the diff against the four execution principles. Use after changing code.

uwuclxdy/agenticat

Agent Claude Code

Drives a TUI or CLI program like a real user in a local tmux pty. - Use when a TUI or CLI needs a real run in a terminal: black-box, drives the built binary, never its unit tests. Read-only on source; builds or launches the target itself, reports pass/fail with captured screens. Spawn one per program or flow.

mfmezger/ai_agent_dotfiles

Agent Claude Code

Identify code smells, best practices violations, and test smells across Python, Go, and Rust codebases with language-specific guidance and recommendations.

sjarmak/coding-agent-workflows

Agent Claude Code

Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.

timurgaleev/vibestack

Agent Claude Code

Workflow automation architect for n8n, Make, Zapier, and custom orchestration pipelines. Use PROACTIVELY when designing automation flows, integrating APIs, or building event-driven workflows.

smicolon/ai-kit

Agent Claude Code

System architect specialist supporting native Mermaid.js and Eraser.io diagram-as-code. Creates ERDs, flowcharts, system architecture, sequence diagrams, class diagrams, cloud diagrams, and BPMN/swimlane diagrams using text-based syntax.

brainOS-HQ/brain-os

Agent Claude Code

Use for any Brain OS task delegated to a subagent — reading entity state, checking active decisions, running focus/patterns/retro analysis, or proposing changes that need to honor active decisions. Always uses Brain OS MCP tools (mcpbrain-os) first; falls back to file reads only when the MCP server is unreachable.…

asale-ai/seo-geo-skill

Agent Claude Code

Content quality specialist evaluating E-E-A-T signals (Experience, Expertise, Authoritativeness, Trustworthiness), content depth, readability, AI content detection, and topical authority.

configflux/weld

Agent Claude Code

Demo worker-shaped orchestrator. Dispatches to implementer / reviewer / qa specialists per task class. Modeled on the real worker.md so that slice-1 q8rl regex (literal subagenttype) and slice-2 hw6j frontmatter (placeholder declaration) both have non-Claude-only fixture coverage.