Agents

Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.

architect

1657

SymKit/bundles-rules

Agent Claude Code

Technical architecture and design specialist. Use when planning feature implementation, making technology choices, designing interfaces, or when a PM specification is ready for technical design. Analyzes existing codebase patterns and produces technical plans.

not rated 3 5mo ago A 44 tokens

reviewer

1658

beettlle/pi-spine

Agent Claude Code

Cross-model code and plan reviewer — provides independent quality assessment.

not rated 3 7d ago A 14 tokens original MIT

financial-analyst

1659

lsiyu241-creator/awesome-claude-cookbook

Agent Claude Code needs its repo

Financial analysis expert specializing in startup metrics, burn rate, runway calculations, and investment decisions. Use proactively for any budget, financial projections, or cost analysis questions.

not rated 3 2mo ago A 37 tokens copy · 100% MIT

gemini-research-expert

1660

ishandutta2007/Awesome-AI-Job-Hunting

Agent Claude Code

Use this agent when the user needs to perform research tasks, gather information from external sources, or investigate topics that require web searches and synthesis of information.

not rated 3 18d ago A 37 tokens copy · 100% MIT

azure-governance

1661

janegilring/awesome-azure-landing-zones

Agent Claude Code

Azure governance and policy expert. Designs and operates policy-driven guardrails with Azure Policy and initiatives, the ALZ default policies, Azure Monitor Baseline Alerts (AMBA), Enterprise Policy as Code (EPAC), compliance mapping, and remediation.

not rated 3 2mo ago A 53 tokens original MIT

geometry-solver

1662

jchildree/Claud-itect-Skill

Agent Claude Code

Specialized agent for NgonENGINE's Ren (練) mathematical solver layer. Handles Newell normal computation, Mean Value Coordinates, GJK/EPA physics, SubRegion generation, and planarity validation. Use for any geometry math task.

not rated 3 2mo ago A 53 tokens

code-reviewer

1664

rileyhilliard/agentrc

Agent Claude Code

Expert at comprehensive code review for merge requests and pull requests from technical, product, and DX perspectives. Use this agent when the user has completed work on a feature branch and needs review before merging. Analyzes all changes between branches, evaluates user impact, assesses developer experience…

not rated 3 6mo ago A 72 tokens original MIT

qa

1666

erniker/understudy

Agent Claude Code

QA Engineer — testing, quality, testing strategy.

not rated 3 9d ago A 11 tokens original MIT

glean-expert

1667

gleanwork/configure-mcp-server

Agent Claude Code

PROACTIVELY use this subagent when coding tasks would benefit from enterprise context—debugging, testing, understanding code, or researching features. This agent searches Slack/Jira/GitHub/Confluence/Drive via Glean, then chains read/quote or code lookup for precise, sourced answers.

not rated 3 11d ago A 66 tokens original MIT

asp-migrator

1668

maxmash1/dotnet-react-starter-demo

Agent Claude Code

Migrates Classic ASP pages to modern .NET 8 Web API + React 18 TypeScript — full-stack analysis, backend scaffolding, frontend creation, and security hardening.

not rated 3 4mo ago A 40 tokens

trsdn/github-copilot-agent

Agent Claude Code

Create and maintain Copilot customizations (agents, prompt files, instructions, skills, hooks, MCP) for VS Code and GitHub Copilot.

not rated 3 19d ago A 35 tokens original MIT

plan-reviewer

1670

S-Corkum/mirdan

Agent Claude Code

Plan review agent — verifies plan grounding and produces staff-engineer-quality review report.

not rated 3 3mo ago A 19 tokens

Technical Manager

1671

mcpambassador/server

Agent Claude Code

Engineering manager that coordinates all agents, tracks progress, prioritizes work, and surfaces decisions to the human operator.

not rated 3 5d ago A 25 tokens original Apache-2.0

performance-analyst

1672

DEBARPAN2000/tradingview-mcp

Agent Claude Code

Trading strategy performance analyst. Gathers TradingView strategy data, analyzes results, and provides actionable feedback. Use when reviewing backtest results.

not rated 3 5mo ago A 32 tokens fork

code-reviewer

1673

mattmre/EVOKORE-MCP-PUBLIC

Agent Claude Code

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

not rated 3 3mo ago A 52 tokens copy · 100% MIT

theagenticguy/opencodehub

Agent Claude Code

Produce {{ docsroot }}/architecture/data-flow.md: a walk of the top 3 processes in {{ repo }}, each rendered as numbered steps plus one Mermaid sequenceDiagram. Every step cites path:LOC for the function that advances the flow.

not rated 3 1mo ago A 0 tokens original Apache-2.0

gitlab-assistant

1675

nickveenhof/cursor-gitlab-plugin

Agent Claude Code

GitLab Assistant — AI agent with product management capabilities that uses the GitLab MCP server for Agile planning, prioritization, delivery tracking, and stakeholder communication. Refers to Duo Agent Platform agents and flows for specialized tasks.

not rated 3 6mo ago A 49 tokens original MIT

agent-spawning

1676

airmcp-com/mcp-standards

Agent Claude Code

Guide to spawning agents with Claude Code's Task tool.

not rated 3 9mo ago A 0 tokens copy · 100% MIT archived

project-tracking-pm

1677

urjitbhatia/tpm-mcp

Agent Claude Code

Project tracking PM using the TPM MCP server. Invoke when user mentions ':TPM:', asks about roadmaps/tasks, or completes work that should be tracked.

not rated 3 8mo ago A 37 tokens

auth-guard

1678

Njengah/claude-code-tracker

Agent Claude Code

Read-only reviewer for JWT login, password hashing, and /auth routes in this tracker. Use when the user asks to review auth.py, registration, login tokens, or getcurrentuser. Use after changes to auth helpers or auth routes. Do not use for session/cost exploration or for implementing features.

not rated 3 20d ago A 65 tokens

rig-debugger

1679

agent-rig/rig

Agent Claude Code

Systematic root-cause debugger. Use when investigating a failing test, a production bug, a flaky behavior, or any "this doesn't work and I don't know why" situation. Walks Phase 1 → 4 (root-cause → pattern analysis → hypothesis → minimal fix) and refuses to propose fixes before evidence is in.

not rated 3 yesterday A 71 tokens original MIT

adr-reviewer

1680

shimo4228/claude-harness

Agent Claude Code

Strict Architecture Decision Record reviewer. Reviews ADRs for section completeness, context-decision alignment, straw-man alternatives, one-sided consequences, unsourced numeric claims, and unstated override relationships with prior ADRs. Use PROACTIVELY after writing or substantially revising an ADR, before commit.…

not rated 3 +1 6d ago A 91 tokens original MIT

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: