agentkitai

47 mods across 4 repositories, 63 stars between them.

agentgate

01

agentkitai/agentgate

MCP server Claude CodeCodexCursor +2

Human-in-the-loop approval gateway for AI agents over MCP: request, decide, approve. Runs locally from the @agentkitai/agentgate-mcp npm package.

33 2d ago A tokens not measured original MIT

bmad-master

02

agentkitai/agentlens

Command Claude Code

You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.

22 2d ago A 8 tokens original MIT

analyst

03

agentkitai/agentlens

Command Claude Code

You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.

22 2d ago A 6 tokens copy · 83% MIT

architect

04

agentkitai/agentlens

Command Claude Code

You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.

22 2d ago A 4 tokens copy · 81% MIT

dev

05

agentkitai/agentlens

Command Claude Code

You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.

22 2d ago A 4 tokens copy · 78% MIT

pm

06

agentkitai/agentlens

Command Claude Code

You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.

22 2d ago A 4 tokens copy · 81% MIT

qa

07

agentkitai/agentlens

Command Claude Code

You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.

22 2d ago A 4 tokens copy · 84% MIT

quick-flow-solo-dev

08

agentkitai/agentlens

Command Claude Code

You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.

22 2d ago A 12 tokens copy · 77% MIT

sm

09

agentkitai/agentlens

Command Claude Code

You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.

22 2d ago A 4 tokens copy · 83% MIT

tech-writer

10

agentkitai/agentlens

Command Claude Code

You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.

22 2d ago A 8 tokens copy · 88% MIT

ux-designer

11

agentkitai/agentlens

Command Claude Code

You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.

22 2d ago A 8 tokens copy · 86% MIT

agentkitai/agentlens

Command Claude Code

Critical validation workflow that assesses PRD, Architecture, and Epics & Stories for completeness and alignment before implementation. Uses adversarial review approach to find gaps and issues.

22 2d ago A 39 tokens copy · 84% MIT

code-review

13

agentkitai/agentlens

Command Claude Code

Perform an ADVERSARIAL Senior Developer code review that finds 3-10 specific problems in every story. Challenges everything: code quality, test coverage, architecture compliance, security, performance. NEVER accepts looks good - must find minimum issues and can auto-fix with user approval.

22 2d ago A 61 tokens copy · 77% MIT

correct-course

14

agentkitai/agentlens

Command Claude Code

Navigate significant changes during sprint execution by analyzing impact, proposing solutions, and routing for implementation.

22 2d ago A 20 tokens copy · 89% MIT

create-architecture

15

agentkitai/agentlens

Command Claude Code

Collaborative architectural decision facilitation for AI-agent consistency. Replaces template-driven architecture with intelligent, adaptive conversation that produces a decision-focused architecture document optimized for preventing agent conflicts.

22 2d ago A 38 tokens copy · 89% MIT

agentkitai/agentlens

Command Claude Code

Transform PRD requirements and Architecture decisions into comprehensive stories organized by user value. This workflow requires completed PRD + Architecture documents (UX recommended if UI exists) and breaks down requirements into implementation-ready epics and user stories that incorporate all available technical…

22 2d ago A 73 tokens copy · 84% MIT

create-prd

17

agentkitai/agentlens

Command Claude Code

Create a comprehensive PRD (Product Requirements Document) through structured workflow facilitation.

22 2d ago A 19 tokens original MIT

agentkitai/agentlens

Command Claude Code

Create comprehensive product briefs through collaborative step-by-step discovery as creative Business Analyst working with the user as peers.

22 2d ago A 26 tokens original MIT

create-story

19

agentkitai/agentlens

Command Claude Code

Create the next user story from epics+stories with enhanced context analysis and direct ready-for-dev marking.

22 2d ago A 23 tokens copy · 78% MIT

create-ux-design

20

agentkitai/agentlens

Command Claude Code

Work with a peer UX Design expert to plan your applications UX patterns, look and feel.

22 2d ago A 23 tokens copy · 81% MIT

dev-story

21

agentkitai/agentlens

Command Claude Code

Execute a story by implementing tasks/subtasks, writing tests, validating, and updating the story file per acceptance criteria.

22 2d ago A 25 tokens copy · 95% MIT

document-project

22

agentkitai/agentlens

Command Claude Code

Analyzes and documents brownfield projects by scanning codebase, architecture, and patterns to create comprehensive reference documentation for AI-assisted development.

22 2d ago A 28 tokens copy · 72% MIT

domain-research

23

agentkitai/agentlens

Command Claude Code

Conduct domain research covering industry analysis, regulations, technology trends, and ecosystem dynamics using current web data and verified sources.

22 2d ago A 27 tokens original MIT

edit-prd

24

agentkitai/agentlens

Command Claude Code

Edit and improve an existing PRD - enhance clarity, completeness, and quality.

22 2d ago A 19 tokens original MIT