kanNINJA turns project management into something an agent does. Create boards, break down work, move tasks, and run standups by talking to your AI instead of clicking around a UI.
Pull action items out of notes and file them as Kata.
Break a goal into Kata and lay them out on a Dojo.
Summarize where a Dojo stands right now.
Turn your assigned Kata into a tight standup update.
Sweep a Dojo for stale, blocked, and unassigned Kata.
Run kanNINJA — Dojos, Kata, standups — from any AI agent.
This repository is the distribution layer for the kanNINJA MCP server. One hosted server, packaged for three agent platforms from a single source.
/plugin marketplace add brandonkorous/kanninja-marketplace
/plugin install kanninja@wizeworks
The first tool call opens an OAuth sign-in to kanNINJA — no API key to copy.
You get the kanninja MCP server (~40 tools), a fluency skill, and five
workflow commands: /kanninja:standup, :plan-sprint, :triage, :recap,
:capture.
| Platform | Lives in | How to use |
|---|---|---|
| Claude Code | repo root (.claude-plugin/, plugins/) | /plugin marketplace add brandonkorous/kanninja-marketplace |
| Gemini CLI | gemini/ | gemini extensions link ./gemini |
| ChatGPT | openai/ | Add the MCP URL as a connector — see openai/README.md |
All three connect to the same remote MCP server, https://mcp.kanninja.com/mcp.
Everything is generated from one canonical source:
shared/ ← edit here. The single source of truth.
kanninja.config.json product, vendor, MCP endpoints, version
skill.md the kanNINJA fluency skill
recipes/ standup · plan-sprint · triage · recap · capture
build/ the generator (plain Node 22+, no dependencies)
Rebuild after any change to shared/:
node build/build.mjs
Generated — do not hand-edit: .claude-plugin/, plugins/, gemini/,
openai/. Change shared/ and rebuild.
Adding a recipe is a one-file edit in shared/recipes/. Adding a fourth
platform is one new module in build/lib/.
MIT
External network access
Connects to servers outside your machine
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub brandonkorous/kanninja-marketplace --plugin kanninjaHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows