What is mcp-kanban CLAUDE.md?

Project instructions for MCP Kanban, a local task board that AI agents control through the Model Context Protocol while developers watch in a web interface.

Use them when developing, debugging, or extending the MCP Kanban CLI, web UI, MCP server, or local SQLite database.

They give an agent the project structure, architecture, technology choices, and important design decisions needed to work safely in the repository.

How gablabelle/mcp-kanban configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to gablabelle/mcp-kanban. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/gablabelle/mcp-kanban/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/gablabelle/mcp-kanban

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/gablabelle/mcp-kanban/claude-md/github.svg)](https://agentmods.dev/instructions/gablabelle/mcp-kanban/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/gablabelle/mcp-kanban/claude-md"><img src="https://agentmods.dev/badge/instructions/gablabelle/mcp-kanban/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/gablabelle/mcp-kanban/claude-md"><img src="https://agentmods.dev/badge/instructions/gablabelle/mcp-kanban/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 599 This file is loaded in full into every session.

When invoked 599 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00599	$0.00599
Opus 5	$0.00300	$0.00300
Sonnet 5	$0.00120	$0.00120
Haiku 4.5	$0.00060	$0.00060

Measured 9d ago against content hash 073caf82f511, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-kanban CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

MCP Kanban is a local-first Kanban board for AI agents, powered by the Model Context Protocol (MCP). AI agents interact with the board via MCP tools to create, update, and complete tasks. Developers observe and guide through a real-time web UI. Distributed as a CLI tool (npx mcp-kanban).

Architecture

Four layers:

CLI Layer — Entry point (npx mcp-kanban). Handles onboarding, DB init, config, provider integration, and launches the server + UI.
Web UI — React + Vite + Tailwind + dnd-kit + WebSockets. Visual Kanban board with drag-and-drop, real-time updates, details panel, session filtering.
MCP Server — Exposes tools (create_ticket, update_ticket, move_ticket, create_subtask, etc.) for AI agents. Acts as the agent API layer.
Database — SQLite (local-first, zero config). Tables: projects, columns, sessions, tickets, attachments, dependencies.

Key Design Decisions

Provider system: Pluggable adapters for AI agent integrations (Claude Code, Codex, Cursor). Each provider implements detect/install/uninstall/verify.
Sessions: Represent AI execution contexts; tickets are color-coded by session.
Tickets: Can be stories or subtasks. Subtasks are full tickets nested under a parent. Stories show progress bars based on subtask completion.
Real-time: WebSockets push all changes (ticket CRUD, moves, subtask completion) to the UI instantly.
Config: Stored at ~/.mcp-kanban/config.json.
Attachments: Stored locally in attachments/ directory.
Worktree support: When Claude Code runs with --worktree, a new MCP server process is spawned in the worktree directory. It auto-detects the worktree branch and creates (or reuses) a session for it. All MCP server instances share the same SQLite DB (~/.mcp-kanban/kanban.db) — they do NOT start a new HTTP/WebSocket server. The single web UI server (started by mcp-kanban start) receives notifications from all MCP processes. If mcp-kanban start detects an existing server on the port, it skips startup and opens the browser to the running instance.

Read the full file on GitHub · 36 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

9d ago First seen · 36 lines · 599 tokens per session scan A 073caf82f511

Subscribe to this mod's changes

mcp-kanban CLAUDE.md is an instructions file published in the GitHub repository gablabelle/mcp-kanban (3 stars, last pushed 6mo ago), licensed MIT. It adds 599 tokens to every session, about $0.0030 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Project management

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

mcp-kanban: Instructions file for Claude Code