Agent Kanban — Testing skill for Claude Code
Local-first kanban for AI-agent workflows.
How to install Agent Kanban
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open boian-ivanov/agent-kanban and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Agent Kanban does
Local-first kanban for AI-agent workflows. Drag a task to Approved and your AI coding agent picks it up via MCP and drives it through analyst → in_progress → testing on its own. MCP for Claude Code & Cline, OpenAPI for opencode / Open WebUI / Ollama / any function-calling LLM. SQLite + FastAPI, runs on localhost.
Alternatives in Testing
- Spec Kitty — Spec-Driven Development for serious software developers 1.6k ★
- Spec Driven Develop — Spec-driven development workflow for AI coding agents: architecture-first planning, task decomposition, GitHub 975 ★
- Claude Dev Skill — A Claude Code custom skill that turns Claude into a Tech Lead — coordinating parallel Worker Agents through a 112 ★
README
agent-kanban
Local-first kanban for AI-agent workflows. SQLite, FastAPI, no auth, no cloud.
[](LICENSE) [](https://www.python.org/)
A self-hosted kanban board designed to be driven by AI coding agents (Claude Code, Cline, opencode, Open WebUI, any function-calling LLM). Drag-drop in browser, REST + MCP for agents. Multi-project, light/dark theme, markdown plan-file import, automation rules.

More themes & profiles| Dark theme | Cyberpunk profile | Horizon profile |
|---|---|---|
![]() |
![]() |
![]() |
Toggle theme with `t`, cycle profiles with `p`. Or pin a theme/profile via URL: `?theme=light&profile=cyberpunk`.
Features
- 9 workflow columns: Backlog → Approved → Analyst → In progress → Testing → UAT → Done, plus Blocked / Cancelled.
- Multiple projects in one DB, URL-routed (
/p/{slug}), each with optional Claude Code-project directory binding. - Light/dark theme switcher (
t), density toggle (d), collapsible columns, sidebar. - Search + filter chips, keyboard shortcuts (
/,n,r,\,Esc). - Inbox watcher: drop a
.mdintokanban_data/inbox/, get a card in 5 sec. PointKANBAN_INBOX_DIRat any folder you like — even~/.claude/projects//memory/inbox/for Claude session captures. - PLAN.md import (loose-mode parser): any
## Section→ cards in backlog with section-name in description. - Automation rules (
kanban_data/rules.json):task_idle: status=done, days=14 → move_to cancelled, etc. Hot-reloaded. - Outbound webhooks (
kanban_data/webhooks.json): POST to Slack / Telegram / any HTTP endpoint ontask_created/task_moved/task_commented/task_updated. 3 formats: `generi
Related Skills
Pi Task
Deterministic spec-orchestration for local LLMs in the pi coding agent — drives prompts through refine→researc
Vindicate
A local-first Playwright test automation toolkit for AI coding agents (Cursor, Claude Code, Copilot), with MCP
Tatai
Tatai 塔台 — local-first workbench for one person orchestrating multiple AI coding agents (Claude Code / Codex /
Superpowers Evals
Behavioral eval lab (Quorum) for the superpowers project that drives real coding-agent CLIs (Claude, Codex, Ge
Zames Pro
Terminal coding agent that drives chat.deepseek.com through Playwright — no API key required. Reads/edits file
Specstride
Spec-driven autonomous coding orchestrator: drives your agent through GitHub Spec Kit phases behind an LLM cri
Related Agents
Worca Cc Manual Web UI Testing
Manual web UI testing agent for the orchestrator pipeline. Drives the RUNNING web UI through the manual test c
Orca
Lead-developer orchestrator. Watches a project's GitHub issues, plans, dispatches work to subagent workers, tr
E2e QA Tester
Browser QA specialist for wp-rocket. Boots the local environment, drives the WordPress admin via Playwright MC


