vibekanban

A workspace for organizing and supervising AI coding agents. It can manage tasks, reviews, coding sessions, and separate Git worktrees, which are isolated copies of a project.

In plain words
What is it for?
Use it to assign coding tasks, run agents in isolated workspaces, review changes, handle subtasks and conflicts, and connect coding work with tools such as GitHub or VS Code.
Why use it?
It keeps AI-generated changes separated and makes it easier to track what each agent is doing and review its output before merging work.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/itechmeat/llm-code/vibekanban
Any agent
npx skills add itechmeat/llm-code --skill vibekanban
Clone the repo
git clone --depth 1 https://github.com/itechmeat/llm-code

Made for: Claude Code, Codex.

Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,328 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00074 $0.02328
Opus 5 $0.00037 $0.01164
Sonnet 5 $0.00015 $0.00466
Haiku 4.5 $0.00007 $0.00233

Measured 2d ago against content hash 9558bbbae4f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vibekanban 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 2d 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.

skills/vibekanban/SKILL.md · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vibe Kanban

Orchestration platform for AI coding agents. Plan, review, and manage AI-generated code in isolated git worktrees.

Quick Navigation

Topic Reference
Installation & Setup getting-started.md
Workspaces (Beta) workspaces.md
Projects, Tasks, Review core-features.md
Subtasks, Attempts, Conflicts advanced-features.md
Settings, Agents, Tags configuration.md
GitHub, Azure, VSCode, MCP integrations.md
Common Issues troubleshooting.md
Best Practices vibe-guide.md

Quick Start

Install & Run

npx vibe-kanban

npx vibe-kanban remains the canonical cross-platform launch path. As of v0.1.30, the packaged desktop app is moving onto a Tauri v2 shell with built-in auto-update behavior for installed desktop builds.

Release Highlights (0.1.15 → 0.1.28)

  • MCP server expanded: richer issue retrieval (get_issue includes tags/relationships/sub-issues) and new workspace/relationship/tag tools (e.g. update_workspace, relationship + tag mutations).
  • Frontend routing migrated to TanStack Router (navigation/URLs may differ from older screenshots).
  • Reliability improvements around Electric fallback and cancellation/tab-switch handling.
  • Review/diff UI improvements (annotation width fixes for horizontal scrolling).
  • Remote Access: pair a host via a code and access its workspaces from another device.
  • Workspace actions became safer around spin-off/duplicate flows by preserving branch and executor configuration more reliably.
  • Active agent runs can now accept image attachments, which is useful when feeding UI state, screenshots, or design feedback back into an in-progress session.
  • Transport reliability improvements: better relay disconnect handling and signing-session refresh.
  • Claude: bumped the default Sonnet model to 4.6.
  • Worktrees: preserve worktree path across cleanup to maintain Claude Code session continuity.
  • Workspaces: improved workspace logs capture (root execution-process provider).
  • Mobile UI fixes and Remote Access docs refresh.

Read the full file on GitHub · 284 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 2d ago First seen · 284 lines · 74 tokens per session scan A 9558bbbae4f2

Subscribe to this mod's changes

vibekanban is a skill published in the GitHub repository itechmeat/llm-code (22 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 2,328 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

paperclip

Interact with the Paperclip control plane API for task coordination and governance. Use when checking assignments, updating issue status, posting comments, delegating work, managing routines, or calling Paperclip API endpoints.

paperclipai/paperclip · 43 tokens

mempalace-task

Create, hand off, claim, execute, and close agent tasks through the MemPalace logstream. Use when the user wants to delegate work, prepare a ready-to-paste task for another agent, receive a MemPalace task id, or explicitly launch a supported headless agent in controlled mode.

MemPalace/mempalace · 67 tokens

agentflow

Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear). Manages multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and crash-proof pipeline execution.

sickn33/agentic-awesome-skills · 52 tokens

parallel-feature-development

Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…

wshobson/agents · 105 tokens

add-linear

Add Linear channel integration via Chat SDK. Issue comment threads as conversations.

nanocoai/nanoclaw · 17 tokens

coordinate

Coordinate a small team of Qwen Code teammates with enforced read-only workers, an optional worktree-pinned writer, shared tasks, peer messages, and existing Agent View tabs. Invoke explicitly with /coordinate.

QwenLM/qwen-code · 43 tokens