vibeboard AGENTS.md

Repository instructions for VibeBoard, a self-hosted kanban board for developers who use AI coding agents. Moving a card to “In Progress” can start an agent in the project folder, while people and agents can update the same board.

In plain words
What is it for?
Use them when working on cards, agent start and stop behavior, task dependencies, progress notes, real-time updates, or the board’s MCP server.
Why use it?
They explain how the board, agent routing, live updates, and communication tools fit together before code is changed.

Instructions file for CodexOpenCode

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 instructions/zanuartri/vibeboard/agents-md
Clone the repo
git clone --depth 1 https://github.com/zanuartri/vibeboard

Made for: Codex, OpenCode.

Per session 2,838 This file is loaded in full into every session.
When invoked 2,838 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.02838 $0.02838
Opus 5 $0.01419 $0.01419
Sonnet 5 $0.00568 $0.00568
Haiku 4.5 $0.00284 $0.00284

Measured yesterday against content hash a13f38cc3152, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

vibeboard AGENTS.md scanned grade B with 1 finding 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 yesterday.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- **Codex**: add a `vibeboard` entry under `mcpServers` in `~/.codex/config.json`
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VibeBoard — Agent Context

What is this project

VibeBoard is a self-hostable open source kanban board built for developers who work with AI coding agents.

Core concept: When you move a card with an assigned agent to "In Progress", VibeBoard automatically spawns that agent (Claude Code, OpenCode, Codex, or Command Code) in your project directory. The agent can then use MCP tools to add progress notes, move cards, and mark tasks complete.

Bidirectional MCP: Both the human (via UI) and the agent (via MCP) can control the same board in real-time.

Project structure

vibeboard/
├── mcp-server/
│   ├── index.js        ← Bootstrap: migrate, prune, wire modules, listen
│   ├── config.js       ← PORT / HOST / PUBLIC_DIR / VERSION
│   ├── events.js       ← SSE client registry + emitSSE (proxy in MCP-only mode)
│   ├── auth.js         ← Network-mode token middleware
│   ├── http-routes.js  ← registerRoutes(app): all REST + SSE endpoints
│   ├── mcp-tools.js    ← registerMcpTools(mcp): all MCP tool definitions
│   ├── mcp-config.js   ← Per-agent MCP config discovery / write
│   ├── agent-routing.js← routeSpawn/Stop + dependency (blocked_by) checks
│   ├── agent.js        ← Agent spawning, queue, lifecycle, usage parsing
│   ├── worktree.js     ← Git worktree create/merge/PR helpers
│   ├── models.js       ← Per-agent model lists
│   ├── db.js           ← SQLite database layer (cross-platform)
│   └── migrate.js      ← Legacy JSON to SQLite migration
├── public/
│   ├── index.html      ← Kanban UI markup (no inline JS/CSS)
│   ├── styles.css      ← UI styles
│   └── js/             ← UI logic as ordered classic scripts (no bundler)
│       ├── bootstrap.js, workspaces.js, board.js, realtime.js,
│       └── shortcuts-io.js, md-render.js, datepicker.js, card-sidebar.js,
│           dialogs.js, app.js
├── .claude/
│   └── mcp.json        ← MCP config for Claude Code
├── README.md           ← User documentation
├── CONTRIBUTING.md     ← Contributor guidelines
└── AGENTS.md           ← This file (agent context)

Read the full file on GitHub · 223 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.

  1. yesterday First seen · 223 lines · 2,838 tokens per session scan B a13f38cc3152

Subscribe to this mod's changes

vibeboard AGENTS.md is an instructions file published in the GitHub repository zanuartri/vibeboard (2 stars, last pushed 3mo ago), licensed MIT. It adds 2,838 tokens to every session, about $0.0142 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.