What is agentboard CLAUDE.md?

A set of instructions for AgentBoard, a shared code repository for tracking AI-agent work through projects, tasks, progress, comments, and state changes.

Use it when changing AgentBoard’s shared types, task state machine, Fastify server, SQLite database, WebSocket features, Telegram integration, or agent worker.

It explains how the repository is divided into packages and how its server, database, API, and agent workflow fit together.

How seoshmeo/agentboard configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to seoshmeo/agentboard. 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/seoshmeo/agentboard/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/seoshmeo/agentboard

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/seoshmeo/agentboard/claude-md/github.svg)](https://agentmods.dev/instructions/seoshmeo/agentboard/claude-md)

Your own site

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

Per session 2,509 This file is loaded in full into every session.

When invoked 2,509 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	$0.02509	$0.02509
Opus 5.5	$0.01004	$0.01004
Sonnet 5.5	$0.00502	$0.00502
Haiku 4.5	$0.00251	$0.00251

Measured 2mo ago against content hash 62c7a13de0c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agentboard 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 2mo 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 · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentBoard

Acceptance-driven development board for AI agents. Monorepo with pnpm workspaces.

Architecture

packages/
├── shared/          # TypeScript types + state machine (ItemStatus, Role, transitions)
│   └── src/
│       ├── types.ts     # Item, Project, Epic, DecisionLog, Comment, ItemContext, ItemProgress, FileEntry, etc.
│       ├── states.ts    # 7 transitions, findTransition(), getAvailableTransitions()
│       └── index.ts     # Barrel export
├── server/          # Fastify API + SQLite (Drizzle ORM) + WebSocket + Telegram + Agent Worker
│   └── src/
│       ├── index.ts              # Entry point (port 3000)
│       ├── db/schema.ts          # 10 tables: projects, api_keys, items, dependencies, decision_logs, comments, chat_messages, epics, settings, item_progress
│       ├── db/connection.ts      # better-sqlite3 + Drizzle, WAL mode
│       ├── db/migrate.ts         # CREATE TABLE IF NOT EXISTS (runs on startup)
│       ├── middleware/auth.ts     # Bearer token → role extraction
│       ├── routes/projects.ts    # CRUD + API key gen + CLAUDE.md template
│       ├── routes/items.ts       # CRUD + transitions + /next + dependencies + comments + progress
│       ├── routes/decisions.ts   # Decision log CRUD
│       ├── routes/epics.ts       # Epic CRUD + roadmap-text endpoint
│       ├── routes/chat.ts        # AI chat per item (Claude Haiku 4.5)
│       ├── routes/files.ts       # File browser (tree + content, path traversal protection)
│       ├── routes/settings.ts    # Global settings key-value store + resolveAnthropicKey()
│       ├── routes/health.ts      # GET /api/health + GET /api/auth/me
│       ├── services/state-machine.ts  # Transition validation + execution
│       ├── services/context.ts        # Context assembly (item + deps + logs)
│       ├── services/agent-worker.ts   # Auto-plans drafts, auto-implements approved items (Claude Haiku 4.5)
│       ├── services/telegram.ts       # Notifications on pending_review/done/rejected
│       └── ws/index.ts                # WebSocket broadcast to all connected clients
└── web/             # React 19 + Vite + Tailwind v4 + TanStack Query + dnd-kit
    └── src/
        ├── main.tsx              # React entry point + QueryClient
        ├── App.tsx               # Auth screen + sidebar layout + page routing
        ├── api/client.ts         # fetch wrapper + all React Query hooks + validateApiKey()
        ├── hooks/useWebSocket.ts # Auto-reconnecting WS, invalidates queries
        ├── hooks/useEscapeKey.ts # Escape key handler for modals
        ├── lib/utils.ts          # cn(), color maps, status labels
        └── components/
            ├── Board.tsx          # DnD context + 6 columns
            ├── Column.tsx         # Droppable column with status header
            ├── ItemCard.tsx       # Draggable card (title, priority, sprint, progress bar)
            ├── ItemDetail.tsx     # Modal: transitions, edit/delete, deps, logs, comments, epic, progress, AI chat
            ├── CreateItemForm.tsx # Create item modal with epic selector
            ├── DecisionLog.tsx    # Expandable log list with markdown rendering
            ├── SprintFilter.tsx   # Sprint dropdown filter
            ├── Sidebar.tsx        # Collapsible left nav (Board, Projects, Roadmap, Activity, Files, Settings)
            ├── ProjectsPage.tsx   # Projects management page (list, connect, switch, create with key validation)
            ├── ProjectSettings.tsx  # Project settings modal (name, description, API keys, Telegram, localPath)
            ├── ActivityFeed.tsx   # Activity feed (full page)
            ├── Roadmap.tsx        # Epics/roadmap (full page) with progress bars
            ├── ErrorBoundary.tsx  # React error boundary with refresh button
            ├── FileBrowser.tsx    # File tree + code viewer modal
            ├── GlobalSettings.tsx # Global Anthropic API key settings modal
            ├── ItemChat.tsx       # AI chat panel within ItemDetail
            └── Markdown.tsx       # Reusable markdown renderer (marked + DOMPurify)

Read the full file on GitHub · 178 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.

2mo ago First seen · 178 lines · 2,509 tokens per session scan A 62c7a13de0c8

Subscribe to this mod's changes

agentboard CLAUDE.md is an instructions file published in the GitHub repository seoshmeo/agentboard (6 stars, last pushed 8mo ago), licensed MIT. It adds 2,509 tokens to every session, about $0.0100 per session on Opus 5.5. 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.

agentboard CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agentboard CLAUDE.mdseoshmeo/agentboard	Instructions file	6	8mo ago	MIT	A	2,509	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	280k	2d ago	MIT	A	4,325	Codex, OpenCode

agentboard: Instructions file for Claude Code