agentmods.dev

dafthunk CLAUDE.md

A project guide for Dafthunk, a visual workflow automation platform built on Cloudflare. It explains the monorepo layout, where the web app, API, shared packages, and database-related code live, and which commands operate on each part.

In plain words
What is it for?
Use it to start the web or API locally, build the project, check types, lint, run tests, or run API integration tests.
Why use it?
It helps agents work on the correct service and avoid running broad commands when only one workspace needs attention.

Instructions file

119 7d ago A scan 1,553 tokens original MIT
View the source file dafthunk-com/dafthunk
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/dafthunk-com/dafthunk/claude-md
Clone the repo
git clone --depth 1 https://github.com/dafthunk-com/dafthunk
Per session 1,553 This file is loaded in full into every session.
When invoked 1,553 The same file — it is already loaded in full.
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 $0.01553 $0.01553
Opus 5 $0.00776 $0.00776
Sonnet 5 $0.00311 $0.00311
Haiku 4.5 $0.00155 $0.00155

Measured 3d ago against content hash 6073e60ddbe1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dafthunk 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 3d 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.

CLAUDE.md

Project Overview

Dafthunk is a visual workflow automation platform built on Cloudflare infrastructure (Workers, D1, R2, AI). Users create workflows by connecting 50+ node types in a visual editor (React Flow).

Monorepo structure (pnpm workspaces):

  • apps/api - Backend (Hono on Cloudflare Workers)
  • apps/web - Frontend (React 19 + React Router v7 + Vite)
  • packages/types - Shared TypeScript types
  • packages/utils - Shared utilities

Development Commands

Common commands

pnpm dev                                       # Start all services
pnpm build                                     # Build all packages and apps
pnpm typecheck                                 # Type check all workspaces
pnpm lint                                      # Lint and type check
pnpm check                                     # Auto-fix linting + format
pnpm test                                      # Run tests

# Workspace-specific (use --filter)
pnpm --filter '@dafthunk/api' dev              # API dev server (port 3001)
pnpm --filter '@dafthunk/web' dev              # Web dev server (port 3000)
pnpm --filter '@dafthunk/api' test:integration # Integration tests

# Database migrations
pnpm --filter '@dafthunk/api' db:migrate       # Apply migrations locally
pnpm --filter '@dafthunk/api' db:generate      # Generate new migrations
pnpm --filter '@dafthunk/api' db:prod:migrate  # Apply to production

Architecture

Backend: API (apps/api/)

Routes (src/routes/)

  • Organized by feature (workflows, executions, objects, etc.)
  • Stateless: each request is self-contained
  • Auth in src/auth.ts (JWT + API Keys)
  • Multi-tenant: always scope by organizationId from context (c.get("organizationId"))
  • Validate with Zod + @hono/zod-validator

Database (src/db/)

  • D1 (SQLite) + Drizzle ORM
  • Schema: schema/index.ts
  • Queries: queries.ts
  • Migrations: migrations/ (generate with drizzle-kit)
  • Convention: snake_case in SQL, camelCase in TypeScript

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.

  1. 3d ago First seen · 178 lines · 1,553 tokens per session scan A 6073e60ddbe1

Subscribe to this mod's changes

dafthunk CLAUDE.md is an instructions file published in the GitHub repository dafthunk-com/dafthunk (119 stars, last pushed 7d ago), licensed MIT. It adds 1,553 tokens to every session, about $0.0078 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.

artificial-intelligenceautomationcloudflaredata-flowdevelopmentgenerative-ai
Related

Other instructions, from other repositories

langgraphjs CLAUDE.md

Instructions for langchain-ai/langgraphjs, covering langgraphjs development guide, corridor security analysis, build & test commands, code style guidelines and library architecture.

langchain-ai/langgraphjs · 497 tokens

langgraphjs AGENTS.md

Instructions for langchain-ai/langgraphjs, covering repository instructions and corridor security analysis.

langchain-ai/langgraphjs · 54 tokens

flow-like node-creation.instructions.md

Instructions for Rheosoph/flow-like, covering node creation guidelines, feature gating for heavy dependencies, when to use feature gating, how to gate a node and what not to gate.

Rheosoph/flow-like · 4,313 tokens

flow-like CLAUDE.md

Claude Code instructions for Rheosoph/flow-like, covering claude.md — flow-like, repository layout, build & dev commands, rust and full workspace check.

Rheosoph/flow-like · 2,163 tokens

flow-like AGENTS.md

AGENTS.md instructions for Rheosoph/flow-like, covering repository prose standard, start with the reader, voice and structure, patterns to remove and technical prose.

Rheosoph/flow-like · 973 tokens

flow-like copilot-instructions.md

Copilot instructions for Rheosoph/flow-like, covering flow-like wasm node development — rust, project overview, build & test, architecture and pin types.

Rheosoph/flow-like · 1,349 tokens