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.
npx agentmods add instructions/yoshyaes/deckle/claude-mdgit clone --depth 1 https://github.com/Yoshyaes/deckleWrote 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.
[](https://agentmods.dev/instructions/yoshyaes/deckle/claude-md)<a href="https://agentmods.dev/instructions/yoshyaes/deckle/claude-md"><img src="https://agentmods.dev/badge/instructions/yoshyaes/deckle/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02344 | $0.02344 |
| Opus 5 | $0.01172 | $0.01172 |
| Sonnet 5 | $0.00469 | $0.00469 |
| Haiku 4.5 | $0.00234 | $0.00234 |
Grade A, and why
deckle 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Deckle is a PDF generation API ("Stripe for PDFs"). It accepts HTML or template data and returns pixel-perfect PDFs. The codebase is a pnpm monorepo with Turborepo orchestration.
Commands
pnpm install # Install all workspace dependencies
pnpm dev # Run all dev servers (API :3000, Dashboard :3001)
pnpm build # Build all packages via Turborepo
# API server
pnpm --filter @deckle/api dev # API dev server with hot reload
pnpm --filter @deckle/api build # Build API
pnpm --filter @deckle/api db:push # Push schema to database
pnpm --filter @deckle/api db:generate # Generate migration files
pnpm --filter @deckle/api db:migrate # Run migrations
# Testing
cd apps/api && npx vitest run # Run all 36 API tests
cd apps/api && npx vitest run src/__tests__/generate-validation.test.ts # Single test file
# Dashboard
pnpm --filter @deckle/dashboard dev # Next.js dev on port 3001
pnpm --filter @deckle/dashboard build # Build dashboard
# TypeScript SDK
pnpm --filter @getdeckle/sdk build # Build SDK (ESM + CJS + types)
pnpm --filter @getdeckle/sdk dev # Watch mode build
# React component library
cd packages/react && npm run build # Build @deckle/react
# Playwright (required once before API dev)
cd apps/api && npx playwright install chromium
# Docker (self-hosted)
docker compose -f docker-compose.selfhost.yml up -d
Architecture
Monorepo layout (pnpm-workspace.yaml covers apps/* and packages/*):
apps/api— Hono API server. Playwright renders HTML→PDF. Drizzle ORM for PostgreSQL. Redis for rate limiting + BullMQ job queue. Multi-provider storage (local/R2/S3/GCS).apps/dashboard— Next.js 14 App Router. Clerk auth. Tailwind CSS with dark theme (#0A0A0B bg, #F97316 accent). DM Sans body font, JetBrains Mono for code.packages/sdk-typescript— npm packagedeckle. Dual ESM/CJS build via tsup.Deckleclass withgenerate(),fromTemplate(),fromReact(),batch(), andtemplates.*namespace.packages/sdk-python— pip packagedeckle. Mirrors TS SDK API. Uses httpx + Pydantic v2.packages/sdk-go— Go modulegithub.com/Yoshyaes/deckle/packages/sdk-go. Stdlibnet/http+ functional options. Context-based API.packages/sdk-ruby— Ruby gemdeckle. Uses Faraday HTTP client. Idiomatic Ruby API.packages/react—@deckle/reactcomponent library (Document, Page, Header, Footer, Table, Grid, Watermark, Barcode, Signature).packages/mcp-server— MCP server for AI agent integration (Claude Desktop, Cursor, Claude Code). 7 tools.docs/— Mintlify documentation site. Framework guides for Next.js, Express, FastAPI, Django, Rails.public/— AI discoverability:llms.txt,llms-full.txt.
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.
- 4d ago First seen · 157 lines · 2,344 tokens per session scan A a60ef9846ddf
deckle CLAUDE.md is an instructions file published in the GitHub repository Yoshyaes/deckle (2 stars, last pushed 1mo ago), licensed MIT. It adds 2,344 tokens to every session, about $0.0117 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.