grain CLAUDE.md

grain CLAUDE.md is an instructions file for coding agents from tjakoen/grain. It costs 1,246 tokens per session, scanned A, original, Apache-2.0.

A set of working instructions for the GRAIN monorepo, a single code repository containing several related packages. It documents the packages, working rules, commands and writing style for that project.

In plain words
What is it for?
Use it when working in the GRAIN workspace to understand its packages, commands, standards and relationships between the design system, content tools, planning board and guided-tour layer.
Why use it?
It gives the coding agent the project’s structure and non-negotiable rules before it makes changes. This reduces misunderstandings about how the repository is organised and operated.

Instructions file

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/tjakoen/grain/claude-md
Clone the repo
git clone --depth 1 https://github.com/tjakoen/grain

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.

agentmods badge for grain CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tjakoen/grain/claude-md.svg)](https://agentmods.dev/instructions/tjakoen/grain/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/tjakoen/grain/claude-md"><img src="https://agentmods.dev/badge/instructions/tjakoen/grain/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,246 This file is loaded in full into every session.
When invoked 1,246 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 $0.01246 $0.01246
Opus 5 $0.00623 $0.00623
Sonnet 5 $0.00249 $0.00249
Haiku 4.5 $0.00125 $0.00125

Measured 5d ago against content hash a4296e850352, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

grain 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 5d 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 · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md: GRAIN monorepo

Read this first, then the docs it points to. Keep it accurate: if you change how the workspace works (a package, a command, a rule), update this file in the same change. This repo wires into Tjakoen's personal standards, published at https://tjakoen.github.io/standards. Reference them, don't fork them.

What this is

The Bun-workspace monorepo for the GRAIN family: four published layers that build on each other, plus a workspace-only MCP server over their built output, each its own package, no build step, everything runs on Bun straight from TypeScript. An app can adopt just the design system or the whole stack.

Package What it is
@tjakoen/grain The AI-interaction design system + default theme. Every surface is operable by a human or an AI through one shared vocabulary, with the AI's presence shown as a visible signal (grain = AI).
@tjakoen/mill Markdown In, Living Layouts. A Markdown to GRAIN-pages CMS.
@tjakoen/proof The AI plan board. Plans are markdown; the board is a live projection that never writes back.
@tjakoen/crumb The guided-tour, demo-mode, and AI-review layer. Published and live on tjakoen.github.io.

Dependency direction runs one way: a substrate (BATCH is the reference) sits below grain, mill builds on grain, proof builds on mill, crumb builds on grain and mill. grain imports nothing from the substrate except one port. Never reach across or upward; add a port instead.

Each package carries its own CLAUDE.md and PLAN.md with that layer's rules, non-negotiables, and hard-won lessons. Working inside a layer? Read its file first. This root file is the workspace front door.

How I work here (non-negotiables)

The full rulebook is AI-DEVELOPMENT.md plus SESSION-LOOP.md (session mechanics, memory, handoff, model economy). The short version:

Read the full file on GitHub · 91 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. 5d ago First seen · 91 lines · 1,246 tokens per session scan A a4296e850352

Subscribe to this mod's changes

grain CLAUDE.md is an instructions file published in the GitHub repository tjakoen/grain (184 stars, last pushed 16d ago), licensed Apache-2.0. It adds 1,246 tokens to every session, about $0.0062 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 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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

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.

vercel/next.js · 7,296 tokens