tinker-cookbook: Instructions file for Claude Code

AGENTS.md

tinker-cookbook AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from thinking-machines-lab/tinker-cookbook. It costs 1,835 tokens per session, scanned A, original, Apache-2.0.

Project instructions for working on Tinker Cookbook, a code library for training and evaluating language models through the Tinker service.

In plain words
What is it for?
They help agents work with the repository, understand its nested data types, follow its skills for research, debugging, and Inkling models, and respect public-repository practices.
Why use it?
They explain the project’s structure, conventions, data types, and how its training and evaluation work is divided between local code and remote GPU processing.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: Claude Code plugin machinery, but also the file is AGENTS.md. Also seen: mentions Claude Code.

This is thinking-machines-lab/tinker-cookbook's own configuration. It tells Claude Code, Codex and OpenCode how to work on tinker-cookbook itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tinker-cookbook configures →

About the project

Tinker Cookbook is a collection of libraries and examples for fine-tuning language models through the Tinker training service, which handles distributed training behind an API. It is used by researchers and developers for language-model post-training and experimentation, with examples built around common fine-tuning tasks. The catalogue entries provide agent workflows and integrations for using the cookbook.

thinking-machines-lab/tinker-cookbook · 4,097 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to thinking-machines-lab/tinker-cookbook. 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/thinking-machines-lab/tinker-cookbook/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/thinking-machines-lab/tinker-cookbook

Made for: Claude Code, Codex, OpenCode.

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 tinker-cookbook AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/thinking-machines-lab/tinker-cookbook/agents-md.svg)](https://agentmods.dev/instructions/thinking-machines-lab/tinker-cookbook/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/thinking-machines-lab/tinker-cookbook/agents-md"><img src="https://agentmods.dev/badge/instructions/thinking-machines-lab/tinker-cookbook/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,835 This file is loaded in full into every session.
When invoked 1,835 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01835 $0.01835
Opus 5 $0.00918 $0.00918
Sonnet 5 $0.00367 $0.00367
Haiku 4.5 $0.00184 $0.00184

Measured 7d ago against content hash 1ccc02bb74c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tinker-cookbook AGENTS.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 7d 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.

AGENTS.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tinker Cookbook Agent Guide

Quick reference for agents working on tinker-cookbook. Detailed guidance is in the skills under skills/.

tinker-cookbook is a client library with training and eval code built on the Tinker service (hosted by Thinking Machines Lab) and the Tinker SDK (a separate repo with just the API). You author training/eval loops that run on a CPU machine; Tinker executes the heavy GPU work.

Skills: This repo ships three Claude Code skills in skills/: research (SFT, RL, DPO, distillation, evaluation, model selection, experiment methodology), debug (performance, correctness, renderer, and error triage), and inkling (thinking effort, rendering, post-training, and multimodal input for Inkling series models). Install via /plugin marketplace add thinking-machines-lab/tinker-cookbook, then use /tinker:research, /tinker:debug, or /tinker:inkling.

Composing Types

Agents often struggle with the nested type hierarchy.

Core types:

  • Datum = model_input (ModelInput) + loss_fn_inputs (dict of TensorData)
  • ModelInput = list of chunks (EncodedTextChunk, ImageChunk)
  • TensorData = wrapper for numpy/torch arrays with shape info

Helper functions (use these instead of manual construction):

  • datum_from_model_input_weights(model_input, weights, max_length) - SL datum creation (supervised/common.py)
  • conversation_to_datum(messages, renderer, max_length, train_on_what) - Full pipeline (supervised/data.py)
  • renderer.build_supervised_example(messages) - Returns (ModelInput, weights)
  • ModelInput.from_ints(tokens) - Create from token list
  • TensorData.from_numpy(arr) / TensorData.from_torch(tensor) - Wrap arrays

Architecture

Builder pattern: Config objects are chz dataclasses (SupervisedDatasetBuilder, RLDatasetBuilder, EnvGroupBuilder). They expose .build()/__call__() returning runtime objects.

Key code locations:

  • SL: tinker_cookbook/supervised/train.py
  • RL: tinker_cookbook/rl/train.py
  • DPO: tinker_cookbook/preference/train_dpo.py
  • Renderers: tinker_cookbook/renderers/
  • Completers: tinker_cookbook/completers.py
  • RL types: tinker_cookbook/rl/types.py
  • Rollout strategies: tinker_cookbook/rl/rollout_strategy.py (FailFast, RetryOnFailure)
  • Logging: tinker_cookbook/utils/logtree.py, tinker_cookbook/rl/rollouts.py
  • Recipes: tinker_cookbook/recipes/

Read the full file on GitHub · 111 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. 7d ago First seen · 111 lines · 1,835 tokens per session scan A 1ccc02bb74c1

Subscribe to this mod's changes

tinker-cookbook AGENTS.md is an instructions file published in the GitHub repository thinking-machines-lab/tinker-cookbook (4,097 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,835 tokens to every session, about $0.0092 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

next.js AGENTS.md

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

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

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

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

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 · 4,469 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