autozyme: Instructions file for Claude Code

CLAUDE.md

autozyme CLAUDE.md is an instructions file for Claude Code from ElliotXie/autozyme. It costs 289 tokens per session, scanned A, original, MIT.

Project instructions for Autozyme, a command-line workflow that optimises scientific-computing functions on the CPU. It supports Python and R tasks and uses datasets hosted on Hugging Face.

In plain words
What is it for?
Use them to initialise an optimisation task, try and assess hypotheses, accept or reject changes, check task status, and run validation.
Why use it?
They explain the required environments and the optimisation loop, reducing setup mistakes when improving a target function.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is ElliotXie/autozyme's own configuration. It tells Claude Code how to work on autozyme 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 autozyme configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ElliotXie/autozyme. 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/ElliotXie/autozyme/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ElliotXie/autozyme

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.

agentmods badge for autozyme CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/elliotxie/autozyme/claude-md/github.svg)](https://agentmods.dev/instructions/elliotxie/autozyme/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/elliotxie/autozyme/claude-md"><img src="https://agentmods.dev/badge/instructions/elliotxie/autozyme/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.

agentmods 80×15 button for autozyme CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/elliotxie/autozyme/claude-md"><img src="https://agentmods.dev/badge/instructions/elliotxie/autozyme/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 289 This file is loaded in full into every session.
When invoked 289 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 $0.00289 $0.00289
Opus 5.5 $0.00116 $0.00116
Sonnet 5.5 $0.00058 $0.00058
Haiku 4.5 $0.00029 $0.00029

Measured 2mo ago against content hash 6538b8ff8bba, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

autozyme 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 · 33 lines

What it actually says

autozyme

Autonomous CPU-side speed optimization of scientific computing functions. One target function per task; iterate via the zyme CLI.

Layout

  • autozyme_cli/ — the CLI framework. Install with pip install -e autozyme_cli/.
  • autozyme_py/ — Python accelerator package (ships optimized patches).
  • autozyme_r/ — R accelerator package (ships optimized patches).
  • datasets/ — README + setup scripts. Actual data on HuggingFace: elliotxie/autozyme-datasets.

How to use

  1. pip install -e autozyme_cli/
  2. zyme --version to verify
  3. Follow autozyme_cli/zyme/prompts/Bio/0_bootstrap.md to start a new optimization task

Environment

  • R tasks (Seurat, Bioconductor): need R + relevant packages installed.
  • Python tasks (Scanpy, etc.): need conda env with the target package.
  • Data: downloaded from HuggingFace by the init agent when needed.

CLI quick reference

zyme init <repo> [<function>]    # scaffold a task
zyme run "<hypothesis>"          # run an optimization attempt
zyme accept / reject             # keep or discard
zyme status                      # task state summary
zyme verify                      # thread x tier validation matrix
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. 2mo ago First seen · 33 lines · 289 tokens per session scan A 6538b8ff8bba

Subscribe to this mod's changes

autozyme CLAUDE.md is an instructions file published in the GitHub repository ElliotXie/autozyme (80 stars, last pushed 1mo ago), licensed MIT. It adds 289 tokens to every session, about $0.0012 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 2026-08-30.

Related

autozyme CLAUDE.md compared with instructions from other repositories

autozyme CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
autozyme CLAUDE.mdElliotXie/autozymeInstructions file801mo agoMITA289Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot