llm-as-computer

llm-as-computer is a skill for Claude Code, Codex from oaustegard/claude-skills. It costs 90 tokens per session (1,435 once invoked), scanned A, original, MIT.

An experimental computer implemented with transformer-model building blocks. It runs programs on a stack machine, a computer model that stores temporary values in a last-in, first-out stack.

In plain words
What is it for?
Use it to run example programs such as Fibonacci, factorial, greatest-common-divisor, and multiplication calculations, or to study compiled transformer behavior.
Why use it?
It provides a way to demonstrate how attention and feed-forward layers can perform program execution without conventional training.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to run example programs such as Fibonacci, factorial, greatest-common-divisor, and multiplication calculations, or to study compiled transformer behavior.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oaustegard/claude-skills/llm-as-computer
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.

Any agent
npx skills add oaustegard/claude-skills --skill llm-as-computer
Clone the repo
git clone --depth 1 https://github.com/oaustegard/claude-skills

Made for: Claude Code, Codex.

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 llm-as-computer

README.md
[![agentmods](https://agentmods.dev/badge/skills/oaustegard/claude-skills/llm-as-computer/github.svg)](https://agentmods.dev/skills/oaustegard/claude-skills/llm-as-computer)
Your own site
<a href="https://agentmods.dev/skills/oaustegard/claude-skills/llm-as-computer"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/llm-as-computer/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 llm-as-computer

Your own site · 80×15
<a href="https://agentmods.dev/skills/oaustegard/claude-skills/llm-as-computer"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/llm-as-computer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,435 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Data Exfiltration · line 126
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 130
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
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 $0.00090 $0.01435
Opus 5 $0.00045 $0.00718
Sonnet 5 $0.00018 $0.00287
Haiku 4.5 $0.00009 $0.00144

Measured 9d ago against content hash df7a335821e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

llm-as-computer scanned grade A with 1 finding 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 9d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (src/isa_lite.py, src/programs.py, src/runner.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sL -H "Authorization: token $GH_TOKEN" -H "Accept: application/vnd.github.v3.raw" \
llm-as-computer/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM-as-Computer: Compiled Transformer Stack Machine

A working computer built from transformer primitives. Every instruction fetch and stack read is a parabolic attention head (dot-product → argmax → value extraction). The transformer's weights ARE the interpreter — compiled analytically, not trained.

What This Proves

Attention is lookup; feed-forward is routing. A vanilla transformer with compiled weights can execute arbitrary programs: loops, recursion, arithmetic, memory access. 55 opcodes covering WASM i32 semantics. 21M+ steps/second via the Mojo executor.

Setup (once per session)

cd /mnt/skills/user/llm-as-computer/src && bash setup.sh

This installs Mojo (~20s) and compiles the executor binary (~6s). If Mojo is unavailable, the skill falls back to a pure-Python executor (slower but functional).

Usage

import sys
sys.path.insert(0, '/mnt/skills/user/llm-as-computer/src')

from programs import make_fibonacci, make_factorial, make_gcd, make_multiply
from runner import run, setup

# Ensure Mojo is compiled (idempotent)
setup()

# Run a program — shows instructions, trace, result
prog, expected = make_fibonacci(10)
print(run(prog))

# Benchmark mode — measures throughput
print(run(prog, benchmark=True, repeat=200))

Available Programs

From programs.py — all return (program, expected_result):

Generator Description Example
make_fibonacci(n) Iterative fib via SWAP+OVER+ADD+ROT fib(10)=55, 111 steps
make_multiply(a, b) Repeated addition mul(7,8)=56
make_factorial(n) Loop with MUL fact(8)=40320
make_gcd(a, b) Euclidean algorithm gcd(48,18)=6
make_power_of_2(n) Repeated doubling 2^7=128
make_sum_1_to_n(n) Accumulation loop sum(15)=120
make_is_even(n) Parity check is_even(7)=0
make_native_multiply(a,b) Single MUL opcode
make_native_divmod(a,b) DIV_S + REM_S
make_compare_binary(op,a,b) eq/ne/lt_s/gt_s/le_s/ge_s
make_bitwise_binary(op,a,b) and/or/xor/shl/shr_u/rotl/rotr
make_select(a,b,c) Conditional select

Read the full file on GitHub · 135 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 135 lines · 90 tokens per session scan A df7a335821e4

Subscribe to this mod's changes

llm-as-computer is a skill published in the GitHub repository oaustegard/claude-skills (148 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 1,435 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

claude-cookbooks

Claude AI cookbooks - code examples, tutorials, and best practices for using Claude API. Use when learning Claude API integration, building Claude-powered applications, or exploring Claude capabilities.

aiskillstore/marketplace · 41 tokens

rlhf

Understanding Reinforcement Learning from Human Feedback (RLHF) for aligning language models. Use when learning about preference data, reward modeling, policy optimization, or direct alignment algorithms like DPO.

itsmostafa/llm-engineering-skills · 40 tokens

claude-students

Transforma una carpeta cruda de material de un parcial universitario (PDFs, DOC/DOCX, PPT, audios .ogg de WhatsApp, capturas) en un material de estudio polished y completo — HTML SOTA autocontenido + paquete de artefactos de NotebookLM (podcast en español, infografía, guía de estudio, briefing doc, mind map, quiz…

josuebustosn/claude-students · 234 tokens

moodle-coderunner

Generate Moodle CodeRunner programming questions with Jobe server validation. Uses minimal pipeline: AI generates code + tests, Jobe computes expected output. Supports Java, Python, C, C++, Node.js. Produces import-ready Moodle XML. Battle-tested: 1000+ questions validated with 0% failure rate.

danielcregg/coderunner-skill · 69 tokens

02-ai-ml-learning

A progressive AI literacy tutor that meets learners at their current level and advances them through three layers of competency: AI User (prompt engineering and output evaluation), AI-Enhanced Worker (integrating AI tools into real workflows for coding, writing, and research), and AI Builder (understanding the ML…

24kchengYe/human-skill-tree · 0 tokens

scholar-wendao

A tool for building reusable analysis lenses from scholars and research fields. It gathers multilingual books, secondary research, biographies, and academic debates, then extracts the scholar’s concepts and methods.

tizzy916/scholar-wendao-skill · 181 tokens