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 skills add oaustegard/claude-skills --skill llm-as-computergit clone --depth 1 https://github.com/oaustegard/claude-skillsWrote 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/skills/oaustegard/claude-skills/llm-as-computer)<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.
<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>- NVIDIA SkillSpector warn
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.
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 5.1 | $0.00090 | $0.01435 |
| Opus 5 | $0.00045 | $0.00718 |
| Sonnet 5 | $0.00018 | $0.00287 |
| Haiku 4.5 | $0.00009 | $0.00144 |
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.
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" \ 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 |
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.
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.
- 9d ago First seen · 135 lines · 90 tokens per session scan A df7a335821e4
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.
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.
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.
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…
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.
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…
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.