llm-as-computer SKILL.md skillA
llm-as-computer from oaustegard/claude-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add oaustegard/claude-skills/llm-as-computer@v1.0.1Pins v1.0.1 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- oaustegard/claude-skills
- Path
llm-as-computer/SKILL.md- Versions recorded
- 2
- Latest version
- v1.0.1, committed Mar 25, 2026
- First version recorded
- Mar 24, 2026
- Size
- 4,854 bytes
- Repository stars
- 158
- License
- MIT
Execute programs on a compiled transformer stack machine where every instruction fetch and memory read is a parabolic attention head. Demonstrates that transformer attention + FF layers can implement a working computer. Use when user mentions "llm-as-computer", "lac", "stack machine", "compiled transformer", "percepta", "parabolic attention", "execute program", or asks to run/trace programs on the transformer executor.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 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) ```bash 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 ```python 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)) …
Read the whole file at its exact version.
How to install
mdr add oaustegard/claude-skills/llm-as-computer@sha256:df7a335821e49e25The line at the top of this page pins the label v1.0.1, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_a3mkoinbvkixjqsl)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Mar 24, 2026 and Mar 25, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.1 latest | 2026-03-25 | d7cc8b2 | 4,854 B | A | view · diff |
| v1.0.0 | 2026-03-24 | 3313f52 | 4,854 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4854 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
oaustegard/claude-skills · 158 stars · license MIT · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_a3mkoinbvkixjqsl GET https://markdownregistry.com/api/v1/resolve?ref=oaustegard/claude-skills/llm-as-computer GET https://markdownregistry.com/api/v1/blob/df7a335821e49e25dc241dbbd814f04f10afebf3e38101248f9158a9b63e6e5d
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from oaustegard/claude-skills
Every file in oaustegard/claude-skills