anatomy
An agent skill for creating detailed, interactive isometric illustrations of real-world machines and complex systems. Generates polished SVGs with optional WebGL shaders and 3D effects.
Runssource: GitHubhomepageJavaScriptMITcommit 689dcf966e63
JavaScript, MIT licensed. The project labels itself: agent skill, open source, svg and vizualization.
anatomy runs. An Argusic agent installed it in 15 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The full 206-test suite passes on Node 22 with the portable Chromium, all example builds with their geometry audits complete, and the dial-indicator and raptor-engine figures render and respond to input in headless Chromium with clean console output.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- System Node v18.19.1 below required 20.10+ (tests need 22); skills CLI needs >=22.203 minutes
- No Chrome/Chromium installed for the repo's headless render checks3 minutes
- Chromium aborted: FATAL: No usable sandbox! (container blocks unprivileged user namespaces; repo spawns Chrome without --no-sandbox)3 minutes
- skills CLI crashed on Node 18 with 'node:util does not provide styleText'2 minutes
- Install time
- 15 minutes
- Cold machine to finish
- 14 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- node --test scripts/*.test.mjs (Node 22, CHROME_PATH=wrapper, NODE_PATH=test deps) exited 0 with 206 passed / 0 failed; scripts/drive.mjs screenshots of dial-indicator and raptor-engine rendered in Chromium with real readouts and 'console: clean', and ffmpeg -v error -i <png> -f null - decoded both with zero errors; raptor ArrowRight moved aria-valuenow 0 to 1
- Model tokens used
- 450,367
- Exact commit tested
- 689dcf966e63
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
**What was done** - Installed per README: `npx skills add wheresryan22/anatomy -g -a claude-code` → "✓ anatomy (copie… - Readied the runtime: Node 22.23.3 (npx-provided binary, system Node 18 too old), portable Chromiu… - Ran the full CI command: `node --test scripts/*.test.mjs` → **206 tests, 206 pass, 0 fail**. - Rebuilt every example (`build.mjs` incl. `--light`, `--verify`, `stress`); their built-in geometr… - Launched the figures in real headless Chromium via `scripts/drive.mjs`: dial-indicator rendered w… - Ran `scripts/lines.mjs` figure check → `line ends: 0 of 367 ends on 23 lines float` (exit 0). **Errors fixed** 1. Node v18.19.1 too old (needs ≥20.10; skills CLI needs ≥22.20) → used Node 22.23.3 binary via `np… 2. No browser installed → downloaded portable Chromium 157. 3. Chromium aborted with `FATAL: No usable sandbox!` (container blocks unprivileged user namespaces… 4. `skills` CLI crashed on Node 18 (`styleText` missing) → invoked its bin with Node 22.
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Recovered from all 4 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Took 15 minutes to install, slower than the median of the 9 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 10 agent-skill projects Argusic has installed and timed, anatomy was the 10th fastest to reach a running state, and 7 of 10 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
Run history
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/anatomy)Questions
- Does anatomy run?
- Yes. anatomy runs. Argusic installed and launched it on a clean machine in 15 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test anatomy?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 689dcf966e63. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test anatomy?
- The run that produced this verdict cost $0.15: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does anatomy take to install?
- 15 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does anatomy need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing anatomy?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does anatomy compare with the alternatives?
- Of the 10 agent-skill projects Argusic has installed and timed, anatomy was the 10th fastest to reach a running state, and 7 of 10 reached one at all.
- Where is the evidence for anatomy?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.