design.how
Design systems, skills and visuals for coding agents
Runssource: GitHubhomepageTypeScriptMITcommit c0f7df5116fc
TypeScript, MIT licensed. The project labels itself: agent skills, ai agents, canvas, claude code, codex, coding agents, creative coding and cursor.
design.how runs. An Argusic agent installed it in 11 minutes and hit 3 errors on a clean machine with no GPU, and the whole session was recorded.
All 278 self-test checks pass across 9 test suites (evals, oklch, check-system, capture-guard, pixdiff, land, bodies-check, legacy, parity), lint is clean for 8 skills, all 72 vault check scripts pass, Playwright with Chromium launches successfully, and all Python dependencies (fonttools, brotli, uharfbuzz, numpy, pillow) import correctly.
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 93.3 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.
- Python dependencies fonttools, brotli, uharfbuzz, numpy, pillow not installed2 minutes
- Playwright and Chromium browser not installed2 minutes
- make-motion template requires Node >=22.6, environment has v18.19.1
- Install time
- 11 minutes
- Cold machine to finish
- 12 minutes
- Errors hit and fixed
- 3 hit, 2 fixed with no human help
- How the result was proved
- node evals/run.mjs --lint exited 0 (8 skills clean); node evals/run.mjs --self-test passed (22 checks); oklch.mjs --self-test passed (35 checks); check-system.mjs --self-test passed (55 checks); capture-guard.mjs --self-test passed (52 checks); pixdiff.mjs --self-test passed (6 checks); land.mjs --self-test passed (44 checks); bodies-check.mjs --self-test passed (16 checks); legacy.mjs --self-test passed (32 checks); parity.mjs --self-test passed (16 checks); 278 total self-test checks all passed; 72 vault visual skill checks all passed; 4 webp assets decoded cleanly via PIL and ffmpeg
- Model tokens used
- 100,853
- Exact commit tested
- c0f7df5116fc
- 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.
ok a GraphQL request is logged under its operation name ok guard.log keeps no body on a GET all as expected exec /bin/sh -lc 'cd /work/repo && echo "Time check:" && date' in /work/repo succeeded in 0ms: Time check: Mon Nov 16 07:27:23 UTC 2026 All verification is complete. Here is the final report: tokens used 100,853 All verification is complete. Here is the final report:
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.
- 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 11 minutes to install, slower than the median of the 122 comparable projects Argusic has measured.
- Hit 3 errors during setup, 1 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 123 agent-skills projects Argusic has installed and timed, design.how was the 104th fastest to reach a running state, and 94 of 123 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.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
agent-skillsai-agentscanvasclaude-codecodexcoding-agentscreative-codingcursordesign-systemdesign-tokenskinetic-typographyreactshadcnshadcn-registryshaderstailwindcsstypescriptuiwebgl
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/design-how)Questions
- Does design.how run?
- Yes. design.how runs. Argusic installed and launched it on a clean machine in 11 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test design.how?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit c0f7df5116fc. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test design.how?
- The run that produced this verdict cost $0.09: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does design.how take to install?
- 11 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 design.how need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing design.how?
- 3 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does design.how compare with the alternatives?
- Of the 123 agent-skills projects Argusic has installed and timed, design.how was the 104th fastest to reach a running state, and 94 of 123 reached one at all.
- Where is the evidence for design.how?
- 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.