stack-diagram
Agent skill: describe your stack in a sentence, get an architecture diagram with official logos
Runssource: GitHubPythonMITcommit 75dbd3e3c6fe
Python, MIT licensed. The project labels itself: agent skills, architecture diagram, claude code, claude skills, codex, diagram, system architecture and tech stack.
stack-diagram runs. An Argusic agent installed it in 14 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The real icon-fetch, HTML-build, and Chromium PNG-render pipeline for stack-diagram runs successfully in this container and produces valid self-contained HTML plus decodable 2000x1082 PNGs in light and dark themes.
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. 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.
- First build failed: unresolved %%ICON_tool1%%/%%ICON_tool2%% tokens — my draft's node-section regex missed template sample nodes3 minutes
- System pip refused install (PEP 668 externally-managed environment)2 minutes
- `check.png` displayed image incorrect in initial test: `file` binary not installed in container2 minutes
- fontTools WOFF2 probe needed brotli extension1 minute
- `assets/template.html` has no token for the HTML <title> (sample `<!-- TITLE -->` leaks into output)1 minute
- Install time
- 14 minutes
- Cold machine to finish
- 4 minutes
- Errors hit and fixed
- 5 hit, 5 fixed with no human help
- How the result was proved
- python3 scripts/build.py … → exit 0 'built out.html (100 KB)'; python3 scripts/render_png.py … → exit 0 'rendered check.png' + 'rendered check-dark.png' (2000x1082 each); ffmpeg -v error -i check.png -f null - and check-dark.png both exit 0; headless Chromium DOM check: 10/10 icons loaded, 0 broken, both themes
- Model tokens used
- 172,330
- Exact commit tested
- 75dbd3e3c6fe
- 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
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 1, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
- `fonttools` woff2 probe initially failed (missing `brotli`); fixed by installing `brotli` in the … - Repo gap (no fix needed): `assets/template.html` ships the sample `<title><!-- TITLE --></title>`… **Verification evidence** - Python 3.12.3; `python3 -m venv` works; Playwright 1.64.1 + Chromium 156.0.8078.4 installed. - `fetch_icons.py`: 9/9 icons fetched, exit 0, `manifest.json` written with per-icon source/url/fil… - `build.py`: exit 0 — `built out.html (100 KB)`; 9 embedded svg data URIs + 2 font data URIs; zero… - Bundled fonts decode as valid WOFF2 (Geist Regular / JetBrains Mono Regular via fonttools). - `render_png.py`: exit 0, printed `rendered check.png` and `rendered check-dark.png`; both 2000×10… - DOM check in headless Chromium at `/tmp/sd-work/out.html`: 10/10 icon images loaded, 0 broken, in… **Notes** - This is a Argusic Agent/Claude *skill* repo, not an app or a servable project, so "launch" is the… - The title token gap aside, everything in README/SKILL that I tried worked as documented. Artifact…
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 5 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 14 minutes to install, slower than the median of the 104 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 105 agent-skills projects Argusic has installed and timed, stack-diagram was the 91st fastest to reach a running state, and 75 of 105 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-skillsarchitecture-diagramclaude-codeclaude-skillscodexdiagramsystem-architecturetech-stack
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/stack-diagram)Questions
- Does stack-diagram run?
- Yes. stack-diagram runs. Argusic installed and launched it on a clean machine in 14 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test stack-diagram?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 75dbd3e3c6fe. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test stack-diagram?
- The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does stack-diagram take to install?
- 14 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 stack-diagram need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing stack-diagram?
- 5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does stack-diagram compare with the alternatives?
- Of the 105 agent-skills projects Argusic has installed and timed, stack-diagram was the 91st fastest to reach a running state, and 75 of 105 reached one at all.
- Where is the evidence for stack-diagram?
- 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.