claude-howto
A visual, example-driven guide to Claude Code, from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
Runssource: GitHubhomepagePythonMITcommit 188f46889323
Python, MIT licensed. The project labels itself: claude code, guide and tutorial.
claude-howto runs. An Argusic agent installed it in 0.3 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
All automated tests pass, EPUB and static website build successfully, and all validation/check scripts (mermaid, cross-references, links, markdown rendering, epub diagrams) report clean results.
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.
- Node.js v18.19.1 too old for Pele 1.6.0 (requires >=20)2 minutes
- Install time
- under a minute
- Cold machine to finish
- 3 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- pytest scripts/tests/ -v exited 0, 174 passed 1 skipped; build_epub.py produced valid EPUB; build_website.py produced 85-page site served with HTTP 200; all 5 check scripts passed
- Model tokens used
- 159,136
- Exact commit tested
- 188f46889323
- 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.
**Install**: Dependencies installed successfully via `python3 -m venv .venv` and `pip install -r re… **Tests**: 174 passed, 1 skipped (the skipped test is `test_bundle_loads_as_esm_without_syntax_dete… **Build verification**: - `scripts/build_epub.py` — EPUB created (510KB, 139 entries, valid ZIP, valid `mimetype`) - `scripts/build_website.py` — Static site built (85 pages, Tailwind CSS compiled) - `scripts/check_mermaid.py` — 286 Mermaid blocks rendered across 55 files - `scripts/check_cross_references.py` — 479 files validated, all OK - `scripts/check_links.py` — 215 external URLs reachable - `scripts/check_markdown_rendering.py` — 79 README files clean, 4 rules - `scripts/check_epub_diagrams.py` — 54 Pele-rendered diagrams, 62 references, 0 placeholders - Website pages served with HTTP 200 (index, guide, CSS, module pages, learning roadmap) - Vietnamese EPUB build also succeeded
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.
- Installed in 0.3 minutes, faster than the median of the 16 comparable projects Argusic has measured.
- Recovered from all 1 error 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
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 17 claude-code projects Argusic has installed and timed, claude-howto was the 2nd fastest to reach a running state, and 16 of 17 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.
- A quick evaluation: it was running 0.3 minutes after the clone.
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)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/claude-howto)Questions
- Does claude-howto run?
- Yes. claude-howto runs. Argusic installed and launched it on a clean machine in 0 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test claude-howto?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 188f46889323. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test claude-howto?
- The run that produced this verdict cost $0.02: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does claude-howto take to install?
- 0.3 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 claude-howto need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing claude-howto?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does claude-howto compare with the alternatives?
- Of the 17 claude-code projects Argusic has installed and timed, claude-howto was the 2nd fastest to reach a running state, and 16 of 17 reached one at all.
- Where is the evidence for claude-howto?
- 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.