learn-claude-code
Bash is all you need - A nano claude code, like 「agent harness」, built from 0 to 1
Runssource: GitHubhomepagePythonMITcommit 0dcafa2ae053
Python, MIT licensed. The project labels itself: agent, agent development, ai agent, claude, claude code, educational, llm and python.
learn-claude-code runs. An Argusic agent installed it in 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 482 pytest tests pass after fixing 'python' to 'python3' in one test; all 17 chapter code.py files and 13 legacy agent scripts compile cleanly; s01 and s08 agent loop scripts launch their REPL prompt successfully
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 97.3 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.
- test_goal_loop.py called 'python' but only 'python3' exists on system1 minute
- Install time
- 3 minutes
- Cold machine to finish
- 6 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- pytest tests/ --tb=short -q exited 0, 482 passed, 100 subtests passed in 12.12s
- Model tokens used
- 54,479
- Exact commit tested
- 0dcafa2ae053
- 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 2, run . The verdict above comes from a different attempt, so read this as one session and not as the current result. 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.
**Other findings:** - The web platform's `next build` requires Node.js >=20.9.0, but only v18.19.1 is available — canno… - The chapter `code.py` scripts need `ANTHROPIC_API_KEY` for real agent execution, but the entire t… - All 17 chapter `code.py` files and 13 legacy `agents/*.py` scripts compile cleanly. tokens used 54,479 All 482 tests pass, 100 subtests pass. Here's the summary: **Error found:** `test_bash_output_keeps_exit_code_when_the_tail_is_trimmed` in `tests/test_goal_lo… **Other findings:** - The web platform's `next build` requires Node.js >=20.9.0, but only v18.19.1 is available — canno… - The chapter `code.py` scripts need `ANTHROPIC_API_KEY` for real agent execution, but the entire t… - All 17 chapter `code.py` files and 13 legacy `agents/*.py` scripts compile cleanly.
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 3 minutes, faster than the median of the 32 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.
- Measured 3 times, so the result is not a one-off.
Of the 33 agent projects Argusic has installed and timed, learn-claude-code was the 11th fastest to reach a running state, and 25 of 33 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 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)
agentagent-developmentai-agentclaudeclaude-codeeducationalllmpythonteachingtutorial
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/learn-claude-code)Questions
- Does learn-claude-code run?
- Yes. learn-claude-code runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test learn-claude-code?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 0dcafa2ae053. 3 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test learn-claude-code?
- The run that produced this verdict cost $0.04: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does learn-claude-code take to install?
- 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 learn-claude-code need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing learn-claude-code?
- 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 learn-claude-code compare with the alternatives?
- Of the 33 agent projects Argusic has installed and timed, learn-claude-code was the 11th fastest to reach a running state, and 25 of 33 reached one at all.
- Where is the evidence for learn-claude-code?
- All 3 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.