buildwithclaude
A single hub to find Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections to extend Claude Code, Claude Desktop, Agent SDK and OpenClaw
Runs with mockssource: GitHubhomepagePythonMITcommit 18e6760b9901
Python, MIT licensed. The project labels itself: claude, claude code, claude code commands, claude skills, cli tool, commands, mcp and mcp server.
buildwithclaude runs, with stand-ins for the services it depends on. An Argusic agent installed it in 2 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The repository installs, builds, and runs: the production web UI on port 3457 returns HTTP 200 for home, subagents, commands, hooks, and skills pages, and the unit and plugin-harness test suites pass; database-backed listings fall back to local content because the container has no real Postgres.
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 84 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.
- DB-backed pages logged 127.0.0.1:5432 connection failures and the server exited after /skills; a local Postgres-protocol stub accepts TCP but postgres-js still times out mid-handshake20 minutes
- web-ui/server.js did not exist at the repo root (standalone output lives at web-ui/.next/standalone/web-ui/server.js)3 minutes
- web-ui unit tests failed under the container Node 18 with 'bad option: --experimental-strip-types'2 minutes
- Install time
- 2 minutes
- Cold machine to finish
- 56 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- PATH=/home/runner/tools/node22/bin:$PATH npm test exited 0, 25 passed / 0 failed; curl -s -o /dev/null -w %{http_code} http://127.0.0.1:3457/ and /subagents /commands /hooks /skills each returned 200
- Model tokens used
- 400,544
- Exact commit tested
- 18e6760b9901
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
\"verified_how\": \"PATH=/home/runner/tools/node22/bin:"'$PATH npm test exited 0, 25 passed / 0 f…
"final_state": "The repository installs, builds, and runs: the production web UI on port 3457 ret…
}
line = "ARGUSIC_RESULT:" + json.dumps(report, ensure_ascii=False, separators=('"',', ':'))
print(line)
PYEOF" in /work/repo
succeeded in 0ms:
2026-11-09T05:13:05.025921Z ERROR codex_core::session: failed to record rollout items: thread 01a1b…
2026-11-09T05:13:05.025976Z ERROR codex_core::session: failed to record rollout items: thread 01a1b…
2026-11-09T05:13:05.026045Z ERROR codex_core::session: failed to record rollout items: thread 01a1b…
tokens used
400,544Replay 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
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Took 2 minutes to install, slower than the median of the 8 comparable projects Argusic has measured.
Of the 9 claude projects Argusic has installed and timed, buildwithclaude was the 6th fastest to reach a running state, and 5 of 9 reached one at all.
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
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 1.28 | |
| Argusic Runner | 1/3 | Runs with mocks | 76.00 | 0.07 |
Topics (from GitHub)
claudeclaude-codeclaude-code-commandsclaude-skillscli-toolcommandsmcpmcp-servermcp-toolsopenclawplugin-marketplacesubagents
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/buildwithclaude)Questions
- Does buildwithclaude run?
- buildwithclaude runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 2 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test buildwithclaude?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 18e6760b9901. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test buildwithclaude?
- The run that produced this verdict cost $1.28: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does buildwithclaude take to install?
- 2 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 buildwithclaude need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing buildwithclaude?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does buildwithclaude compare with the alternatives?
- Of the 9 claude projects Argusic has installed and timed, buildwithclaude was the 6th fastest to reach a running state, and 5 of 9 reached one at all.
- Where is the evidence for buildwithclaude?
- All 2 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.