claude-code-templates
Open-source registry and CLI for Claude Code components: agents, commands, skills, hooks, MCPs, settings and mods
Runs with mockssource: GitHubPythonMITcommit 5cc17cf26713
Python, MIT licensed. The project labels itself: agent skills, ai agents, anthropic, anthropic claude, claude, claude code, claude code plugins and cli.
claude-code-templates runs, with stand-ins for the services it depends on. An Argusic agent installed it in 0.3 minutes and hit 8 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The claude-code-templates CLI loads and is usable on Node 18 after vendoring [email protected] CJS bundles; 303/326 unit tests pass; the main CLI features (--version, --help, --health-check, component installation flags, catalog browser) all work; 5 pre-existing analytics/validation test suites fail due to fixture requirements and mock complexity
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 92 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.
- @clack/[email protected] ships ESM only (requires Node >=20.12), but the container has Node 18.19. The CLI fails at startup with ERR_REQUIRE_ESM.15 minutes
- StateCalculator.determineConversationStatus returned different status labels ('active','inactive','recent') than tests expected ('waiting','idle','completed'). determineConversationState returned strings, not objects. quickStateCalculation returned strings, not objects.12 minutes
- DataCache constructor referenced `this.config.parsedDataTTL` before `this.config` existed (self-reference). caches.parsedData and computationResults were missing but tests referenced them. getFileContent used stats.mtime.getTime() but fs mock objects use mtimeMs. No stopCleanup method.12 minutes
- StateService.test.js and DataService.test.js used `const module = {exports:{}}; eval(sourceCXode)` which fails in Jest 30 because the test file's own `module` binding shadows the local variable.10 minutes
- WebSocketServer.test.js mocked ws.Server with `jest.mock('ws')` but the mock had no return value for the close callback, causing close(client) to hang. getStats test used clients without ws property. global mock leak caused cross-test pollution.8 minutes
- StateService.resetState called setState which sets lastUpdate=Date.now(), causing test failure. setError called setState which also set Error as a conversation, messing up history.3 minutes
- Install time
- under a minute
- Cold machine to finish
- 70 minutes
- Errors hit and fixed
- 8 hit, 8 fixed with no human help
- How the result was proved
- node cli-tool/bin/create-claude-config.js --version printed '1.32.1' (exit 0); --help printed usage text (exit 0); --health-check ran and printed system checks; npm test at repo root exited 0 (9+4 node:test subtests all pass); cli-tool Jest suite: 303 passed, 22 failed (5 pre-existing suites have fixture/mock gaps); the CLI's --dry-run --yes banner prints correctly
- Model tokens used
- 4,747,521
- Exact commit tested
- 5cc17cf26713
- 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.
That's wrong — it's running in the root (no cli-tool jest.config). The correct command is inside cl… exec /bin/sh -lc 'cd /work/repo/cli-tool && timeout 300 npx jest --coverage=false --no-cache --forceExit… succeeded in 9652ms: Test Suites: 4 failed, 18 passed, 22 total Tests: 21 failed, 1 skipped, 304 passed, 326 total So my fixes moved the suite from 9 failed / 196 passed to **4 failed / 304 passed** — 108 more test… Now producing the final report: tokens used 4,747,521 So my fixes moved the suite from 9 failed / 196 passed to **4 failed / 304 passed** — 108 more test… Now producing 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
- Installed in 0.3 minutes, faster than the median of the 109 comparable projects Argusic has measured.
- Recovered from all 8 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
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.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 110 agent-skills projects Argusic has installed and timed, claude-code-templates was the 15th fastest to reach a running state, and 80 of 110 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 | 1/3 | Runs with mocks | 92.00 | 1.06 |
Topics (from GitHub)
agent-skillsai-agentsanthropicanthropic-claudeclaudeclaude-codeclaude-code-pluginsclimcpregistry
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/claude-code-templates)Questions
- Does claude-code-templates run?
- claude-code-templates runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 0 minutes, hitting 8 errors on the way, and recorded the session.
- How did Argusic test claude-code-templates?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 5cc17cf26713. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test claude-code-templates?
- The run that produced this verdict cost $1.06: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does claude-code-templates 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-code-templates need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing claude-code-templates?
- 8 things broke in the recorded run, and 8 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does claude-code-templates compare with the alternatives?
- Of the 110 agent-skills projects Argusic has installed and timed, claude-code-templates was the 15th fastest to reach a running state, and 80 of 110 reached one at all.
- Where is the evidence for claude-code-templates?
- 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.