Yes. claudexor runs. Argusic installed and launched it on a clean machine in 5 minutes, hitting 3 errors on the way, and recorded the session.

How did Argusic test claudexor?

On a fresh, disposable machine, with every command recorded and the repository pinned at commit 529e512f5f11. 2 attempts are recorded, and the full method is on the methodology page.

What did it cost to test claudexor?

The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.

How long does claudexor take to install?

5 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 claudexor need a GPU?

Not to start. Argusic reached a running state on a machine with no GPU.

What goes wrong when installing claudexor?

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.

Where is the evidence for claudexor?

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.

claudexor

Multi-harness control plane for Claude Code, Codex, Cursor, and OpenCode: quota-aware rotation across multiple Claude/Codex subscriptions, shared thread context, and cross-model review.

Runssource: GitHub homepageTypeScriptMITcommit 529e512f5f11

TypeScript, MIT licensed. The project labels itself: agent orchestration, ai agents, ai coding, ai coding assistant, claude code, cli, code review and codex.

claudexor runs. An Argusic agent installed it in 5 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

pnpm install completed, pnpm build succeeded (31 packages in 18s), the CLI runs and reports version 3.9.8, the full test suite passes (350 test files, 4692 tests), canary stories pass (6 files, 50 tests), and typecheck passes (61 tasks)
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 86 of 100 (the mean of this project's run scores).

At a glance

verdict: Runs
Argusic Score: 86 / 100
cost of the verifying run: $0.05 (measured)
recorded runs: 2
last tested: 2026-09-19
stars: 480
forks: 49
open issues: 82
watchers: 1
size: 35 MB
created: 2026-06-05
last push: 2026-09-22

Subject data from GitHub, linked at the top of this page, refreshed 2026-09-23. 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.

Time lost to each failure while testing claudexor, drawn from the recorded run — Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

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 installed but project requires >=20.19.01 minute
pnpm not found (corepack unavailable on Node 18)1 minute
git tag v3.3.7 missing from shallow clone, causing 1 test failure in legacy-writer-claimant.test.ts1 minute

Install time: 5 minutes
Cold machine to finish: 20 minutes
Errors hit and fixed: 3 hit, 3 fixed with no human help
How the result was proved: pnpm test exited 0: 350/353 test files passed, 4692/4702 tests passed; pnpm canary exited 0: 6/6 files passed, 50/50 tests passed; pnpm typecheck 61/61 tasks passed; node packages/cli/dist/cli.js --version returned 3.9.8; node packages/cli/dist/cli.js --help exited 0
Model tokens used: 72,209
Exact commit tested: 529e512f5f11
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.

[ok] fake-context-then-error 3.9.8
    intents: plan, implement, review, verify, explain, audit
    routable: plan, implement, review, verify, explain, audit
    auth sources: readiness-not-reported
    checks: installed:pass, structured_output:pass
All done. Let me compile the final result
exec
/bin/sh -lc 'echo "Start time estimates: node setup ~13:16:40 (~1m), pnpm install ~13:17:30 (~4s), …
 succeeded in 0ms:
Start time estimates: node setup ~13:16:40 (~1m), pnpm install ~13:17:30 (~4s), build ~13:18:24 (~1…
tokens used
72,209

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 5 minutes.
Recovered from all 3 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.
Measured 2 times, so the result is not a one-off.

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 5 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

tested by	attempt	outcome	score	cost USD	when
Argusic Runner	2/3	Runs	100.00	0.05	2026-09-19 13:35 UTC
Argusic Runner	1/3	Runs with mocks	72.00	0.30	2026-09-13 05:41 UTC

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/claudexor.svg)](https://argusic.com/subject/claudexor)

Questions

Does claudexor run?: Yes. claudexor runs. Argusic installed and launched it on a clean machine in 5 minutes, hitting 3 errors on the way, and recorded the session.
How did Argusic test claudexor?: On a fresh, disposable machine, with every command recorded and the repository pinned at commit 529e512f5f11. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test claudexor?: The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does claudexor take to install?: 5 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 claudexor need a GPU?: Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing claudexor?: 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.
Where is the evidence for claudexor?: 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.