Yes. code-mode runs. Argusic installed and launched it on a clean machine in 16 minutes, hitting 3 errors on the way, and recorded the session.

How did Argusic test code-mode?

On a fresh, disposable machine, with every command recorded and the repository pinned at commit e5fdc319bfae. One attempt is recorded, and the full method is on the methodology page.

What did it cost to test code-mode?

The run that produced this verdict cost $0.28: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.

How long does code-mode take to install?

16 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 code-mode need a GPU?

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

What goes wrong when installing code-mode?

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 code-mode?

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.

code-mode

🔌 Plug-and-play library to enable agents to call MCP and UTCP tools via code execution.

Runssource: GitHubTypeScriptMPL-2.0commit e5fdc319bfae

TypeScript, MPL-2.0 licensed. The project labels itself: ai agents, codemode, mcp, model context protocol, toolchain and utcp.

code-mode runs. An Argusic agent installed it in 16 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

TypeScript library @utcp/code-mode builds and passes all 29 tests using [email protected] native sandbox. Python library builds and passes all 17 tests using RestrictedPython sandbox. CLI and MCP bridge both start and respond correctly.
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

verdict: Runs
Argusic Score: 100 / 100
cost of the verifying run: $0.28 (measured)
recorded runs: 1
last tested: 2026-10-06
stars: 1,588
forks: 108
open issues: 4
watchers: 14
size: 0 MB
created: 2025-11-11
last push: 2026-08-25

Subject data from GitHub, linked at the top of this page, refreshed 2026-10-06. 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 code-mode, 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.

[email protected] requires Node.js >=22, container has Node 1810 minutes
Built [email protected] from source; linker missing unversioned .so symlinks (z, uv, brotli, cares, nghttp2, crypto, ssl, icu)8 minutes
Python CodeModeUtcpClient missing abstract close() method2 minutes

Install time: 16 minutes
Cold machine to finish: 17 minutes
Errors hit and fixed: 3 hit, 3 fixed with no human help
How the result was proved: npm test in typescript-library: 1 suite, 29 passed; pytest in python-library: 17 passed; code-mode-cli --help prints all commands; code-mode-mcp responds to MCP initialize + tools/list
Model tokens used: 132,273
Exact commit tested: e5fdc319bfae
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.

    'verified_how': 'npm test in typescript-library: 1 suite, 29 passed; pytest in python-library: …
    'final_state': 'TypeScript library @utcp/code-mode builds and passes all 29 tests using isolate…
}
print(json.dumps(output))
\"" in /work/repo
 succeeded in 0ms:
{"install_succeeded": true, "launch_succeeded": true, "install_minutes": 16.0, "errors": [{"msg": "…
2026-10-06T22:33:39.333458Z ERROR codex_core::session: failed to record rollout items: thread 01a11…
2026-10-06T22:33:39.333528Z ERROR codex_core::session: failed to record rollout items: thread 01a11…
2026-10-06T22:33:39.333558Z ERROR codex_core::session: failed to record rollout items: thread 01a11…
tokens used
132,273

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.
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 MPL-2.0, as reported by its host.

What did not, or is not known

Took 16 minutes to install, slower than the median of the 44 comparable projects Argusic has measured.
Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 45 ai-agents projects Argusic has installed and timed, code-mode was the 35th fastest to reach a running state, and 33 of 45 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.

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	100.00	0.28	2026-10-06 22:33 UTC

Topics (from GitHub)

ai-agents codemode mcp model-context-protocol toolchain utcp

Embed the badge

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

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

Questions

Does code-mode run?: Yes. code-mode runs. Argusic installed and launched it on a clean machine in 16 minutes, hitting 3 errors on the way, and recorded the session.
How did Argusic test code-mode?: On a fresh, disposable machine, with every command recorded and the repository pinned at commit e5fdc319bfae. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test code-mode?: The run that produced this verdict cost $0.28: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does code-mode take to install?: 16 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 code-mode need a GPU?: Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing code-mode?: 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 code-mode compare with the alternatives?: Of the 45 ai-agents projects Argusic has installed and timed, code-mode was the 35th fastest to reach a running state, and 33 of 45 reached one at all.
Where is the evidence for code-mode?: 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.