codex-keysmith

Versioned Codex instruction deployment with preview, ownership manifests, hook isolation, scenario evaluation, and recovery.

Runssource: GitHubhomepagePythonMITcommit c4d3f4806788

Python, MIT licensed. The project labels itself: cli, codex, codex cli, configuration management, developer tools, local first, prompt engineering and python.

codex-keysmith runs. An Argusic agent installed it in 2 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

The codex-keysmith CLI version 0.6.0 reports correctly, deploys an instruction overlay into an isolated Codex config dir (config, managed MD, manifest) and cleanly uninstalls it restoring the original config, and both test suites pass (1198 pytest + 169 GUI vitest) with the GUI frontend building 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 90 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
90 / 100
cost of the verifying run
$0.03 (measured)
recorded runs
2
last tested
stars
4,811
forks
741
open issues
3
watchers
9
size
24 MB
created
last push

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.

Time lost to each failure while testing codex-keysmith, 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.

  • pip install --user blocked by PEP 668 externally-managed-environment1 minute
  • gui npm test failed: MODULE_NOT_FOUND @tailwindcss/oxide/tailwindcss-oxide.linux-x64-gnu.node (npm 9 skipped the platform optional dep on this musl libc host)1 minute
Install time
2 minutes
Cold machine to finish
7 minutes
Errors hit and fixed
2 hit, 2 fixed with no human help
How the result was proved
python3 codex-instruct.py --version printed 'codex-instruct.py 0.6.0'; on mock dir /tmp/ks-dotcodex: --status exit 0 (not-installed/ready), --dry-run exit 0, --yes deploy exit 0 (config.toml gained model_instructions_file="./gpt-overlay.md", manifest JSON written), post-deploy --status showed active/healthy, --uninstall --yes exit 0 restored the original config and archived the manifest; python3 -m pytest -q: 1198 passed, 27 skipped; cd gui && npm test: 12 files, 169 passed; cd gui && npm run build: vite build succeeded with dist/ emitted.
Model tokens used
110,525
Exact commit tested
c4d3f4806788
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 1, 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.

                         [--scaffold-list] [--scaffold-uninstall PACK]
                         [--workspace-root WORKSPACE_ROOT]
                         [--pack-dir PACK_DIR] [--force]
Argusic Agent MD 指令文件部署脚本
Everything is verified. Cleaning up the test venv and converting the gui build artifacts. Final che…
2026-11-08T01:22:20.659557Z ERROR codex_core::tools::router: error=exec_command failed: CreateProce…
exec
/bin/sh -lc 'ls /tmp/ks-dotcodex >/dev/null && echo "scratch dir retained for reference"' in /work/…
 succeeded in 0ms:
scratch dir retained for reference
tokens used
110,525

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 2 minutes, faster than the median of the 123 comparable projects Argusic has measured.
  • Recovered from all 2 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.

Of the 124 cli projects Argusic has installed and timed, codex-keysmith was the 37th fastest to reach a running state, and 112 of 124 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 2 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 byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs100.000.03
Argusic Runner1/3Runs80.000.04

Topics (from GitHub)

clicodexcodex-cliconfiguration-managementdeveloper-toolslocal-firstprompt-engineeringpython

Embed the badge

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

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

Questions

Does codex-keysmith run?
Yes. codex-keysmith runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test codex-keysmith?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit c4d3f4806788. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test codex-keysmith?
The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does codex-keysmith 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 codex-keysmith need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing codex-keysmith?
2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does codex-keysmith compare with the alternatives?
Of the 124 cli projects Argusic has installed and timed, codex-keysmith was the 37th fastest to reach a running state, and 112 of 124 reached one at all.
Where is the evidence for codex-keysmith?
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.

Discussion