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 9 minutes and hit 1 error on a clean machine with no GPU, and the whole session was recorded.
The codex-instruct.py CLI v0.6.0 installs, deploys overlay/unrestricted/contract prompts into Codex config directories with timestamped backups and manifest transactions, reports accurate multi-field status, and uninstalls with full rollback, verified by 1198 passing tests and a complete end-to-end deploy/status/uninstall workflow on a real config directory.
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 80 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.
- GUI npm test fails: @tailwindcss/oxide native binary missing for linux-x64-gnu — cannot build/test the Tauri/React frontend2 minutes
- Install time
- 9 minutes
- Cold machine to finish
- 11 minutes
- Errors hit and fixed
- 1 hit, 0 fixed with no human help
- How the result was proved
- pytest tests/ passed 1198, 27 skipped; python3 codex-instruct.py --version returned 'codex-instruct.py 0.6.0'; end-to-end deploy to /tmp/test-codex verified config.toml gains model_instructions_file = ./gpt-overlay.md, gpt-overlay.md is written, manifest appears, status reports 'active'; subsequent --uninstall restores original config and removes MD/manifest
- Model tokens used
- 40,516
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
now=$(date +%s) echo "Wall seconds elapsed: $((now - start_time))" # But that'"'s not right. Let me instead read the start time from the file stat -c %Y /work/repo/pyproject.toml" in /work/repo succeeded in 0ms: Wall seconds elapsed: 624 1790741160 Here's a summary of everything I did and the final report. 2026-09-30T04:16:45.077545Z ERROR codex_core::session: failed to record rollout items: thread 01a0f… tokens used 40,516 Here's a summary of everything I did and 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
- Reached a running state on a clean machine, with the session recorded.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Took 9 minutes to install, slower than the median of the 26 comparable projects Argusic has measured.
- Hit 1 error during setup, 1 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 27 cli projects Argusic has installed and timed, codex-keysmith was the 22nd fastest to reach a running state, and 25 of 27 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 9 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
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.
[](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 9 minutes, hitting 1 error 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. One attempt is 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 $0.04: 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?
- 9 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?
- 1 thing broke in the recorded run. Each one, and the time it cost, is listed on this page.
- How does codex-keysmith compare with the alternatives?
- Of the 27 cli projects Argusic has installed and timed, codex-keysmith was the 22nd fastest to reach a running state, and 25 of 27 reached one at all.
- Where is the evidence for codex-keysmith?
- 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.