codex-plusplus
Codex++ tweak system for the Codex desktop app
Not yet verifiedsource: GitHubJavaScriptMITcommit bf81723554be
JavaScript, MIT licensed.
codex-plusplus has not been verified yet.
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 13.3 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 most recent recorded attempt, which did not reach a 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.
- Project declares macOS-only Swift package (platforms .macOS(.v14), AppKit/Security imports) and container is Ubuntu with no swift toolchain and no root30 minutes
- Node v18.19.1 test crash: Object.groupBy is not a function in Tests/native-trace.test.mjs5 minutes
- Node v18.19.1 test crash: crypto is not defined in Tests/sidebar-adapter.test.mjs4 minutes
- Install time
- 45 minutes
- Cold machine to finish
- 3 minutes
- Errors hit and fixed
- 3 hit, 2 fixed with no human help
- How the result was proved
- node --test Tests/*.test.mjs returned exit 0: 129 tests total, 117 passed, 12 skipped (pre-existing, need ChatGPT vendor/macOS), 0 failed; also reran the identical suite under Node v22.23.3 with 117/12/0 to confirm the two Node-18 fixes preserve behavior on current Node
- Model tokens used
- 134,588
- Exact commit tested
- bf81723554be
- 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.
**Summary of what I found and did:** - Repo is **Argusic Agent++ 2.0.0**, a macOS-only Swift menu-bar helper (`Package.swift` declares `… - The project nevertheless ships a sizable **cross-platform Node test suite**; CI runs `node --test… 1. `Tests/native-trace.test.mjs` — `Object.groupBy` (Node ≥21) → replaced with a plain-loop equiv… 2. `Tests/sidebar-adapter.test.mjs` — bare global `crypto` (Node ≥19) → `globalThis.crypto ?? web… - After fixes: **`node --test Tests/*.test.mjs` exits 0 — 129 tests, 117 pass, 12 skipped, 0 fail**… exec /bin/sh -lc 'echo "placeholder"' in /work/repo succeeded in 0ms: placeholder tokens used 134,588
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.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Did not run | 13.33 | 0.03 |
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/codex-plusplus)Questions
- Does codex-plusplus run?
- codex-plusplus has not been fully verified yet. No recorded run has produced a verdict yet.
- How did Argusic test codex-plusplus?
- On a fresh, disposable machine, with every command recorded. One attempt is recorded, and the full method is on the methodology page.
- Where is the evidence for codex-plusplus?
- 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.