codexqa
codexqa: 11 local-first Agent Skills for Cursor, Claude Code, Codex & OpenClaw, change impact analysis, AI code review, defect scan, testcase generation, browser replay & RCA.
Runssource: GitHubhomepagePythonApache-2.0commit 783954281fc4
Python, Apache-2.0 licensed. The project labels itself: agent skills, agentskills, ai code review, ai testing, browser automation, change impact analysis, claude code and code analysis.
codexqa runs. An Argusic agent installed it in 14 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The repo installs from a local checkout via npx skills with Playwright Chromium and the @openqa-cn/codexqa CLI in a user prefix; all repository checks pass: check-docs, compose-release-notes, checkout-boundary and inventory-service verifiers, polyglot fixture build, code-wiki 47/47, defect-analyzer full suite, skill-router 120 fixtures, testcase-generator self-checks, and jev-browser 92/92, and an end-to-end dry-run...
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
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.
- codexqa-defect-analyzer npm test failed: AssertionError 'scope_policy must list data/adhoc excludes' because PyYAML was missing, so scope_policy.yaml loaded as {}6 minutes
- npx skills add . --list failed on container Node 18.19.1 (styleText import from node:util, [email protected] requires node >=22.20.0; docs say Node 18+, so container is below tooling bar)5 minutes
- defect-analyzer full scan first failed EACCES on global npm install of closed-source @openqa-cn/codexqa into /usr/local (no root; auto-installer uses npm prefix -g)4 minutes
- jev-browser npm test: 16/92 live Chromium tests failed 'Chromium distribution chrome is not found' (Playwright browser absent, no root for system chrome)3 minutes
- Install time
- 14 minutes
- Cold machine to finish
- 6 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- cd skills/codexqa-jev-browser && npm test exited 0, 92 passed (11 files, incl. 16 live Chromium flows); codexqa index/stats/wiki inputs on /work/repo returned 791 files/4476 nodes/8643 edges and 12 communities; defect-analyzer run_scan.py full --repo /tmp/polyglot-service-fixture --llm-mode dry-run exited 0 with report_scan.json 3 files scanned, 6 findings (P0=1 P1=2 P2=2 P3=1); npx skills add . --skill codexqa-defect-analyzer --agent codex --copy installed to ./.agents/skills
- Model tokens used
- 413,005
- Exact commit tested
- 783954281fc4
- 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 attempt that decided the verdict above. 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.
succeeded in 0ms: # Working with codexqa codexqa is a verification project. Agent-assisted contributions are welcome, but every change must … ## Before changing a skill 1. Read the skill's `SKILL.md` and its examples. 2. State the user problem and acceptance criteria. 3. Add a known-good case and, where possible, a seeded-defect or expected-failure case. 4. Document supported agents, frameworks, environments, and limitations. 5. Run the repository checks before opening a pull request. Never include secrets, customer code, private logs, or personal data. Do not claim that a check pro… tokens used 413,005
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 4 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 Apache-2.0, as reported by its host.
What did not, or is not known
- Took 14 minutes to install, slower than the median of the 95 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 96 agent-skills projects Argusic has installed and timed, codexqa was the 83rd fastest to reach a running state, and 69 of 96 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
Topics (from GitHub)
agent-skillsagentskillsai-code-reviewai-testingbrowser-automationchange-impact-analysisclaude-codecode-analysiscode-reviewcoding-agentcursormanual-testingopenai-codexquality-assurancerequirements-analysisroot-cause-analysis-skillsastsoftware-testingstatic-analysistest-case-generation
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/codexqa)Questions
- Does codexqa run?
- Yes. codexqa runs. Argusic installed and launched it on a clean machine in 14 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test codexqa?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 783954281fc4. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test codexqa?
- The run that produced this verdict cost $0.09: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does codexqa take to install?
- 14 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 codexqa need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing codexqa?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does codexqa compare with the alternatives?
- Of the 96 agent-skills projects Argusic has installed and timed, codexqa was the 83rd fastest to reach a running state, and 69 of 96 reached one at all.
- Where is the evidence for codexqa?
- 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.