lazycodex
The one and only agent harness for complex codebases. Project memory, planning, execution, and verified completion inside Codex.
Runs with mockssource: GitHubhomepageTypeScriptMITcommit 8d16365e3f21
TypeScript, MIT licensed. The project labels itself: ai, ai agents, claude, claude code, cli, codex, developer tools and lazy.
lazycodex runs, with stand-ins for the services it depends on. An Argusic agent installed it in 8.5 minutes and hit 3 errors on a clean machine with no GPU, and the whole session was recorded.
LazyCodex plugin (omo 5.0.0-beta.90) is installed, enabled, and verified via the Codex marketplace path with 9/9 repo tests passing, 288/319 plugin tests passing, 27 skills, 21 hooks, and 4 components (rules, comment-checker, lsp, telemetry) responding to CLI commands.
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 85.3 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 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.
- npx lazycodex-ai install fails: oh-my-openagent-linux-x64 platform binary package lacks "type": "module" (Node 18 needs it for ES module imports)3 minutes
- npx lazycodex-ai install fails at final step: npm 9.x doesn't support workspace:* protocol (plugin source uses npm workspaces)3 minutes
- Plugin tests: 30/319 fail because @oh-my-opencode/shared-skills is not resolvable (npm install failed on workspace deps)1 minute
- Install time
- 9 minutes
- Cold machine to finish
- 37 minutes
- Errors hit and fixed
- 3 hit, 2 fixed with no human help
- How the result was proved
- cd /work/repo && node --test test/*.test.mjs exited 0, 9/9 pass; cd /home/runner/.codex/plugins/cache/sisyphuslabs/omo/5.0.0-beta.90 && npm test: 288/319 pass; codex plugin list shows omo@sisyphuslabs installed, enabled, 27 skills, 21 hooks; component CLIs (rules, comment-checker, lsp, telemetry) all respond to --help
- Model tokens used
- 303,797
- Exact commit tested
- 8d16365e3f21
- 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
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
rules: OK
comment-checker: OK
lsp: OK
telemetry: OK
succeeded in 15018ms:
# tests 319 # pass 288 # fail 30 ---27 skills---21 hooks
Here is the final report for the LazyArgusic Agent repository.
<pre style="display:none">ARGUSIC_RESULT:{"install_succeeded":true,"launch_succeeded":true,"install…
tokens used
303,797
Here is the final report for the LazyArgusic Agent repository.
<pre style="display:none">ARGUSIC_RESULT:{"install_succeeded":true,"launch_succeeded":true,"install…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
- Licensed MIT, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Took 8.5 minutes to install, slower than the median of the 66 comparable projects Argusic has measured.
- Hit 3 errors 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 67 ai projects Argusic has installed and timed, lazycodex was the 48th fastest to reach a running state, and 51 of 67 reached one at all.
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 with mocks | 85.33 | 0.25 |
Topics (from GitHub)
aiai-agentsclaudeclaude-codeclicodexdeveloper-toolslazylazycodexoh-my-openagentomoopenaiorchestrationtypescript
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/lazycodex)Questions
- Does lazycodex run?
- lazycodex runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 9 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test lazycodex?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 8d16365e3f21. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test lazycodex?
- The run that produced this verdict cost $0.25: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does lazycodex take to install?
- 8.5 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 lazycodex need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing lazycodex?
- 3 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 lazycodex compare with the alternatives?
- Of the 67 ai projects Argusic has installed and timed, lazycodex was the 48th fastest to reach a running state, and 51 of 67 reached one at all.
- Where is the evidence for lazycodex?
- 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.