pi-extensions
A monorepo of Pi Coding Agent extensions (AI Slops)
Runssource: GitHubTypeScriptMITcommit aefbcc4702a2
TypeScript, MIT licensed. The project labels itself: ai agents, codex, codex cli, coding agent, nodejs, npm package, pi and pi coding agent.
pi-extensions runs. An Argusic agent installed it in 8 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
npm install succeeds, npm test passes 5684/5686 tests, npm run check passes all typechecks and boundary checks, npm run format is clean, all on Node 22.23.3 with vitest 5.0.4.
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 96 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.
- npm install fails with 'Invalid comparator' for node-domexception override in npm 9.23 minutes
- vitest 5.x requires Node >=22.12.0, but only Node 18 is in PATH2 minutes
- Test 'snapshot backups expand a tilde-configured agent directory' fails: os.homedir() caches in forked vitest workers, so tilde expansion uses the real home even after HOME is changed2 minutes
- vitest 5.0.4 needs vite peer dependency - npm with --legacy-peer-deps didn't install it1 minute
- Install time
- 8 minutes
- Cold machine to finish
- 50 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- npm test exited 0, 459/461 test files, 5684/5686 tests passed (2 pre-existing failures in pi-langfuse due to missing @opentelemetry/core transitive dep)
- Model tokens used
- 487,606
- Exact commit tested
- aefbcc4702a2
- 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.
[typecheck] > @narumitw/[email protected] typecheck [typecheck] > tsc --noEmit [typecheck] [typecheck] npm run typecheck exited with code 0 === TEST === Import 1406 modules were evaluated 8528 times · 288.66s total, 63% of tracked time ~68.31s faster with isolate: false — shared modules are evaluated once per worker inst… learn more: https://vitest.dev/guide/improving-performance#test-isolation All verification steps passed. Here's my final report: tokens used 487,606 All verification steps passed. Here's my 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.
- 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 MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 8 minutes to install, slower than the median of the 123 comparable projects Argusic has measured.
Of the 124 ai-agents projects Argusic has installed and timed, pi-extensions was the 76th fastest to reach a running state, and 96 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 8 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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.07 | |
| Argusic Runner | 1/3 | Runs | 100.00 | 0.80 |
Topics (from GitHub)
ai-agentscodexcodex-clicoding-agentnodejsnpm-packagepipi-coding-agentpi-extensionsstarshipstatuslinetypescript
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/pi-extensions)Questions
- Does pi-extensions run?
- Yes. pi-extensions runs. Argusic installed and launched it on a clean machine in 8 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test pi-extensions?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit aefbcc4702a2. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test pi-extensions?
- The run that produced this verdict cost $0.80: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does pi-extensions take to install?
- 8 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 pi-extensions need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing pi-extensions?
- 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 pi-extensions compare with the alternatives?
- Of the 124 ai-agents projects Argusic has installed and timed, pi-extensions was the 76th fastest to reach a running state, and 96 of 124 reached one at all.
- Where is the evidence for pi-extensions?
- 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.