prime-agent
A self-improving RLM agent for coding workflows and long-running autonomous tasks.
Runs with mockssource: GitHubTypeScriptMITcommit e260085dd8f7
TypeScript, MIT licensed.
prime-agent runs, with stand-ins for the services it depends on. An Argusic agent installed it in 5 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
npm install succeeds, npm run build succeeds, npm run check passes, all 4 package test suites pass: agent (66/66), ai (1012/1012 across two runs), tui (538/538), coding-agent (~3200+/3200+ in serial batches), and prime-agent CLI --version prints 0.9.6
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 92 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.
- Node.js 18.19.1 too old (requires >=22.8.0)2 minutes
- uv not installed - Python kernel bootstrap failed1 minute
- catalog assets not generated (models.bundled.json missing)1 minute
- packages/ai/test/stream.test.ts hangs when run with other ai tests due to parallel provider test contention1 minute
- coding-agent test suite hangs in large parallel batches (parallel test file contention from daemon socket/process tests)
- Install time
- 5 minutes
- Cold machine to finish
- 55 minutes
- Errors hit and fixed
- 5 hit, 5 fixed with no human help
- How the result was proved
- npm run build exited 0; npm run check passed; packages/agent/agent/test/agent.test.ts 66 passed; packages/ai 503+509=1012 passed; packages/tui 538 passed; packages/coding-agent ~3200+ passed across 190+ files in batched runs; dist/cli.js --version returned 0.9.6
- Model tokens used
- 603,663
- Exact commit tested
- e260085dd8f7
- 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.
✓ test/semaphore.test.ts > Semaphore > hands permits to waiters in FIFO order 1ms
✓ test/semaphore.test.ts > Semaphore > a queued waiter aborts out of the queue without consuming a…
✓ test/semaphore.test.ts > Semaphore > rejects immediately if the signal is already aborted 0ms
Test Files 1 passed (1)
Tests 6 passed (6)
Start at 23:12:41
Duration 324ms (transform 54ms, setup 0ms, import 72ms, tests 34ms, environment 0ms)
Let me now compile the final report. I've tested extensively. Let me get final counts on what has b…
2026-09-25T23:12:50.793480Z ERROR codex_core::session: failed to record rollout items: thread 01a0d…
tokens used
603,663
Let me now compile the final report. I've tested extensively. Let me get final counts on what has b…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
- Installed in 5 minutes, faster than the median of the 6 comparable projects Argusic has measured.
- Recovered from all 5 errors without a human stepping in, which says the failures are documented well enough to solve.
- 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.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 7 TypeScript projects Argusic has installed and timed, prime-agent was the 3rd fastest to reach a running state, and 5 of 7 reached one at all.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.81 |
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/prime-agent)Questions
- Does prime-agent run?
- prime-agent runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 5 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test prime-agent?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit e260085dd8f7. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test prime-agent?
- The run that produced this verdict cost $0.81: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does prime-agent take to install?
- 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 prime-agent need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing prime-agent?
- 5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does prime-agent compare with the alternatives?
- Of the 7 TypeScript projects Argusic has installed and timed, prime-agent was the 3rd fastest to reach a running state, and 5 of 7 reached one at all.
- Where is the evidence for prime-agent?
- 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.