Does agent-purge run?

Yes. agent-purge runs. Argusic installed and launched it on a clean machine in 5 minutes, hitting 2 errors on the way, and recorded the session.

How did Argusic test agent-purge?

On a fresh, disposable machine, with every command recorded and the repository pinned at commit 629494c706b6. One attempt is recorded, and the full method is on the methodology page.

What did it cost to test agent-purge?

The run that produced this verdict cost $0.06: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.

How long does agent-purge 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 agent-purge need a GPU?

Not to start. Argusic reached a running state on a machine with no GPU.

What goes wrong when installing agent-purge?

2 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.

Where is the evidence for agent-purge?

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.

agent-purge

One persona, many coding agents. Replace or inject system prompts across codex, claude, opencode, grok, omp, hermes, pi, zcode - with a local web console.

Runssource: GitHubJavaScriptMITcommit 629494c706b6

JavaScript, MIT licensed. The project labels itself: claude code, codex, coding agent, opencode, pi and system prompt.

agent-purge runs. An Argusic agent installed it in 5 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

agent-purge CLI is functional from source checkout: all 8 subcommands (help, status, ls, use, mode, matrix, detect, web) work correctly, web server serves UI on port 7788 returning HTTP 200, and 70 test assertions pass. Added missing neutral.md persona template so first-run persona auto-generation works.
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

verdict: Runs
Argusic Score: 100 / 100
cost of the verifying run: $0.06 (measured)
recorded runs: 1
last tested: 2026-10-27
stars: 543
forks: 428
open issues: 0
watchers: 2
size: 0 MB
created: 2026-10-25
last push: 2026-10-26

Subject data from GitHub, linked at the top of this page, refreshed 2026-10-27. 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.

Time lost to each failure while testing agent-purge, drawn from the recorded run — Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

Missing lib/templates/personas/ directory - neutral.md starter persona not auto-generated on first run3 minutes
npm install -g requires root permissions (EACCES)1 minute

Install time: 5 minutes
Cold machine to finish: 4 minutes
Errors hit and fixed: 2 hit, 2 fixed with no human help
How the result was proved: npm test exited 0 (70 assertions passed); node bin/agent-purge.mjs web served HTTP 200; node bin/agent-purge.mjs --help printed usage; node bin/agent-purge.mjs codex --dry-run output correct launch command; node bin/agent-purge.mjs status printed 12 harnesses
Model tokens used: 211,809
Exact commit tested: 629494c706b6
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.

- Armor benchmarks require live model API keys (`--base`/`--key`/`--model`)
- Installing to actual coding agent harnesses (e.g., pi, opencode, claude) requires them to be inst…
exec
/bin/sh -lc "cat > /tmp/argus_result.json << 'EOF'
{\"install_succeeded\": true, \"launch_succeeded\": true, \"install_minutes\": 5, \"errors\": [{\"m…
}
EOF
echo "ARGUSIC_RESULT: $(cat /tmp/argus_result.json)"' in /work/repo
 succeeded in 0ms:
}
tokens used
211,809

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 2 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.

What did not, or is not known

Took 5 minutes to install, slower than the median of the 19 comparable projects Argusic has measured.
Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 20 claude-code projects Argusic has installed and timed, agent-purge was the 12th fastest to reach a running state, and 19 of 20 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 5 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	1/3	Runs	100.00	0.06	2026-10-27 08:33 UTC

Topics (from GitHub)

claude-code codex coding-agent opencode pi system-prompt

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/agent-purge.svg)](https://argusic.com/subject/agent-purge)

Questions

Does agent-purge run?: Yes. agent-purge runs. Argusic installed and launched it on a clean machine in 5 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test agent-purge?: On a fresh, disposable machine, with every command recorded and the repository pinned at commit 629494c706b6. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test agent-purge?: The run that produced this verdict cost $0.06: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does agent-purge 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 agent-purge need a GPU?: Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing agent-purge?: 2 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 agent-purge compare with the alternatives?: Of the 20 claude-code projects Argusic has installed and timed, agent-purge was the 12th fastest to reach a running state, and 19 of 20 reached one at all.
Where is the evidence for agent-purge?: 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.