agent-scripts
Scripts for agents, shared between my repositories.
Runssource: GitHubhomepageShellMITcommit d15557c94fa1
Shell, MIT licensed. The project labels itself: ai agents.
agent-scripts runs. An Argusic agent installed it in 2.5 minutes and hit 4 errors on a clean machine with no GPU, and the whole session was recorded.
All 12 test suites pass; npm install completes with 0 vulnerabilities; Python, Node.js, and Ruby scripts compile and run correctly; browser-tools CLI loads and reports help; docs-list enumerates all docs with metadata checks; no Chrome binary available for browser launch tests
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 95 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.
- Ruby not installed in container; scripts/validate-skills, test-maintainer-orchestrator-policy, and codex-huge-context preflight required it2 minutes
- pyyaml Python package not available (system Python managed by apt, no user pip allowed)0.3 minutes
- No Chrome/Chromium binary available - browser-tools start cannot launch a browser
- Ruby psych C extension (YAML parser) could not compile due to missing libyaml system library
- Install time
- 3 minutes
- Cold machine to finish
- 26 minutes
- Errors hit and fixed
- 4 hit, 3 fixed with no human help
- How the result was proved
- Ran 12 test suites: sync-skills (9 PASS), validate-skills (54 OK), maintainer-orchestrator (1 PASS), codex-huge-context preflight (1 PASS), clawsweeper-status (5 PASS), npm-auth-cache (18/18 pass), npm-auth-login (12/12 pass), npm-auth-shell (4 PASS), mac-release (1 PASS), mac-release-canary (1 PASS), mac-release-assets (1 PASS), mac-release-publication (1 PASS), mac-release-download (1 PASS), mac-release-provider (0 failed assertions), xcode-post-install-smoke (5 OK)
- Model tokens used
- 152,829
- Exact commit tested
- d15557c94fa1
- 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.
}
],
'test_depth': 'tier1_real',
'verified_how': 'Ran 12 test suites: sync-skills (9 PASS), validate-skills (54 OK), maintainer-…
'final_state': 'All 12 test suites pass; npm install completes with 0 vulnerabilities; Python, …
}
print(json.dumps(result))
\"" in /work/repo
succeeded in 0ms:
{"install_succeeded": true, "launch_succeeded": true, "install_minutes": 2.5, "errors": [{"msg": "R…
tokens used
152,829Replay 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.
- Installed in 2.5 minutes, faster than the median of the 35 comparable projects Argusic has measured.
- 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
- Hit 4 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 36 ai-agents projects Argusic has installed and timed, agent-scripts was the 8th fastest to reach a running state, and 26 of 36 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 2.5 minutes after the clone.
Run history
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/agent-scripts)Questions
- Does agent-scripts run?
- Yes. agent-scripts runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test agent-scripts?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit d15557c94fa1. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test agent-scripts?
- The run that produced this verdict cost $0.21: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does agent-scripts take to install?
- 2.5 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-scripts need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing agent-scripts?
- 4 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does agent-scripts compare with the alternatives?
- Of the 36 ai-agents projects Argusic has installed and timed, agent-scripts was the 8th fastest to reach a running state, and 26 of 36 reached one at all.
- Where is the evidence for agent-scripts?
- 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.