cheap-ag runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 7 minutes, hitting 2 errors on the way, and recorded the session.

How did Argusic test cheap-ag?

On a fresh, disposable machine, with every command recorded and the repository pinned at commit d4a8a52b9bb5. One attempt is recorded, and the full method is on the methodology page.

What did it cost to test cheap-ag?

The run that produced this verdict cost $0.07: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.

How long does cheap-ag take to install?

7 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 cheap-ag need a GPU?

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

What goes wrong when installing cheap-ag?

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 cheap-ag?

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.

cheap-ag

50x your Claude usage with cheap-ag. Opus plans, a dirt-cheap model writes every line, and tests decide what ships. Your $20 plan stops hitting limits. One MCP server for Claude Code.

Runs with mockssource: GitHubTypeScriptMITcommit d4a8a52b9bb5

TypeScript, MIT licensed. The project labels itself: agentic coding, ai agents, anthropic, cheap llm, claude, claude code, claude code hooks and claude code plugin.

cheap-ag runs, with stand-ins for the services it depends on. An Argusic agent installed it in 7 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

npm install, TypeScript build, and all 392 tests pass on Linux x86_64 with Node v22.23.4, using a compiled lsof replacement and no API keys.
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

verdict: Runs with mocks
Argusic Score: 92 / 100
cost of the verifying run: $0.07 (measured)
recorded runs: 1
last tested: 2026-11-02
stars: 205
forks: 0
open issues: 0
watchers: 0
created: -
last push: -

Subject data from GitHub, linked at the top of this page. 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 cheap-ag, 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.

Node.js v18.19.1 < required >=20.11.12 minutes
lsof binary not found in container (ENOENT)2 minutes

Install time: 7 minutes
Cold machine to finish: 7 minutes
Errors hit and fixed: 2 hit, 2 fixed with no human help
How the result was proved: npm test exited 0: 27 test files passed, 392 tests passed, 5 skipped
Model tokens used: 51,877
Exact commit tested: d4a8a52b9bb5
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

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 2026-11-02, 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.

 RUN  v5.0.4 /work/repo
cheapag-shutdown: stdin end
cheapag-shutdown: exit handler, stopping opencode
 Test Files  27 passed | 1 skipped (28)
      Tests  392 passed | 5 skipped (397)
   Start at  10:03:51
   Duration  71.33s (tests 98%, import 1%)
=== Done ===
Everything is verified. Here's the summary:
tokens used
51,877
Everything is verified. Here's the summary:

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

Recovered from all 2 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.
Took 7 minutes to install, slower than the median of the 25 comparable projects Argusic has measured.
Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 26 agentic-coding projects Argusic has installed and timed, cheap-ag was the 19th fastest to reach a running state, and 19 of 26 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	92.00	0.07	2026-11-02 10:05 UTC

Embed the badge

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

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

Questions

Does cheap-ag run?: cheap-ag runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 7 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test cheap-ag?: On a fresh, disposable machine, with every command recorded and the repository pinned at commit d4a8a52b9bb5. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test cheap-ag?: The run that produced this verdict cost $0.07: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does cheap-ag take to install?: 7 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 cheap-ag need a GPU?: Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing cheap-ag?: 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 cheap-ag compare with the alternatives?: Of the 26 agentic-coding projects Argusic has installed and timed, cheap-ag was the 19th fastest to reach a running state, and 19 of 26 reached one at all.
Where is the evidence for cheap-ag?: 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.