humanizer
Agent skill that removes signs of AI-generated writing from text
Could not verifysource: GitHubPythonMITcommit 225a6f39ac85
Python, MIT licensed. The project labels itself: agent skills, ai humanizer, ai writing, chatgpt, claude, claude code, codex and cursor.
Argusic could not get humanizer running. An Argusic agent installed it in 2 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
The Humanizer skill package passes all three CI validation checks: the Python package validator reports the v3.1.0 package is valid, the Skills CLI discovers the skill and lists it correctly, and the Claude plugin marketplace validator passes. The skill was also successfully installed to ~/.agents/skills/humanizer/.
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 80 of 100 (the mean of this project's run scores).
At a glance
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.
- Install time
- 2 minutes
- Cold machine to finish
- 3 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- python3 scripts/validate-package.py exited 0 ('Humanizer package v3.1.0 is valid'); npx [email protected] add . --list showed 'Found 1 skill' and listed humanizer; claude plugin validate . --strict exited 0 ('Validation passed')
- Model tokens used
- 38,804
- Exact commit tested
- 225a6f39ac85
- 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
- Whether it works at all
- this run verified nothing, so this page makes no claim either way
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
echo \"Current: "'$(date +%s)"' in /work/repo succeeded in 0ms: Current epoch: 1791271590 Log file created around Oct 6, 07:24:31 UTC That's roughly epoch 1791271471 (approx) So elapsed approx 107 seconds = 1 minutes 1791271471 Current: 1791271590 All validations pass cleanly with no fixes needed. The package is well-formed out of the box. tokens used 38,804 All validations pass cleanly with no fixes needed. The package is well-formed out of the box.
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 2 minutes, faster than the median of the 37 comparable projects Argusic has measured.
- Nothing broke on the way: zero errors between clone and running.
- 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
- An agent with no time limit did not get it running.
Of the 38 agent-skills projects Argusic has installed and timed, humanizer was the 13th fastest to reach a running state, and 27 of 38 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 | 2/3 | Unverified | 80.00 | 0.02 | |
| Argusic Runner | 1/3 | Unverified | 80.00 | 0.04 |
Topics (from GitHub)
agent-skillsai-humanizerai-writingchatgptclaudeclaude-codecodexcursorhumanize-ai-texthumanizerllmprompt-engineeringwriting-tools
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/humanizer)Questions
- Does humanizer run?
- Argusic could not verify that humanizer runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test humanizer?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 225a6f39ac85. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test humanizer?
- The run that produced this verdict cost $0.02: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does humanizer take to install?
- 2 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 humanizer need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing humanizer?
- Nothing did, in the recorded run: zero errors between clone and running.
- How does humanizer compare with the alternatives?
- Of the 38 agent-skills projects Argusic has installed and timed, humanizer was the 13th fastest to reach a running state, and 27 of 38 reached one at all.
- Where is the evidence for humanizer?
- 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.