humanize
The agent flow system for token maxxing.
Runs with mockssource: GitHubhomepagePythonApache-2.0commit 60cab7e69fbf
Python, Apache-2.0 licensed. The project labels itself: agent, ai agents, claude code, codex, coding agents, flow, harness and infra.
humanize runs, with stand-ins for the services it depends on. An Argusic agent installed it in 2.3 minutes and hit 3 errors on a clean machine with no GPU, and the whole session was recorded.
The hmz package installs cleanly, ruff lint passes, the CLI binary prints valid usage output, and 2600+ unit tests + 145+ integration tests pass against mocked backends; 11 unit test failures are pre-existing environment constraints (Landlock, argv0 path) unrelated to install.
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 72 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.
- 11 unit tests fail: 2 Codex tests expect argv0='codex' but system resolves to '/usr/local/bin/codex'; 9 fencing tests expect Landlock or seccomp support not present on this kernel (kernel lacks ABI 4 and needed LSMs)
- 2 integration tests (test_tui_epics.py) timeout in Textual headless mode
- A few integration tests (test_tui_settings, test_tui_flows, test_tui_monitor) hang in headless environment and could not be tested
- Install time
- 2 minutes
- Cold machine to finish
- 25 minutes
- Errors hit and fixed
- 3 hit, 0 fixed with no human help
- How the result was proved
- uv run hmz --help returned usage info with 3 commands; uv run ruff check src/hmz returned 'All checks passed!'; uv run pytest tests/unit/ -p no:xdist (per-package) returned ~2660 passed
- Model tokens used
- 411,178
- Exact commit tested
- 60cab7e69fbf
- 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.
exec /bin/sh -lc 'export PATH="$HOME/.local/bin:$PATH" && cd /work/repo && echo "=== Summary of all inte… succeeded in 9086ms: === Summary of all integration tests === tests/integration/test_agents_codex.py::test_a_failed_turn_is_a_failure_with_what_codex_said PASSED… ============================== 13 passed in 3.78s ============================== tests/integration/test_agents_kimi.py::test_a_prompt_the_daemon_refuses_is_a_failed_turn_leaving_no… ============================== 4 passed in 4.60s =============================== Now I have complete data. Here is the final analysis: tokens used 411,178 Now I have complete data. Here is the final analysis:
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 2.3 minutes, faster than the median of the 122 comparable projects Argusic has measured.
- Licensed Apache-2.0, 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.
- Hit 3 errors during setup, 3 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 123 agent projects Argusic has installed and timed, humanize was the 32nd fastest to reach a running state, and 81 of 123 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 | 72.00 | 0.12 |
Topics (from GitHub)
agentai-agentsclaude-codecodexcoding-agentsflowharnessinfrallmpythonsystemworkflow
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/humanize)Questions
- Does humanize run?
- humanize runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 2 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test humanize?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 60cab7e69fbf. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test humanize?
- The run that produced this verdict cost $0.12: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does humanize take to install?
- 2.3 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 humanize need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing humanize?
- 3 things broke in the recorded run. Each one, and the time it cost, is listed on this page.
- How does humanize compare with the alternatives?
- Of the 123 agent projects Argusic has installed and timed, humanize was the 32nd fastest to reach a running state, and 81 of 123 reached one at all.
- Where is the evidence for humanize?
- 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.