HERO-Anti-OverDefense
HERO = Hashing · Edge cases · Rubrics · Overbuild, the four shapes coding agents over-defend in. A paste-in contract that stops them. Works with Claude Code, Codex, Antigravity, Cursor, Copilot, Windsurf, Gemini CLI.
Runs with mockssource: GitHubPythonMITcommit 92686ca5c7dc
Python, MIT licensed. The project labels itself: agents md, ai agents, antigravity, claude code, claude md, codex, coding agent and cursor.
HERO-Anti-OverDefense runs, with stand-ins for the services it depends on. 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.
Python virtual environment created with websockets 15.0.1; the Goal Pulse CLI parses arguments and all 18 behavioral tests pass, including real Unix WebSocket transport tests without a Codex daemon
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
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
- 1 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- `python3 -m venv .venv && .venv/bin/pip install websockets==15.0.1` succeeded; `.venv/bin/python -m unittest discover -s tests -p test_goal_pulse.py -v` exited 0 with 18/18 passed; `.venv/bin/python skills/goal-pulse/scripts/goal_pulse.py --help` printed the usage banner
- Model tokens used
- 33,343
- Exact commit tested
- 92686ca5c7dc
- 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.
usage: goal_pulse.py [-h] {start,status,stop,tick,run} ...
Short efficiency reminders to an existing active Goal; never start/resume one.
positional arguments:
{start,status,stop,tick,run}
options:
-h, --help show this help message and exit
=== Python version ===
Python 3.12.3
All 18 tests pass, CLI help works, no errors encountered. Here's the final assessment:
tokens used
33,343
All 18 tests pass, CLI help works, no errors encountered. Here's the final assessment: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 4 comparable projects Argusic has measured.
- Nothing broke on the way: zero errors between clone and running.
- 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.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 5 agents-md projects Argusic has installed and timed, HERO-Anti-OverDefense was the 3rd fastest to reach a running state, and 2 of 5 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 | 0.02 |
Topics (from GitHub)
agents-mdai-agentsantigravityclaude-codeclaude-mdcodexcoding-agentcursorgemini-cligithub-copilotllmprompt-engineeringwindsurf
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/hero-anti-overdefense)Questions
- Does HERO-Anti-OverDefense run?
- HERO-Anti-OverDefense runs, with mocks standing in for external services. 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 HERO-Anti-OverDefense?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 92686ca5c7dc. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test HERO-Anti-OverDefense?
- 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 HERO-Anti-OverDefense 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 HERO-Anti-OverDefense need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing HERO-Anti-OverDefense?
- Nothing did, in the recorded run: zero errors between clone and running.
- How does HERO-Anti-OverDefense compare with the alternatives?
- Of the 5 agents-md projects Argusic has installed and timed, HERO-Anti-OverDefense was the 3rd fastest to reach a running state, and 2 of 5 reached one at all.
- Where is the evidence for HERO-Anti-OverDefense?
- 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.