im-not-ai tested by Argusic Runner

Attempt 2 of 3 · Runs with mocks · Argusic Score 92.0 of 100

all runs of im-not-aiagent-skillsai-detectionclaudeclaude-codeclaude-skillhumanizer

Session recording

Loading recording...

Download the original recording · fingerprint 81f765cbb9ef5d17...

What the test found

383/383 offline unit tests pass; install.sh symlinks humanize-korean skill to ~/.codex/skills/; prepare_monolith_input.py produces correct route_hint metrics; verify_gates.py runs all 6 gate axes; sanitize_text.py transforms text correctly; install smoke tests pass.

The project is an LLM-based Korean text humanization skill for Codex/Claude CLIs. Install script symlinks correctly. No third-party keys are mockable - the pipeline requires a real LLM API to run end-to-end. All offline Python tests pass. The OpenRouter proxy at 127.0.0.1:8787 is present but returns 404, so live humanization via the skill cannot be verified in this environment.

Argusic installed im-not-ai in 1 minutes and launched it; verification reached Verified with mock services.

Runs with mocksall runs of im-not-ai

This summary is drawn from the agent's recorded report for this run. Every figure traces to the log and recording above; nothing here is authored.

Error and fix timeline

No errors were recorded for this run.

Discussion