@scaling-group/run-circle-packing-smoke
AUse when a fast end-to-end smoke run is needed for the Eve loop development, will run on circle packing task.
Install
agr install @scaling-group/run-circle-packing-smoke --target claudeWrites 1 file into .claude/skills/, pinned to git-c8537720.
- .claude/skills/run-circle-packing-smoke/SKILL.md
Document
name: run-circle-packing-smoke description: "Use when a fast end-to-end smoke run is needed for the Eve loop development, will run on circle packing task."
If you want to test with the circle packing task (usually when you are implementing Eve), run the following command from the repository root. You don't need to look into the py or yaml file, just run it.
uv run python -m scaling_evolve.algorithms.eve.runner --config-name=circle_packing.smoke
This uses configs/eve/driver/codex_smoke.yaml. It is a runtime validation entrypoint,
not a quality benchmark. Use circle_packing without the .smoke suffix for the
full max-driver run.
If you want to test with your own task (usually when you are using Eve loop for downstream tasks), you should change the config name accordingly. You may refer to other skills or confirm with the user.
Trustgrade A
- passBody integrity
Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.
- passType matchnot applicable to this artifact type
Whether the artifact is really the kind of thing its metadata claims it is.
- passFreshness
How long since the source repository was last pushed to.
- passPrompt injection
Scans the artifact's own text for instructions aimed at your agent rather than at you.
- passLicense
Whether the source repository declares an SPDX license permissive enough to redistribute.
How the grade is calculated
Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:
- Aevery check passed
- Bone warning
- Ctwo warnings
- Dprompt injection or body integrity failed, or three warnings
- Fone of those failed, and something else is wrong
These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.
Versions
git-c8537720090c2026-07-31