incubate — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited incubate (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Mad House project lifecycle manager. Every project in the lab has a stage and a type - no rigid gates, just honest tracking of where something is.
The user wants to: $ARGUMENTS
| Command | What it does |
|---|---|
new <name> [--type TYPE] [--desc "..."] | Create a new lab project |
list [--all] | Show active incubations (--all includes archived) |
stage <name> <stage> | Move to: concept, prototype, building, shipped, maintained, archived |
promote <name> [--org ORG] [--public] | Create GitHub repo from lab project |
ship <name> | Mark shipped + print type-specific ship checklist |
archive <name> [--reason "..."] | Retire gracefully |
info <name> | Show full metadata JSON |
~/.claude/commands/incubate/scripts/incubate.sh $ARGUMENTSFor list: present the table cleanly. For new / stage / ship / archive: echo the script output, then add context if helpful (e.g. suggest the next stage or next command). For promote: confirm the repo was created and show the next step (push). For info: show the JSON.
If the user's intent is ambiguous (e.g. "I want to start a new idea"), ask for the name and type before running.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.