forge-card-validator
Skill1 starsChanged 6 months agoMITView on GitHub
Automated D-018 leak detection + template placeholder validation on the freshly registered HF model card. Hard fails the forge before the public flip if any branding leaks (NEXLESS, MGMO, SIF, internal client names) appear in the published README, OR if any unfilled template placeholders ({{...}}) made it through. Replaces the manual "review the card" step.
Files
forge-card-validator
When this fires
Phase position: CARD_VALIDATOR — after REGISTER (which publishes private), before PUBLISH (the public flip). Hard-fails if checks fail; PUBLISH never runs.
What it checks
- Pull current README.md from the HF model repo
- Case-sensitive grep for:
NEXLESS,MGMO,SIF,Intellident,ToothFerry,Dshamir,blucap - Regex for unfilled template placeholders:
\{\{[a-z_]+\}\} - Required sections present:
## Model Details,## Limitations,## How to Use - Param count is a real number (not the placeholder cap)
- License field set
- base_model field set in YAML frontmatter
Output (machine-readable)
{
"status": "pass" | "fail",
"checks": {
"d018_leaks": {"passed": true, "hits": []},
"template_placeholders": {"passed": true, "hits": []},
"required_sections": {"passed": true, "missing": []},
"param_count_real": {"passed": true, "value": "1.5B"},
"yaml_frontmatter": {"passed": true}
}
}In this repository29 other files it gives its agents.
- slm-forgeSkill
- forge-analyzeSkill
- forge-architectSkill
- forge-auditSkill
- forge-bootstrapSkill
- forge-curateSkill
- forge-estimateSkill
- forge-evalSkill
- forge-ingest-dbSkill
- forge-ingestSkill
- forge-intakeSkill
- forge-monitorSkill
- forge-plan-fitSkill
- forge-planSkill
- forge-preflightSkill
- forge-prepSkill
- forge-provisionSkill
- forge-publishSkill
- forge-quantizeSkill
- forge-registerSkill
- forge-reportSkill
- forge-resumeSkill
- forge-shapeSkill
- forge-smoketestSkill
- forge-sourceSkill
- forge-statusSkill
- forge-synthSkill
- forge-teardownSkill
- forge-trainSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

