Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
little-canary
SkillsDetects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.
git clone https://github.com/hermes-labs-ai/little-canary.git -
skill-router
SkillsSkill + Agent + Model + Thinking depth — auto-routed before any tool fires. One SKILL.md for Claude Code. 90% routing accuracy, per-step model enforcement, 30%+ savings on multi-step chains.
git clone https://github.com/hussi9/skill-router.git -
GraphQL AST query complexity calculator enforcing recursion depth limits and pagination cost budgets
git clone https://github.com/alphaparkinc/genpark-autonomous-graphql-query-complexity-calculator-skill.git -
GraphQL AST query complexity calculator enforcing recursion depth limits and pagination cost budgets
git clone https://github.com/Alpha-Park/genpark-autonomous-graphql-query-complexity-calculator-skill.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.