Most "everything for Claude Code" collections optimize for count: hundreds of skills, agents and hooks that auto-run on your tool calls. It looks impressive and fails quietly. This one optimizes for the opposite.
vet, proof, workflow-upgrade, goal, konsilium, ship-secure, pre-push, system-health, teach, longread. Each one is a procedure that survived real use, not a prompt someone thought sounded good.
An adversarial verifier that tries to refute a finding instead of confirming it, and a read-only scout that reads an incoming tool's repo and reports before anything is installed.
Safety guards, code principles, root-cause discipline, detective mindset, a think-before-code checklist for new projects, and dependency intake.
The newest piece, and the reason for release v0.2.0. An agent's most expensive habit is not being wrong. It's reporting done on work nothing actually checked, in the same tone it uses for work that was.
passpartialfailskip
Climb only to the lowest rung that decides the claim: expense is not evidence. And keep skip distinct from fail — "we didn't look" and "we looked and it's broken" call for opposite actions.
No installer, and no curl | bash: this harness practices what it preaches. Copy what you want.
git clone https://github.com/Sanexxxx777/curated-claude-code cd curated-claude-code cp -r skills/proof ~/.claude/skills/ cp -r skills/vet ~/.claude/skills/ cp agents/*.md ~/.claude/agents/