From coalmine
Verify version-sensitive facts against live authoritative sources before asserting them in code or answers. Triggers on: "/source-grounding", "source-grounding", "sourcing". Standing rule — always active via CLAUDE.md. Invoke for deep verification work (API signatures, CVEs, model IDs, auth flows, deprecated patterns, security advisories).
How this skill is triggered — by the user, by Claude, or both
Slash command
/coalmine:source-groundingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
<!-- SHARED:LANGUAGE_HEADER -->
Standing rule — active every response. No invocation needed for routine use.
⚠️ unverified: check [source].Per-claim-type authoritative source map: read references/sources.md when choosing where to verify.
.coalmine.json trustedDomains if set: treat those domains as additional authoritative / tier-2 sources)Non-interactive runs: log unfetchable claims as ⚠️ UNVERIFIED and continue — never block. Interactive: when sources cannot be fetched, confirm how to proceed via ask_question.
✅ [claim] — source: [link/file]⚠️ unverified — check [exact source]npx claudepluginhub hetcreep/coalmineVerify version-sensitive facts against live authoritative sources before asserting them in code or answers. Triggers on: "/source-grounding", "source-grounding", "sourcing". Standing rule — always active via CLAUDE.md. Invoke for deep verification work (API signatures, CVEs, model IDs, auth flows, deprecated patterns, security advisories).
Verifies version-sensitive and time-changing facts (APIs, configs, CLI flags, pricing, model IDs) against installed environment and current docs before relying on training memory.
Selectively requires citations for high-value factual claims to balance accuracy with token cost. Use before research tasks or when deciding whether a claim needs verification.