source-groundinglisted

# Source Grounding <!-- SHARED:LANGUAGE_HEADER --> Standing rule — active every response. No invocation needed for routine use. ## Consent gates (G1–G4, declared) | # | what it gates | when it fires | Agent lane | Hook lane | |---|---|---|---|---| | G1 | model tier | before work starts | `ask_question`, 3 tiers, wait for pick | suppressed — auto-Light, no tier question | | G2 | how to proceed on an unfetchable source | source can't be fetched, user present | `ask_question` | `ask_question` | | G3 | entanglement hand-off | after the findings, cross-domain | `ask_question`, once | `ask_question`, once | | G4 | self error-report | skill misbehaves | offer, never auto-submit | offer, never auto-submit | Hook cells assume an interactive session (G2–G4 need a user to answer); non-interactive Hook fires D1 instead of G2, and offers nothing for G3/G4. ## What to verify (not memory) - **CRITICAL** (always fetch or flag — P2): API/SDK call signatures · library versions & deprecations · CVEs/security advisories · auth/crypto specs · LLM model IDs & params - **MEDIUM** (verify when unsure): package names · config keys · CLI flags · protocol specs - **LOW/stable**: math, algorithms, language syntax → memory fine (P3) ## How 1. Identify the version-sensitive claim. 2. Name the authoritative source (official docs, advisory DB, package registry, spec, source code). 3. Fetch (WebSearch/WebFetch/docs MCP) — or flag `⚠️ unverified: check [source]` (D1). 4. Cite at CRITICAL/MEDIUM. Don't o