Check your own claims against the user's notes before you state them. For each claim, give the note(s) it came from — the absolute path you read, a file.md#p3 ref from chamber_ask, or a passage id. Chamber confirms the note is indexed and unchanged on disk since indexing, then checks that every number, capitalised name, domain, file name and count in the claim occurs in that note. Verdicts: SUPPORTED, TERMS_ABSENT (names the missing terms), NO_TERMS (nothing specific to check), STALE (the note changed since indexing — not judged), NOT_FOUND, NO_SOURCE. The check uses no model and is deterministic. It does not check meaning — a negated claim built from the note's own words passes. Read-only unless record is true, which commits SUPPORTED claims through Chamber's gate (which may run the local embedder to compare against open citation debt), pinned to the passages that hold their terms, so chamber_verify reports them if a pinned passage changes once the note is re-ingested; unsupported claims are never recorded.

Have Chamber's own configured model answer a question from the user's notes, with every claim judged against its own citations. To check an answer you wrote yourself, use chamber_check instead. Each claim comes back ALLOWED (its cited passages verified against their stored hashes) or UNSUPPORTED (no verified source — recorded, not load-bearing). Cited sources are returned as file#passage references you can open. Answers only from the indexed corpus; says so when nothing matches. NOTE: this WRITES, exactly as chamber ask does — each claim goes through the commit gate, so a claim with verified citations is recorded as a belief with its pins (which is what chamber_verify later checks for drift), an unsourced assertion mints citation debt, and spend is recorded. It cannot bypass that gate, activate a skill, or approve a pending write.

Re-check every stored belief's pinned sources against the corpus as it stands now, and report the ones whose evidence moved: a source that no longer exists (not_found) or whose text changed under the pin (hash_mismatch). This is drift detection — the conclusion did not change, the ground under it did. Read-only.

Report what is actually in the index: passage and file counts, source kinds and which of them are citable, the top contributing folders, and any file far above the median passage count (the signature of an export rather than a note). Use this before trusting a 'nothing matches' answer. Read-only.