/bureau:adrRecord an architecture decision — scaffold a proposed MADR ADR page (auto-numbered, optionally superseding a prior one) into the canon. Authors only; a human approves it via bureau:review. Use when the user asks to write or record an ADR or an architecture decision, or to supersede a prior decision.
/bureau:approve-allBulk-approve the review backlog as canonical — preview it, then hand the user the one `--by human` line to run. Use when the user asks to approve everything, approve the whole queue, or bulk-approve at once.
/bureau:codex-reviewLet Codex (via cc-suite) deliberate over the bureau review queue as your representative — it reads each unapproved claim and recommends approve or hold, then either hands you the exact approve command (advisor, default) or, only where the workspace opted in, commits under its own `codex` authority (
/bureau:compileDistil minutes into consistency-checked dossiers (the canon), with provenance back to each session. Use when the user asks to turn the logbook into canon, update the cabinets, or build the knowledge base from sessions.
/bureau:crewManage bureau's crew — list, enable, or author specialized agents that work the canon.
/bureau:cycleRun the full bureau maintenance lifecycle in one pass — compile pending minutes into dossiers, scan the recursion engine for changed claims, lint for consistency, surface everything that needs human review (by trust tier AND freshness), and rebuild the gazette. Use when running bureau:cycle, or when
/bureau:file-sessionWrite the rich minute for the current session (intent, decisions, changes, open threads).
/bureau:impactShow the pre-change blast radius of a dossier — which pages (transitively) rest on its claim, so you can see the review cost before you touch it. Use when running bureau:impact, or when the user asks "what depends on this?", "what breaks if I change X?", "who rests on this claim?", or "is this safe
/bureau:initScaffold a bureau workspace (cabinets + logbook) in the current repo and wire the press.
/bureau:inspectBuild the gazette (the offline gazette) with the bundled press, and open it for inspection.
/bureau:lintSweep the cabinets for semantic inconsistencies (contradictions, superseded claims, gaps, drift) and write a findings report. Use before a milestone, or when the user asks to check the canon for contradictions, consistency, or drift.
/bureau:noteTake a live note — summarize the current session's decisions/open threads into the running minute (or ephemerally if no workspace).
/bureau:pairPair this repo's external bureau workspace (its .bureau-id) to a local path on this machine.
/bureau:queryAnswer a question from the bureau canon — cited, tier-aware, and never stating an unverified claim as fact.
/bureau:reviewThe human double-check gate — review AI-written cabinet claims and promote the vetted ones to canonical, reject the rest. Use when the user asks to approve, vet, or sign off on what the AI wrote to memory before it is trusted as fact.
/bureau:serveOpen the chamber — a localhost-only room serving the gazette read-only plus an intake form that files proposed claims as append-only logbook minutes (never canon). The interactive write surface that feeds the gate.
/bureau:snapshotVersion the canon with git — pin a named, reproducible snapshot, diff two versions semantically, or render the board as it was at any past commit. Use when running bureau:snapshot, or when the user asks to snapshot / tag / freeze / pin a version of the canon, compare two versions, see what changed,
/bureau:statusReport the state of the bureau — uncompiled sessions, pages by trust tier, dependency freshness (needs-review/stale from the recursion engine), and what needs your attention.