li-audit

Use when a workflow explicitly hands work across a boundary — spawning a subagent, transitioning a phase, passing to a cold executor, or taking operator input…

Use when a non-trivial decision needs recording to bootstrap a new Architecture Decision Record from the template, asking context-gathering questions to fill…

Use to check that PLAN and BUILD still match the approved DEFINE design — run when a plan was revised or a build deviated, to catch drift between what was…

Use when evaluating declared controls with mandatory, advisory, unverified and no-applicable outcomes; this is not host enforcement.

Use for data-architecture depth — schema design, migrations, sharding and partitioning, query-pattern audits, retention policy, and analytics readiness.

Use to identify the current CLI, desktop, IDE or cloud surface and inspect its actual tools without inferring capability from a vendor name.

Use to discover Lintel skills and agents by intent, name, purpose, category, voice or declared client support, or regenerate the committed skill catalog after…

Use to add, list or lift advisory session freeze paths; preserves project policy and never grants or removes host write permission.

Use before landing a change to review just the diff — focused on the changed code only, lighter than a full engineering review.

Use for an independent second opinion on a diff, plan, code or hypothesis through an actually available authorized reviewer.

Use before a large read or handoff, or when context headroom and resource advice are needed; keep observed usage, source estimates and unknown limits distinct.

Use to load bounded files, topic-related sources, ADRs or prior sessions with safe selection and honest input-size estimates before reading.