Delimit Audit
delimit_auditAudit code changes through security, correctness, and governance lenses, using multiple models to surface consensus and tradeoffs for high-confidence review.
Instructions
Cross-model code audit — 3 models, 3 lenses, synthesized (Pro).
When to use: for high-confidence review of a code change, where agreement across models is the signal and disagreements surface tradeoffs. When NOT to use: for raw multi-model debate (use delimit_deliberate) or single-model review (delimit_review).
Sibling contrast: delimit_review is single-prompt multi-model; delimit_deliberate is full debate; this is structured cross-lens audit (security / correctness / governance).
Side effects: gated by require_premium. Calls models via ai.cross_model_audit.audit. No ledger write — caller decides what to do with findings.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| lenses | No | Comma-separated lenses — "security", "correctness", "governance". Empty = all three. | |
| target | No | File path, git diff output, or code snippet to audit. Required. | |
| target_type | No | "file" (default — reads file), "diff" (git diff text), or "snippet" (inline code). | file |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||