| name | remediating-devforgeai-audit |
| description | Deterministically orchestrate remediation for a validated DevForgeAI enterprise audit run through /remediate-audit. Use for explicit run IDs and normalized findings, not custody-chain story audits or raw Markdown findings. |
Remediating DevForgeAI Audit
Receive explicit /remediate-audit <run-id> [--finding <id>] [--dry-run] [--resume] arguments. Reject raw Markdown as execution state.
- Run
audit-findings-status and require a validated durable register.
- Use
audit-content-validate, audit-import-completed, and
audit-findings-build only for immutable completed-report intake.
- Execute phases 00–07 and the shared dependency order.
- Before source mutation, show the exact path/patch digest and require the
CLI-owned one-use approval.
--dry-run stops before mutation.
- Use
audit-remediation-record. Do not edit status, events, approvals,
evidence, closures, reports, or intake snapshots.
- Use
audit-remediation-verify, then dispatch the read-only
audit-closure-verifier from a different actor.
- Use
audit-remediation-compare only after protected-main re-audit and
audit-remediation-render only for a read-only projection.
HALT on missing CLI, exit 127, malformed JSON, missing state/schema, stale
generation, wrong commit/worktree, provider drift, invalid approval, or
incomplete evidence. Do not mark a finding closed before human merge and
protected-main re-audit. The shared CLI owns all policy; this skill is thin.
