Menu
Use when you need request-level Canon decisions, attempts, and policy outcomes for an existing run.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | canon-inspect-invocations |
| description | Use when you need request-level Canon decisions, attempts, and policy outcomes for an existing run. |
available-nowdefault visibility: prominentInspect request-level invocation records for a Canon run.
RUN_IDcanon is on PATH. If missing, point to the install guide..canon/ exists. If missing, point to $canon-init.canon inspect invocations --run <RUN_ID>$canon-status, $canon-inspect-evidence, or $canon-approve.canon/ is missing, point to $canon-init.RUN_ID.canon inspect invocations --run <RUN_ID>.$canon-status for the run headline.$canon-inspect-evidence when you need lineage across generation and validation paths.$canon-approve if the inspected invocation is approval-gated.$canon-status$canon-inspect-evidence$canon-approveUse when you need a governed Canon review of a real diff or pull-request range instead of a loose chat summary.
Use when a repository does not have Canon runtime state yet and you need to initialize .canon before any governed workflow.
Use when you need a governed Canon policy-shaping run to shape a new or modified policy with mandatory impact evaluation.
Use when you need a governed backlog run that decomposes bounded upstream decisions into delivery epics and slices.
Use when you need a governed Canon architecture run to record decisions, tradeoffs, and risk-gated approvals.
Use when you need a governed change run in a live codebase where invariants and existing behavior matter.