// Examine Autodialectics run results, manifests, and stored artifacts. Use after a pipeline run completes or to review past runs.
| name | inspect |
| description | Examine Autodialectics run results, manifests, and stored artifacts. Use after a pipeline run completes or to review past runs. |
Use this skill to examine completed or in-progress pipeline runs and their artifacts.
autodialectics-mcp must be on PATH (pip install autodialectics).
inspect_run(run_id) — retrieve the run manifest: status, decision, scores, timing, and artifact paths.read_artifact(run_id, artifact_name) — read a specific artifact by filename. Common artifacts:
contract.json — the immutable task contractsubmission.json — the original task submissionexecution_output.json — domain executor resultsverification_result.json — independent verification outputevaluation.json — slop scores and gate decisionpre_mortem.json — failure predictions (if pre-mortem routing was enabled)autodialectics inspect <run_id>
inspect_run to get the overview, then drill into specific artifacts with read_artifact.running or starting, it may still be in progress — wait and re-inspect.verification_result against evaluation to understand whether the verifier and evaluator agree.If the user passes a run ID after /autodialectics:inspect, inspect that run and summarize the results.
Run benchmark suites and manage policy evolution — create challengers, compare against champions, promote or rollback policies.
Re-run a stored Autodialectics pipeline run, optionally with a different policy, to compare outcomes or debug regressions.
Compile and execute an Autodialectics anti-slop pipeline for a task. Covers health checks, runtime init, contract compilation, and full pipeline execution.
Use the local Autodialectics MCP server and CLI to compile tasks, execute anti-slop runs, inspect artifacts, replay runs, benchmark policies, and evolve champions in this repository.