16-agentic-output-review (Phase 4.85: Agentic Output Review)
Receipt entry (required):
"$PRINTING_PRESS_BIN" phase-receipt enter --file "$PHASE_RECEIPT_LOG" --run-id "$RUN_ID" --phase "16-agentic-output-review"Runs after Phase 4.8, before Phase 4.95. Phase 4.8 reviews SKILL.md prose against the shipped CLI. Phase 4.85 reviews the CLI's actual command output for plausibility bugs that rule-based checks can't encode (substring-match relevance failures, format bugs, silent source drops, ranking failures). The dispatch prompt, gate logic, and known blind spots live in the printing-press-output-review sub-skill — single source of truth shared with the polish skill (which runs the same review during its diagnostic loop).
Invoke the sub-skill via the Skill tool:
Skill(
skill: "cli-printing-press:printing-press-output-review",
args: "$CLI_WORK_DIR"
)The sub-skill carries context: fork so the reviewer agent's diagnostic chatter stays isolated from this generation flow. It returns a ---OUTPUT-REVIEW-RESULT--- block with status: PASS|WARN|SKIP and a list of findings.
status: SKIP means the sample-output review did not run. Record it as skipped. Do not render SKIP as PASS, and do not count it as a passing review in the phase summary or the score.
Wave B rollout policy: all findings surface as warnings, not blockers. Shipcheck does not fail on Phase 4.85 findings. Log the findings to manuscripts/<api>/<run>/proofs/phase-4.85-findings.md and surface them to the user. The user decides case by case whether to fix before shipping. Wave B calibrates false-positive rates before Wave C flips errors to blocking.
Before following Next:, record the durable handoff and point --evidence at
the findings artifact:
"$PRINTING_PRESS_BIN" phase-receipt complete --file "$PHASE_RECEIPT_LOG" --run-id "$RUN_ID" --phase "16-agentic-output-review" --evidence "<absolute-phase-4.85-findings-path>"Next: phases/17-local-code-review.md