feat: add bounded dual-review reconciliation

.agents/skills/sdlc/SKILL.md

@@ -33,10 +33,9 @@ Use this skill for implementation, bug-fix, refactor, testing, release, publish,
    Reviewer role: inspect the frozen diff and return prioritized code-review findings only; do not edit, implement, run tests, re-plan, or perform follow-up work. The builder owns every correction through the normal SDLC loop.
    `review_model` controls native Codex review model selection but does not set review reasoning independently. `auto_review` is for eligible approval prompts, not code-diff review. Do not require `/autoreview` unless the current Codex host exposes it as a verified feature.
    At each coherent green slice, author-review the exact incremental diff before committing. Once the cumulative candidate is stable, freeze it, run one fresh broad proof, and review the full base-to-candidate diff once. A relevant correction invalidates that completion proof; use narrow delta checks while fixing, then run a fresh final proof.
-   Incremental checkpoint: use affected proof, exact-diff author review, and at most one risk-based reviewer before committing a coherent green slice. During the ten-delivery pilot, the completion boundary reviews the whole base-to-candidate diff with Sol High and then Fable High; outside the pilot, use Fable only when cross-model policy requires it. A finding produces one bounded corrective delta with targeted proof. A third same-plan correction means stop; human approval may authorize a replan with newly scoped work, not silently extend the exhausted plan. Record ten-delivery pilot outcomes in `benchmarks/review-cadence.csv` before making this cadence permanent.
+   Incremental checkpoint: use affected proof, exact-diff author review, and at most one risk-based reviewer before committing a coherent green slice. During the ten-delivery pilot, the completion boundary sends the whole base-to-candidate diff through the bounded Sol High plus Fable High joint gate; outside the pilot, use Fable only when cross-model policy requires it. A finding produces one bounded corrective delta with targeted proof. A third same-plan correction means stop; human approval may authorize a replan with newly scoped work, not silently extend the exhausted plan. Record ten-delivery pilot outcomes in `benchmarks/review-cadence.csv` before making this cadence permanent.
    Severity ladder: P0 stops the line; P1 blocks completion; P2 is a bounded fix now or a follow-up issue; P3 never blocks and is recorded only when worthwhile.
-   When two reviewers are required, they assess the same frozen candidate independently, exchange compact findings once, and return a joint ledger. Allow at most two corrective rounds. If P0/P1 remains, decompose, abandon, or escalate; never waive it or continue an unbounded review loop.
-   Run Fable High only after Sol is clean and only when cross-model policy requires it: `node .codex/hooks/fable-review.cjs --base <ref> --consent-subscription-quota`. The explicit consent acknowledges Claude subscription-quota use; the wrapper rejects API-key and alternate-provider lanes, disables tools/MCP/session persistence, reuses the current proof, and binds its receipt to the frozen staged candidate.
+   When two reviewers are required, run `node .codex/hooks/dual-review.cjs --base <ref> --consent-subscription-quota`. Sol High and Fable High assess the same frozen candidate independently. Clean agreement stops immediately; a verdict split receives one verbatim cross-feed round of findings and then produces one conservative joint receipt. Do not add another reconciliation exchange. Allow at most two corrective rounds; if P0/P1 remains, decompose, abandon, or escalate rather than waiving it or continuing an unbounded loop.
    For every corrective finding, check its provenance against the base. If the blocker is candidate-born and outside the allowlist, remove that accretion instead of repairing it.
    If the work is in a product repo, keep that session focused on the product repo. File a direct GitHub issue for proven reusable wizard findings and only switch to live wizard work if the product repo is actually blocked.
 11. Present a final summary with what changed, what was verified, and any residual risk.