hyper-docs-looplisted

# hyper-docs-loop Autonomous docs-hardening gate. Invokes Codex `docs-review` through the bridge and — on the FIRST round that carries blocking `### Findings` — spawns the `documenter` agent **once** to apply them, reusing that same agent via `SendMessage` on every later round until no blocking findings remain (judged semantically — see Step 4) or the cap is hit. A run Codex clears on its first review spawns no documenter at all. The reviewer is always the Codex bridge, never an agent — this preserves the "Claude builds, Codex reviews" invariant. ## When to use - User typed `/hyperclaude:hyper-docs-loop [target]`. - User wants an autonomous docs-review → fix cycle in a single gesture. Skip when: - A single doc edit is enough — edit it directly or use `/hyperclaude:hyper-docs-sync` for code-change-driven sync. - You want hands-on control over each review / fix round — use `/hyperclaude:hyper-docs-review` + manual edits. ## Failure & recovery protocol — read first `${CLAUDE_PLUGIN_ROOT}/references/loop-protocol.md` carries the shared cross-loop protocol: **Spawn contract**, **Reply transport**, **Correctives and transport failures**, **Shared anti-patterns**. `references/failure-protocol.md` (sibling of this file) is the docs-loop binding layer: it names this loop's structured per-finding reply schema, the schema-gate accept rule, the semantic finding-map validation, the named reports, and what a transport failure preserves. Step 0 makes Reading BOTH mandatory before the