hyper-docs-looplisted

# hyper-docs-loop Autonomous docs-hardening gate. Creates a per-run team, spawns the `documenter` agent as a persistent teammate **once**, invokes Codex `docs-review` through the bridge, and fixes via the still-live documenter until no blocking findings remain (judged semantically — see Step 6) or the cap is hit. The documenter is spawned **once**; every fix round reuses its retained context via SendMessage. The reviewer is always the Codex bridge, never a teammate — 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. - The experimental agent-teams feature is unavailable (this skill stops with a documented fallback message — see Step 2). ## Failure & recovery protocol — read first `${CLAUDE_PLUGIN_ROOT}/references/loop-protocol.md` carries the shared cross-loop protocol — team contract shapes (§A), unsolicited-message protocol skeleton (§B), teardown procedure (§C), shared anti-patterns (§D), abstract request-id state machine (§E). `references/failure-protocol.md` (sibling of this file) is the docs-loop binding layer: structured-schema reply with `request-id: <id>` prefix, semantic findin