hyper-implement-looplisted

# hyper-implement-loop Autonomous implement-hardening gate. Creates a per-run team, runs hyper-implement to completion first, then spawns the `fixer` agent as a persistent teammate **once** (only after implementation finishes), invokes Codex `code-review --base main` through the bridge, and fixes via the still-live fixer until no blocking findings remain (judged semantically — see Step 6) or the cap is hit. The fixer 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-implement-loop <plan path>`. - User wants an autonomous implement → review → fix cycle in a single gesture. Skip when: - The task is one step — use `/hyperclaude:hyper-implement` directly. - You want hands-on control over each implement / review round — use `/hyperclaude:hyper-implement` + `/hyperclaude:hyper-code-review` manually. - 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 imp