fableplan-loop

# fableplan-loop Chain fableplan → work-on-issue-loop into one autonomous run: Fable 5 plans the implementation for a GitHub issue (plan posted to the issue), then work-on-issue-loop implements that plan in an isolated worktree, opens a PR that closes the issue, and drives the PR through `@claude` review to convergence. This is **fableplan-work-on-issue with the review loop added back** — the handoff goes to `work-on-issue-loop` (implement → PR → trigger `@claude` → fix-pr-review cycles until LGTM) instead of `work-on-issue` (single-shot, ends at the open PR). Equivalently, it's **validate-fableplan-loop with the validation stage removed**: no `validate-issue`, no update-issue edits, and no Capability gate — fableplan always runs. Reach for this when you already trust the issue, want a Fable-vetted plan, and want the PR reviewed to convergence without coming back. **Do not skip or reorder the chain.** The plan gates implementation — that's the point of routing through fableplan. There is no Capability gate here: unlike validate-fableplan-loop, this skill has no validation step to produce a score, so fableplan always runs. Every step of each skill still runs; only the "wait for the user's reply" moments are replaced by the handoff below. ## Input A GitHub issue is **required** (work-on-issue-loop targets an issue): a full URL, `#<N>`, bare `<N>`, or `owner/repo#N`. With nothing supplied, default to the latest open issue in the current repo. If no issue can be resolved, st...