simplify: coarser mention gates, tested poll scripts, anchor-based run window

[max-sixty]

Cuts the four complexity hotspots from the recent bot-PR audit back to the #960 vision — mechanism only where it prevents wrong outward actions — and moves the surviving logic under real tests. Everything loaded or executed in production shrinks (~420 lines across the template, generated workflows, and skill prose); the growth is tests for scripts that previously had none.

• mention.yaml.j2 verify gates: 4 → 2. The stacked review-path skip gates collapse into two structural rules: a bot-authored review summons a session only as the reviewer→author handoff (fresh content on a PR the bot authored), and a contentless approval is terminal whoever submitted it. GitHub rejects self-approvals, so the empty-body-APPROVED gate was already subsumed by an author-keyed rule. Outward behavior is unchanged — verified case-by-case twice (by hand, and independently by the review sweep's verifier); each rendered workflow drops ~52 lines.
• running-in-ci: 869 → 677 lines. The two markdown poll recipes become tested scripts. poll-pr-checks.sh polls by commit OID, never the PR head, fixing the false green a concurrent push caused (closes running-in-ci: CI-monitor poll follows the PR head, so a concurrent push makes a run report another commit's green as its own #829) and carrying the edge cases fix(running-in-ci): pin the CI-monitor poll to the SHA the run pushed #837's five review rounds surfaced — null merge-ref rollups, superseded check runs, STARTUP_FAILURE/ACTION_REQUIRED bucketing — so it supersedes fix(running-in-ci): pin the CI-monitor poll to the SHA the run pushed #837. rerun-failed-jobs.sh owns the rerun and finds the new attempt's jobs by run_attempt, so a fast rerun no longer reads as "nothing re-queued" and an unregistered one can't report stale conclusions as fresh. The rarely-taken skill-PR mechanics move to references/skill-pr-workflow.md.
• list-recent-runs.sh: 207 → 113 lines. The completion window becomes "floor = the last successful run's start, clamped at 6h, else 6h with a coverage-gap warning". Any successful run's window opens at or before its own start, so consecutive windows overlap and never gap — which makes the cron parsing, tick tiling, dropped-tick recovery, and the schedule-event restriction all unnecessary, at any cadence. The retry wrapper goes too: a transient failure now fails loud, and the next tick's floor reaches back past the lost window. This supersedes the window-anchoring half of perf(review-reviewers): cut cadence to 3-hourly, and anchor the window to the cron period #845; its cadence-cut half stands alone and needs no script support under anchor-based windows.
• review-reviewers Non-issues: 7 carve-outs → 3 structural rules (designed no-ops at whatever layer catches them, designed silence, reviewer-role independence), with the closed menu folded into Gate 3's cost classification.

Also: pre-commit's shellcheck now covers plugins/**/*.sh (it covered none of them), and the fake-gh test scaffold consolidates into generator/tests/__init__.py (five copies → one).

Testing

The scripts are exercised end-to-end under pytest with fake gh/date/sleep binaries, with the scripts' own jq filters doing the reductions: 21 cases for the poll scripts (false-green guards: >100-context page, null rollup, superseded runs, moved head), 11 for the window logic (anchoring, clamping, self-exclusion, loud failure), and the mention gate consolidation is pinned by the reworked test_generate.py assertions plus regenerated snapshots. Full suite green. The verify gate itself is still string-shape-tested rather than executed — extracting it to a .sh template like review-gate.sh is the natural follow-up, left out here to keep this diff reviewable.

Review-hardening notes (later commits)

An 8-angle verified code-review of the first commit found the substantive gaps in the new scripts themselves, all fixed and pinned by tests: the GraphQL query's one 100-node page could hide a red check past the cap (now routes to UNVERIFIED); a nullable startedAt could let a stale settled check run outrank its QUEUED replacement (a group with any non-terminal entry now reads pending); a transient API blip on a late poll iteration discarded the pending list the cap report names (the last usable rollup is kept); rerun discovery by job status misread fast reruns (now keyed on run_attempt advancing); and overlapping workflow prefixes double-counted runs (unique_by). The known remaining limit: latest-wins can't distinguish two independent runs of a group-less workflow on one SHA — documented in the script header and the skill, with the instruction to read the specific run's conclusion where that distinction must be exact.

A further tend-review round on the PR added: explicit --repo/owner arguments on the three gh calls that leaned on cwd remote detection (with test assertions pinning the flags), a Step 1 sentence in review-reviewers covering a failing list-recent-runs.sh call (retry once, then record a coverage gap — the run still concludes green, so the next tick anchors past the span), and the zero-checks commit named in poll-pr-checks.sh's exit-2 docs.

This was written by Claude Code on behalf of max-sixty

[tend-agent]

Read the mention-gate consolidation case by case against the four gates it replaces (bot review on own PR with a body / with fresh inline comments / reply-only / empty-body approved; bot review on another author's PR; human bare approval) — outward behaviour matches on every one, and the self-approval argument that collapses the #747 gate holds. Ran the suite locally: 458 passed, and shellcheck -S warning is clean on all of plugins/**/*.sh now that the hook covers them.

Three things, one of which I think is a real hole opened by deleting gh_retry — it's a caller-contract gap rather than a script bug, and the fix is one sentence in review-reviewers Step 1 (outside this diff), so I've left it inline rather than as a suggestion. Happy to push it if you'd like it in this PR.