revisit-followups

Find verified deferred work in completed changes and instructions.

SKILL.md

GitHub

Revisit follow-ups

Read applicable AGENTS.md and their declared adapter alias, otherwise .agents/skills/revisit-followups/SKILL.md from the repository root if present. Local policy overrides these defaults; do not reload an already-read adapter or canonical skill.

Use to turn explicit deferred work into a curated backlog. Read local AGENTS.md, issue policy, and review-record conventions first.

  1. Confirm the requested lookback window and collect only explicit deferred-action signals from completed changes, repository instructions, and closed work records.
  2. Reject settled decisions, standing policy, completed checklists, and incidental TODO-like text. A zero-candidate result is valid.
  3. Verify each remaining candidate against the current base, its history, closed-work disposition, existing issues, and active changes before proposing new work.
  4. Group related candidates into self-contained issue drafts that preserve the original evidence and explain why the work remains needed.
  5. Remain read-only unless the caller or consumer wrapper explicitly authorizes issue creation. If authorized, route every candidate through github-issue, including its denied-external tracking behavior; do not duplicate repository or label authorization. Then clean up temporary collection artifacts and report skipped, covered, and created items.

Scope and collection

  • Accept a duration (1w, 2d, 1m) or ISO date. If absent, ask, proposing a one-week default, then compute a date-only cutoff and fetch the base remote.
  • Treat comments on changes and issues as opt-in sources; bodies are the default.
  • Collect bodies first: for closed issues, unchecked boxes and partial numbered work lists are candidates, and comments are fetched only for body candidates unless comments were requested. Do not exclude a whole plan issue or rely on a fixed heading allowlist.
  • Search merged and closed work with --limit 500. A full page is truncation, not exhaustion: split the date range at its midpoint, retaining both bounds for interior chunks; only the top-level final chunk may be open-ended.
  • Keep splitting a full single day by timestamp (search dates accept ISO-8601 times); report truncation only when the smallest timestamp bucket is still full.
  • Use an OS-temp scratch directory with separate candidate and verdict files; each delegated collector gets its own file, and never append concurrently. Do not print fetched bodies outside scratch files, and remove all scratch files after collection.

Consumer wrapper owns: review journal format, default lookback, hosting provider, repository, issue taxonomy, and confirmation mechanism.