Added ht-pr-approve-loop to hermes-talaria — A Skill That Approves user-review-requested:@me PRs in a Single Pass From a Frozen Snapshot With a 👌 Body Tadashi Shigeoka added a skill called ht-pr-approve-loop to the hermes-talaria repository via pull request codenote-net/hermes-talaria#65, which freezes all open PRs matching the GitHub search query `is:pr state:open user-review-requested:@me sort:created-asc` into an oldest-first snapshot and submits exactly one `👌` approval for each PR whose four-review adjudication from Claude Code and Codex finds no P0 findings. The skill reuses the existing ht-pr-approve runner for per-PR reviews, requires the target repository to be supplied explicitly on the command line, and pins each approval to a commit_id that is rechecked immediately before the POST. P1, P2 and P3 findings are recorded in a private ledger but do not block approval. Added ht-pr-approve-loop to hermes-talaria — A Skill That Approves user-review-requested:@me PRs in a Single Pass From a Frozen Snapshot With a 👌 Body Tadashi Shigeoka https://codenote.net/en/author/tadashi-shigeoka/ · Tue, November 17, 2026 The ht-pr-approve skill I wrote last time https://codenote.net/en/posts/hermes-talaria-conditional-pr-approve-skill/ takes one PR URL and a natural-language policy, runs four reviews from Claude Code https://code.claude.com/docs/en/overview and Codex https://openai.com/codex/ inside a disposable git worktree https://git-scm.com/docs/git-worktree , and submits a single commit-bound approval through the GitHub Pull Request Review API https://docs.github.com/en/rest/pulls/reviews when the policy passes with no P0 findings. The gap it left open was that my account keeps accumulating review requests, so clearing them with that skill still meant running it by hand one PR at a time, feeding the same repository and the same policy into it over and over. I added ht-pr-approve-loop to hermes-talaria https://github.com/codenote-net/hermes-talaria to close that outer loop. The pull request is codenote-net/hermes-talaria 65 https://github.com/codenote-net/hermes-talaria/pull/65 . Given one explicit repository, the new skill freezes all open PRs matching is:pr state:open user-review-requested:@me sort:created-asc as an oldest-first snapshot, reuses the existing ht-pr-approve runner for every PR, and submits exactly one 👌 approval for each PR whose four-review adjudication shows no P0 findings. This post walks through the design decisions I had to make to close that loop safely. Shape of the skill ht-pr-approve-loop accepts either a repository URL or the equivalent encoded pulls-search URL, and nothing else: The literal query the helper builds is pinned to: The minimal set of rules I chose for the loop is: - The target repository is only ever the one explicitly supplied on the command line. No inference from the current directory, Organization, or account. - user-review-requested:@me means a request addressed to the authenticated user personally, not through a team. The loop never substitutes review-requested , team-review-requested , is:open , or a guessed username. - The only public write is one API review with event: APPROVE , body: "👌" , and a pinned commit id . No separate comment, fix, merge, retry, or recurring job. - The approval predicate is “no P0 findings” and nothing else. P1, P2, and P3 findings land in the private ledger but do not block approval. The skill runs in five stages. Stage three calls the existing ht-pr-approve runner directly for each PR’s reviews, so the loop itself owns discovery and freezing, per-PR rechecks, adjudication of the four reviews, and aggregation. php flowchart TD IN repo URL or pulls search URL -- DISC discover prs.py