docs(triage): pr-reviewer takes a batch of PRs per call

.agents/skills/triage-prs/SKILL.md

@@ -42,7 +42,7 @@ Execute the approved closes/comments with retries and ~1–2s spacing between ca
 
 The review bot's `review:*` labels are a pre-sort, not a verdict: `review:ready` PRs go first (the bot found no code defects — likely MERGE/MERGE-THEN-FIX), `review:blocked` ones carry a bot comment whose findings the verdict review verifies rather than rediscovers. Bot labels never replace the pr-review pass — the bot cannot judge product fit or maintainability scope. The reverse holds too: when the bot's BLOCKED findings are the whole story and the author has not answered, the maintainer never re-posts them in their own voice — the PR is *waiting on author* and the report says so in one line.
 
-Split the clean pool smallest-first (tiny diffs are fast wins and most likely mergeable). Fan out the `pr-reviewer` subagent (`.opencode/agent/pr-reviewer.md`, which loads the `pr-review` skill and carries the hard rules) — one PR per call, or ~10 PRs per general subagent that receives the full `pr-review` skill text when `pr-reviewer` is unavailable. The subagent inherits the chat's model; never hand verdicts to a smaller model to save quota — a verdict from a small model is a pre-sort, not a decision. Each returns per-PR verdict blocks in the skill's output format.
+Split the clean pool smallest-first (tiny diffs are fast wins and most likely mergeable). Fan out the `pr-reviewer` subagent (`.opencode/agent/pr-reviewer.md`, which loads the `pr-review` skill and carries the hard rules) in batches of ~5–10 PRs per call, grouped by area when possible so one subagent's context serves several PRs; fall back to a general subagent that receives the full `pr-review` skill text when `pr-reviewer` is unavailable. One subagent per PR is the exception for a single large or contentious PR, not the default. The subagent inherits the chat's model; never hand verdicts to a smaller model to save quota — a verdict from a small model is a pre-sort, not a decision. Each returns per-PR verdict blocks in the skill's output format.
 
 **Report format.** The consolidated report is what the maintainer decides from — calibrate each entry so no follow-up question is needed, without ballooning:
 

.opencode/agent/pr-reviewer.md

@@ -1,10 +1,10 @@
 ---
 mode: subagent
-description: Reviews one pull request as the maintainer's proxy and returns a single verdict (DECLINE / PUSH-BACK / MERGE-THEN-FIX / MERGE) with its ready action. Use from PR triage fan-out or whenever a PR needs a verdict; it never posts, merges, or edits.
+description: Reviews a batch of pull requests (one to about ten) as the maintainer's proxy and returns one verdict block per PR (DECLINE / PUSH-BACK / MERGE-THEN-FIX / MERGE) with its ready action. Hand it several PR numbers at once for triage fan-out, or one for a single review; it never posts, merges, or edits.
 color: "#d08770"
 ---
 
-You review exactly one pull request in the OpenChamber repository and return one verdict the maintainer can act on.
+You review the pull requests you were handed — one or a batch of up to about ten — in the OpenChamber repository, and return one verdict block per PR that the maintainer can act on. Work through them one at a time, fully, before starting the next; count your output blocks against the numbers you received and never drop one.
 
 Load `.agents/skills/pr-review/SKILL.md` first and follow it exactly: it owns the verdict ladder, the "symptom's path" bar for MERGE, the verified-vs-unverifiable distinction, the residue-owner rule between PUSH-BACK and MERGE-THEN-FIX, product-fit escalation, ache salvage, pickup mode, the output format, and the voice. Then follow `AGENTS.md` instruction order for the change's character: load every matching project skill and the owning `DOCUMENTATION.md` / `README.md`.