@irythill/orq 0.4.0 → 0.5.0

package/skills/issue/SKILL.md

@@ -58,7 +58,7 @@ independent acceptance criteria.
 - Each batch is independently testable and reviewable; dispatch in order, one implementer per batch. Record the split in
   Plane (sub-issues or a checklist comment) before starting.
 - Scope too big mid-run (reviews hitting `policy.max_rounds`, repeated findings, the implementer asking to change
-  scope): stop, split the remainder, don't force more rounds.
+  scope): stop, split the remainder, don't force more rounds. `orq rounds <ID>` shows the alert; on warn/stop `orq rounds <ID> --diagnose` says why.
 
 ## 3. Pick agent and model: always `orq pick`, never by hand
 `orq pick` decides agent, model, effort and account (user config + delivery and token history + current quota +
@@ -143,6 +143,9 @@ herdr-agent $(cat $O/impl-<repo>.pick) -g <group> -t "<ID> impl <repo>" -d $WT -
   origin/<BASE>...HEAD`); (2) `NODE_OPTIONS=--max-old-space-size=2048 tsc --noEmit` for the project. Don't run tests".
   Full suite only in CI (or a manual `herdr-baseline` if the user asks).
 - An issue that changes an API contract: **API first**; consumers afterwards, with the new contract in the prompt.
+- **A red board line / `✗` pane title = a failure you may have missed.** If you see one (or the user says notices aren't
+  arriving), run `orq notice` (delivery log) and `<prefix>.done` for that issue, then handle the failure; running
+  `orq wait`, `orq verify` or `orq agent` for the issue acknowledges it.
 - **Never block waiting** (`herdr agent wait`, `pane wait-output`, `sleep`, `timeout`): completion arrives as a
   `[HERDR-AGENT DONE]` line in your pane. Dispatch, report in one line and end your turn. "Done yet?" = `<prefix>.done`
   exists (never `pgrep`).
@@ -178,12 +181,14 @@ are in the attached verify)". If the reviewer ends with `status=fail` and no ver
 `jetski: ... permission` line), that is not a rejection: run `orq pick review ... --exclude-agent <it>` and redo it.
 `--exclude-agent` applies **only to redoing that review** (save the new pick to `review-<repo>.pick`); the next
 round reuses whoever gave the verdict. An agent that failed twice in a row with no verdict →
-`orq block <agent> --days 1` and tell the user.
+`orq block <agent> --days 1` and tell the user. If it stopped on a quota limit, use `orq block <agent> --quota` (until
+the window resets; a fixed period outlives it and keeps the agent out of `orq pick` for nothing). If `orq pick` finds no
+candidate, its output is empty and `orq agent` refuses to start: stop and tell the user.
 **Review tools** (an agent whose `run` has no `{prompt}`/`{prompt_text}`/stdin, e.g. a CodeRabbit-like CLI with
 `ok_exit`/`filter` in the config): same command; it ignores the prompt and the attachments and reviews the branch
 against `{base}` itself. Read its answer like any other: `status=ok` with `rc≠0` is a verdict with findings, not a
 failure. Its high-severity items are the blockers, still under the step 6 rule (`file:line` + concrete failure).
-If the tool's answer opens with (or, when short, consists of) a statement that nothing was reviewed (e.g. Corvus's "Nada para revisar"), `agents.<name>.no_review` (a
+If the tool's answer opens with (or, when short, consists of) a statement that nothing was reviewed (e.g. Revtool's "Nothing to review"), `agents.<name>.no_review` (a
 regex) makes `orq agent` end that run `status=fail`: `orq pick`'s fallback and the conductor treat it as not run,
 same as an empty answer.
 **Second opinion** (`orq pick opinion`, read only, same attachments): only on **heavy** issues or when reviewer and
@@ -223,7 +228,7 @@ Then a new `herdr-verify` (4b) and the **round review** (step 5 with these chang
   any regression it introduced, as `[blocker]`/`[suggestion]`. Outside the fix diff, report only a blocker you missed
   before that would break production, and say why it wasn't in the first review". Anything else is a suggestion. A review tool can't answer that: it reviews the whole
 branch again, so you do the matching — a finding is a blocker this round only if it is inside `fix-<n>.diff` or is a
-NOT RESOLVED item of `fix-<n>.md`; one you already decided on (fixed, rejected or downgraded) stays decided. **Maximum: `orq config get policy.max_rounds` rounds** — `orq agent -R` refuses the next one (exit 4) and counts per session, so a renamed prefix doesn't reset it; on exit 4 stop and tell the user, `-F` only with their OK; over it → `orq pick impl
+NOT RESOLVED item of `fix-<n>.md`; one you already decided on (fixed, rejected or downgraded) stays decided. **Maximum: `orq config get policy.max_rounds` rounds** — `orq agent -R` refuses the next one (exit 4) and counts per session, so a renamed prefix doesn't reset it; on exit 4 stop and tell the user. With their OK run `orq rounds <ID> --diagnose` (a cheap independent agent, advisory: read its `RECOMMENDATION` — continue / split / change-implementer / ask-user — and tell the user), then `-F` (refused without a diagnosis newer than the last fix/review; `-F -F` skips that, only if the user says so); over it → `orq pick impl
 --exclude-agent <it> > $O/impl-<repo>.pick` only with the user's OK, or stop and report. Non-blocking suggestions go into the comment; they
 don't become a round.
 

package/templates/workspace.CLAUDE.md

@@ -16,7 +16,8 @@ rules — read the repo's own before touching it. This file only holds the map a
   several unrelated areas, change roughly >400 lines, mix refactor with behavior change, or have independent acceptance
   criteria. Each batch must be testable and reviewable on its own; record the split in Plane before starting.
 - Reviews hitting `policy.max_rounds`, repeated findings or the implementer asking to change scope mean it was too big:
-  stop and split the remainder instead of forcing more rounds.
+  stop and split the remainder instead of forcing more rounds. `orq rounds <ID> --diagnose` asks an independent agent why
+  (advisory); `orq agent -R -F` past `max_rounds` needs that diagnosis (`-F -F` skips it, only on the user's word).
 
 ## Repositories