@feigi/fleet-ctl 3.100.3 → 3.102.0

package/skills/run-team/SKILL.md

@@ -197,7 +197,7 @@ owes beyond its call:
      then records `fleet-heartbeat.mjs --stop` last, because every reader takes
      a recorded stop as the end of the run. A `NEED tier-outcomes append <pr>`
      is a reviewed PR with no verdict row — for an implementer's, one that never
-     reached its finisher: append it with the verdict you rule (**Guard: accumulate per PR**) and run `finish` again.
+     reached its finisher: run `append <pr>` (**Guard: accumulate per PR**) and run `finish` again.
      A PR closing none or several: a NEED if a settled `impl-<N>=PR#<pr>` token
      names it, else a note. A step it fails is explained in
      references/close-out.md. Exit 0 is the run closed.
@@ -281,8 +281,8 @@ digest asks of you:
 
 **Guard: accumulate per PR, never conclude inside one run.** **Append one row to
 `docs/metrics/tier-outcomes.tsv` when you rule each PR's review, before its finisher, with
-`~/.fleet/bin/fleet-run tier-outcomes.mjs append <pr> --closed-own-ticket yes|no --minted-false-claim yes|no --note "<text>"`,
-never by hand** (that file's header carries the column meanings). The script
+`~/.fleet/bin/fleet-run tier-outcomes.mjs append <pr>`, never by hand** (that file's header carries the column meanings).
+The script works both verdicts out from the Charges on the PR's first review. The script
 fills `tier` itself; never type one in. `ledger.mjs dispatch` refuses the finisher until the row exists. That append is the whole duty. See references/pull.md.
 
 **A verdict is a measurement only if it post-dates the run that produced it.** See references/reviewers.md.

package/skills/run-team/briefs/fix-applier.md

@@ -11,6 +11,7 @@ arg violations violations
 path worktree
 path scratch
 path mismatched-record
+ticket ticket
 literal your name
 literal outcome
 literal that path
@@ -64,6 +65,16 @@ claim, never your patch.
 **Before you report, write every ruling to `<scratch>/dispositions-<your name>.json`**,
 `<your name>` the `fix-pr-<pr>[-x]` you were dispatched as — the record the controller checks with
 `dispositions-check.mjs` before it dispatches any finisher.
+
+**Charge every standing entry of that record:** which entries stand, and the
+`charge` and `chargeReason` fields, are in `review-and-fix.md`'s step 2. Read
+the definitions of `closed_own_ticket` and `minted_false_claim` in the header
+of `docs/metrics/tier-outcomes.tsv`, and charge each standing entry by them,
+against the ticket below as its implementer was dispatched with it.
+
+The ticket:
+
+<ticket>
 ## kind: conflict
 Bring `<branch>` current with `origin/main`, resolving every conflict by the
 **No-undo audit** in `$(~/.fleet/bin/fleet-run --root)/commands/run-merge-bot.md`.

package/skills/run-team/references/close-out.md

@@ -25,8 +25,7 @@
      stop as the end of the run. A `NEED tier-outcomes append <pr>` is a
      reviewed PR with no verdict row — for an implementer's PR, one that never
      reached its finisher, since `ledger.mjs dispatch` refuses that finisher
-     until the row exists: append it with the verdict
-     you rule (**Guard: accumulate per PR**) and run `finish` again. A reviewed
+     until the row exists: run `append <pr>` (**Guard: accumulate per PR**) and run `finish` again. A reviewed
      PR that closes no issue, or several, with no settled `impl-<N>=PR#<pr>`
      token naming it takes no row: the check names it in a `note` line and
      never asks for one. With such a token it is a NEED: `append` takes the

package/skills/run-team/references/pull.md

@@ -477,6 +477,12 @@ member-outcomes row (a `tier-unverifiable=` member has no ledger verdict, so
 its one member-outcomes row decides), and BLANK with a WARNING naming why
 when neither settles
 it; never type a tier in over that.
+It also works `closed_own_ticket` and `minted_false_claim` out from the Charges on
+the PR's first review and composes `note` from them, so you type no verdict. A PR whose
+record has no Charge on a standing finding, or whose review file or record is missing,
+is refused, naming what is missing: check the record again, or dispatch the fix-applier
+again as a dispositions retry. Verdicts given by hand, with `--note`, are for a merged
+PR whose evidence is reclaimed, and `append` refuses them on any other.
 
 **Why not decide inside one run.** A run holds 2-3 implementer PRs, and ticket
 difficulty swamps the tier effect — a gojq parity harness and a two-statement