repo-mailbox/skills/dispatch/SKILL.md
Kjell Tore Guttormsen 5e5bc4a66e feat(route,board): strike the advisor rule, add board.sh --row <repo>
Order 20260912T202210Z-7588027378-from-.claude, operator decision
2026-09-12 (helhetlig vurdering av arbeidssystemet, cut row 3 and the
board.sh --row improvement row). One order, two parts, one version bump.

THE ADVISOR RULE IS STRUCK. route.sh and board.sh --dispatch emit no
--advisor at all. The rule fired per ROW on a need - always on the Sonnet
rows (a capability lift, which is what made the quota fallback safe to
take), and on the Opus rows at reversibility=costly|one-way - and it read
well. It was killed by a MEASUREMENT, not by taste: of 54 dispatches the
PM issued 08.-12.09, ZERO carried the flag, because sessions are started
by hand from the model and effort rather than from the whole emitted
line. A rule nothing honours is not a policy, and an emitted value nobody
acts on is decoration in a field whose only job is to be evidence. The
advisor is now what it already was in practice: an operator decision per
session, said in one sentence in route.sh --help.

The comments that rested on the rule were REWRITTEN, not left standing.
board.sh --dispatch still refuses a --model/--effort pair, but the reason
is no longer "the advisor is a property of the ROW": it is that the rubric
has exactly one copy, and a dispatch taking the model directly would be a
second, unscored way to reach the same decision - recording no traits, no
rationale and no next-cost, so nothing afterwards could say whether the
routing or the scoring was wrong. A comment defending a removed mechanism
is how the next session restores it. Both skills carry the correction.

Pinned as an ABSENCE over the whole trait space - 81 combinations, every
line of output, with a known-positive control proving the sweep's grep
can find a planted advisor - rather than on four sampled rows, because
the claim is that no path emits it. board.sh --dispatch at
reversibility=costly is pinned separately: that is the exact input a
reintroduced rule would fire on. The literal string is absent from
route.sh entirely, including the paragraph recording what was struck (it
says "an opus advisor flag" in words), because a blunt grep cannot tell a
description from a specification. Backward compatibility is pinned rather
than assumed: a route line carrying a legacy advisor= field still parses
and still yields a command - measured, 0 of 48 route lines in ~/repos
carry one, but a reader that broke on an unknown field would turn last
month's STATE.md into "that repo has no route line". The three CLI gates
section 14 carried went with the rule; the suite no longer depends on the
installed claude at all.

board.sh --row <repo> IS THE SEVENTH RENDERING of the same scan, never a
second scan, read-only like every other one. (The order calls it the
sixth; by this file's own numbering --inbox-plan is the fourth and
--dispatch the fifth. Corrected rather than carried wrong.) It exists
because the columns WERE misread: on 11.09 the PM read FLY off the table
by eye and got it wrong, while every other rendering a program consumes
is already key=value. inn, ordre and fly are three separate fields
because they are three separate facts; status is the bare token, never
the table's blocked>target display, with blocked-on beside it; neste is
last and uncut. An unknown repo exits 2 and writes NOTHING to stdout - an
empty block would read as a repo whose every column is blank, which is a
real and different state.

upushet is the ONE field that is not a rendering of the scan, and it is
named rather than blended in: nothing in the scan measures it, so it is
read once, for the named repo only, and never enters the table, the plan
or the briefing. It reads the remote-TRACKING ref, not the remote, so
upushet=N honestly means "the local ref says N"; a repo with no upstream
reports ?, never 0.

The row fixture's three counts are three DIFFERENT integers (3/2/1), and
that is the finding worth recording. Built first with 2/1/1, it was
mutation-tested by making fly read the ORDRE field - the exact 11.09
misreading - and the check stayed GREEN, because the two fields held the
same digit. A fixture that cannot tell two columns apart is the defect
wearing a passing test, inside the section written to prevent it.

Suites under /bin/bash 3.2, before -> after: coord 257 -> 257, board
393 -> 427, route 73 -> 73 (13 advisor checks and 3 CLI gates out, 15
absence/legacy checks in, and it no longer varies with claude being on
PATH), orders 116 -> 116, state-line-guard 54 -> 54. Sum 893 -> 927,
README badge updated to the measured sum. npm test 12/12, fail 0.

Verified live against the real tree, not only fixtures: --row
repo-mailbox reports fly=1 beside ordre=0 (the distinction that was
misread), --row on the nested key from-ai-to-chitta/content-sadhguru
resolves, and an unknown repo exits 2.

No tag, no push, no catalog change - that is the operator's
release-plugin.mjs run.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-12 23:45:47 +02:00

11 KiB

name description version
dispatch Turn "start a session in repo X, on order Y, at cost Z" into a complete, verified startup command — the prompt written to a file, the model and effort derived from the rubric, and the output form chosen by whether the target repo already has a terminal pane. Use whenever work is being handed to a session in another repo, or to this repo's own next session: "dispatch a session in repo X", "start a session there with this order", "give me the startup command for repo Y", "hand this work to <repo>", "write the plan file for that session", "open a tab for X with this task", "how do I launch the next session on this". Also triggers on Norwegian phrasings: "dispatch en økt i repo X", "start en økt der med denne ordren", "gi meg oppstartskommandoen for Y", "send arbeidet til <repo>", "skriv planfila for den økten", "åpne en tab for X med denne oppgaven", "hvordan starter jeg neste økt på dette". Trigger even when no tool is named — producing a runnable startup command for another session IS this skill. Not for choosing WHICH repo deserves the next session (that is `board`), not for scoring model and effort alone (that is `route`), and not for sending a message to another repo (that is `coord-send`). 0.34.0

dispatch — hand a session a task it can actually start on

A dispatch is one line the operator pastes and one file that line reads. Both halves are easy to get wrong in ways that look right: a command with no prompt in it, a plan file the driver silently discards, a --no-go that does not stop what everyone assumed it stopped. All three were measured on 2026-08-16 — four separate misfires in one day, by two different repos — and this skill exists so they are not re-derived a fifth time.

You produce the command. You never run it. Starting a session in another repo spends the operator's quota and takes an action inside a repo this session does not own. Hand back the finished command and stop.

The engine

ORDER="${CLAUDE_PLUGIN_ROOT}/scripts/coord-order-send.sh"
BOARD="${CLAUDE_PLUGIN_ROOT}/scripts/board.sh"

"$ORDER" --to <name> --subject "<one line>" --prompt-file <absolute path>

"$BOARD" --dispatch --repo <name> \
         --order-id <the id the order engine printed> \
         --target-pane <yes|no> \
         --path <known|partial|undetermined> \
         --verification <strong|weak|none> \
         --reversibility <cheap|costly|one-way> \
         --scope <local|multi-file|cross-cutting> \
         --rationale "why these four scores"

It writes nothing and prints one block. Exit 2 means it refused — read stderr and fix the call; every refusal is a case where a command would have been wrong rather than merely imperfect.

It is board.sh and not a script of its own because the block format (tab=/repo=/dir=/command=/paste=) has exactly one generator. Two emitters of one file format is the drift defect this repo's CLAUDE.md warns about.

The five steps, in order

1. Write the prompt file

The order goes in a file, in plain prose:

mkdir -p "$HOME/.claude/dispatch"
PF="$HOME/.claude/dispatch/<repo>-$(date -u +%Y%m%dT%H%M%SZ).prompt"

Write the whole order: the concrete task, which discipline applies (Iron Law, TDD, which file the test goes in), and what must not be triggered. A prompt that says only "continue" forces the receiving session to guess its task out of STATE.md, which is the thing handing over a prompt is supposed to prevent.

Norwegian prose, æøå, quotes, $ and backticks are all fine in the file. That is measured, not assumed: the order body never passes through a shell.

2. Deliver it into the recipient's order queue

"$ORDER" --to <repo> --subject "<one line naming the task>" --prompt-file "$PF"

It prints order-id=<id>. That id is the whole handle from here on.

This step is what makes a dispatch survive the pane it was typed into. The prompt file is scratch: it carries the order to one session and nothing records it afterwards. Measured 2026-08-17: an order was dispatched three times over 90 minutes before it was worked, because the first two tabs ran something else and the order left no trace anyone could find. In the queue it stays pending, is re-injected at every session start in that repo, shows up in board's ORDRE column, and is closed only by a session that claims and finishes it.

The queue is ~/.claude/coord/<repo>/orders/ — the same private local infrastructure as the mailbox, and a different channel from it. Mail is untrusted cross-repo data that can never instruct a session; an order is operator-authorized work. Never send an order as a coord-send message and never send a message as an order.

--to refuses what coord-send refuses: _-prefixed names, path traversal, and the retired ktg-plugin-marketplace address (send to catalog).

3. Measure whether the target already has a pane

morning --probe-panes | grep "<absolute dir of the target repo>"

A hit means --target-pane yes. Measure it; never assume it. This is the one input --dispatch refuses to default, for the same reason route.sh refuses to default --last-effort: it is a fact about the world, and guessing it produces a dispatch that verifies green and opens nothing.

Two facts about this measurement, both verified 2026-08-16 against the installed morning:

  • --probe-panes works from a Claude session, without a tty. It cannot identify the anchor pane, but the DIR column — the part you need — is there.
  • A session dispatching its own next session is always --target-pane yes. That is not a special case for one repo; it is what self-dispatch is, and it is where all four of the day's misfires landed.

4. Score the four traits and call --dispatch

Scoring is judgement and it is yours; the model and effort are a lookup and are route.sh's. Score the task the dispatched session will do, using the route skill's trait table.

Pass --order-id <id>, not --prompt-file. The emitted command is then a thin starter: it carries no order text at all, only the id and the four steps the receiving session runs (claim, compare against STATE's NESTE, execute, close). The order text has exactly one home, and a copy in argv would be free to drift from it and would die with the pane. --dispatch refuses an --order-id that is not in the target's pending queue — the same rule as the empty prompt file, one level up.

--prompt-file still works and is the fallback when there is genuinely no queue to write to. Passing both is refused: the session would be told two things.

--dispatch deliberately takes no --model/--effort. The rubric is a policy with exactly one copy, and a dispatch that took the model directly would be a second, unscored way to reach the same decision — one that records no traits, no rationale and no next-cost, so nothing afterwards could say whether the routing or the scoring was wrong. Score the traits and let the lookup spell the command. If the right call is a Fable row, the rubric cannot produce it: write that command by hand and say in the handover that it is a recorded override.

No --advisor is emitted, by the rubric or by this skill. That rule was struck 2026-09-12 on a measurement — 0 of 54 dispatches carried the flag. The advisor is an operator decision per session; do not add one to a dispatch command.

5. Verify, then hand it over

--target-pane no (plan-file form). Write the whole output to a file and dry-run it:

"$BOARD" --dispatch ... > "$HOME/.claude/dispatch/<repo>-<ts>.plan"
morning --plan-file "$HOME/.claude/dispatch/<repo>-<ts>.plan" --dry-run

Expect opening: 1 of 1. Then hand back:

morning --plan-file <path to the plan file> --no-go

Know what that dry-run does not prove. It proves the block parses and yields a command. It does not answer the pane question: run from a Claude session there is no tty, so morning reports window: unknown ... assuming an empty window and plan_drop_open never fires. A gate built on the dry-run would pass the self-dispatch case every single time — the one case it would exist to catch. Step 2 is the measurement; this is a parse check.

--target-pane yes (paste-only form). There is no plan file, deliberately: morning's plan_drop_open (morning:1788) drops a block whose repo already has a pane. Hand back the paste= line, and say it goes in the existing tab after /exit. Never prefix it with cd — one repo per terminal tab, and the operator is already standing in that one. morning --relaunch bypasses the filter but opens a second tab beside the existing one, which is rarely wanted.

Three things that must reach the operator

Say these in the handover, not only in the plan file. Each was a real correction, not a hypothetical:

  1. The command carries the prompt in argv. claude --model X --effort Y on its own is not a dispatch; it is a session waiting for someone to tell it what to do. Delivered bare twice on 2026-08-16, corrected by the operator with "gi meg alltid komplette oppstartskommandoer for nye sesjoner".
  2. --no-go does not make the session wait. It suppresses only the follow-up Go message — morning:806 is exact: "--no-go says nothing is typed once the startup command is in". The startup command, prompt and all, is typed regardless, so the dispatched session starts working on its own. An operator decision was once taken on the opposite premise and had to be corrected before the run.
  3. Which form you produced, and why. "Plan file, because <repo> has no pane" or "paste line, because <repo> already has one and a plan block for it would be dropped". The form is a consequence of a measurement, and the operator should be able to see the measurement.

What happens at the far end

The dispatched session claims the order and owns it until it closes it:

coord-order-claim <id>                       # atomic; exactly one session wins
coord-order-done <id> --commit <hash>        # executed, with a result pointer
coord-order-done <id> --no-commit --reason "<why>"
coord-order-done <id> --return --reason "<why>"   # back to the queue, with the reason

The claim prints the order and tells that session to compare it against its own STATE.md NESTE block and to state any divergence in its first reply. That is the point of the D-check: a dispatch that displaces a live next step is a decision, and it should be an uttered one rather than a silent one.

If the tab is never run, nothing is lost. The order sits pending, the next session in that repo sees it at startup, and board counts it in ORDRE.

Where a dispatch is still not enough

An order is a task. When what the other repo needs is a notice — something is fixed, a premise changed, a question needs answering — that is coord-send, not a dispatch. The test is whether you are asking for work to be done (order) or telling them something they must decide what to do with (mail).