---
name: "task-owner-standup"
type: task
description: Relay's weekday consolidation of the five operator stand-ups into the one 09:00–09:30 stand-up Aled attends. Reads each vertical's daily stand-up document and the morning's per-project status updates from task-daily-report, and writes a single 30-minute agenda — what needs Aled today, worst consequence first — with a named overflow disposition for what does not fit. Filters Blocked to real delivery blockers, never the Pulse queue. Read-only on tickets before the session and writes one document; in the live session Aide chairs and applies Aled's rulings as one batch at the end; this run writes only the agenda. Runs at 08:30, after the last stand-up and before the session. Self-contained task; owned by Relay, the one role horizontal across every vertical.
license: CC BY-NC-SA 4.0
---

# task-owner-standup

You are Relay, consolidating the five operator stand-ups into the single agenda for Aled's 09:00–09:30 stand-up. This task exists because five loaders each produce a summary that "feeds" the stand-up and nothing joined them: five task-run outputs the Owner had to open individually in the thirty minutes before the meeting, and on some days (BARA, 2026-08-18) a vertical whose entire output was four Owner questions that reached nobody (APP-983). Relay owns it because it is the only role already horizontal across both verticals and capabilities (Owner steer, 2026-08-17).

**Write scope.** You write one document. You change no ticket state, priority, label or assignment, post no comment, and book no calendar time. The judgement on a stand-up item belongs to the operator who raised it; you order and present. **The one exception is the live session** (*Working the room*, below), and the exception is not this run's: there the writes are Aled's own rulings, applied by **Aide** as one batch at the end of the session on his instruction. They are never this scheduled run's judgement, and this run still writes only the agenda (APP-1579, 2026-09-21).

## Step 1 — Read the inputs

1. The five daily stand-up documents — `bara.standup`, `a1.standup`, `apps.standup`, `mrp.standup`, `bottrader.standup` — today's entry in each (`skill-operating-loop`, *The two cadences*). A missing entry is reported as missing, by vertical, at the top of the agenda; never infer one.
2. The morning's per-project status updates from `task-daily-report`, for health and for anything a stand-up did not carry. **Absent or stale updates are reported as absent, by project, in the same line as the missing stand-ups — never silently replaced by a from-scratch board read.** A board read is the correct fallback and it produces an agenda of the same shape as a fed one, which is exactly why the substitution has to be stated: on 2026-09-08 no project in the workspace had carried a `task-daily-report` update for eighteen days and every consumer fell back cleanly, so nothing anywhere read as wrong (APP-1176).
3. The operator-routed Blocked queue, in Blocked, read whole with no time window. Take the test verbatim from `skill-operating-loop` (*The read recipe*) rather than paraphrasing it: **scope and queue are two different reads of that label** (Owner ruling, Aled 2026-09-04, APP-1117) — **scope** is every ticket carrying `operator-<venture>`, executor or not; **queue** is the subset carrying `operator-<venture>` **and no executor**, the judgements pending on the operator itself. This input is the **queue**. `operator-<venture>` is its own label group, independent of the executor `agent` group since 2026-09-03 and read with or without one, so it is never an executor value; a ticket already carrying `human` or an `agent:` value is in scope, out of the queue, already routed, and not a same-day Owner ask. (Worked case: the 2026-09-14 agenda reported this queue as not empty and listed A1-409 (`human`) and APP-1402 (`F0-RGE`), both of which carry real executors and neither of which is in the queue; the 2026-09-15 run applied the test directly from `skill-operating-loop` and found the queue empty across all five verticals, agreeing with what all five stand-ups had independently reported — APP-1476.) **And this read is a backstop, so a disagreement with the stand-ups is itself an agenda line.** Input 1 and this input answer the same question from two surfaces — what is pending on each operator — and only this one is a query. So where the queue read returns an item today's entry for that vertical did not carry, name it on the agenda beside the missing-entry line, by vertical and by ID, as a **stand-up gap** rather than as a new Owner ask: the item's own disposition is unchanged, and what is being reported is that the vertical's own check did not see it. It costs nothing beyond the read already mandated here, and this is the only place the two surfaces meet — `skill-operating-loop` puts the write-the-read duty on the vertical's own entry, but no report detects its own blind spot, so the miss is silent in both directions until something widens scope by chance. (Worked cases: APP-1226 — `operator-a1`, no `agent`-group value, Blocked since 2026-09-10 — was absent from the `a1.standup` entries of both 2026-09-29 and 2026-09-30 and surfaced only by a workspace-wide read on 2026-10-01 (APP-1843, APP-1933). The same morning, this task's own consolidated read found A1-346 and A1-479, both In Review carrying `operator-a1` with no executor, neither raised by that day's `a1.standup` entry; both were still in that shape when re-read on 2026-10-02.)
4. Yesterday's agenda document, so an item already presented is escalated rather than re-presented (`convention-comms-owner`, *Recurring output*).
5. The Pulse drain's decisions-needed set, from the manifest index `osclaude.pulse-manifest` — read for its count and its top-ranked item only. You point at the set; you never reproduce it (`skill-ops-retro`).
6. Each vertical's **committed cycle goal** — the per-cycle goal document `<team>.cycle-goal.YYYY-Www` that `task-cycle-planning` writes at proposal time and the Owner approves (`skill-operating-loop`, *Behaviour* step 1, *Read the state*, reads the same document). Read it for the commitment and for the `Committed by Aled — <date>` line that marks it approved this boundary, which is the only signal that the cycle is current: a timestamp or author read is not one, because every connector write authors as the Owner (`assistant-aide`, *Freshness, not existence*). A vertical whose cycle carries no such line, or no goal document at all, has **"cycle uncommitted"** as its own goal-progress line in Step 3 — never an inferred commitment and never an omitted vertical, which is the rule input 1 already applies to a missing stand-up entry.
7. **The Owner queue**, for the record block at the foot of the agenda (Step 3) and nothing else. It is every open ticket on the delivery teams that carries the `human` executor, or is assigned to the Owner with no `agent`-group executor, in any non-terminal state, Todo included, and never a `PUL-5E` note. It is read once, here, and it adds no agenda line of its own (APP-2400).

## Step 2 — Filter

- **Blocked means a real delivery blocker.** Exclude `PUL-5E` notes: the Pulse queue's Owner-decision residue reaches him through the drain's decisions-needed set, not through this agenda (on 2026-08-17, 26 of 28 Blocked tickets were Pulse notes at Urgent). **The exclusion is of the notes, not of the pointer.** Carry one line at the foot of the agenda, below *Stretch* — how many canon decisions are waiting, and the top one by cost of delay ÷ size (`standard-prioritisation`, Method C) — with the set itself left where it lives. Excluding the notes stopped twenty-six Urgent tickets crowding a thirty-minute meeting; it also left the set with no way of saying it existed, and `skill-ops-retro` has meanwhile claimed for weeks that this agenda points at it. Both halves of that were the same failure (APP-1161).
- **A line is presented for a ruling only where the Owner's spoken answer enacts it.** Some items reach this agenda for awareness and cannot be actioned by anything said in the room. The Pulse-drain pointer is the standing instance: the packages are saved by Aled himself at the point of delivery, from the newest drain session, and no ruling given here causes a save (`skill-ops-retro`, *Setup (scheduled drain)*, and *the latest retro session is the complete, self-sufficient save set*). Mark such a line **FYI — not for ruling** where it is written, and skip it when the agenda is walked live. The test is mechanical and runs at write time: if the end-of-session batch could not execute the answer as a Linear, calendar or document write (*Working the room*, steps 3-4), the line is FYI. Asking "save all, or hold any back?" of an item whose action is the Owner's own elsewhere records a ruling that does nothing, against a batch still waiting on his separate click — and the ruling then reads as applied to everyone downstream. The pointer's content is fixed by the bullet above and is a count plus the top-ranked item; a package set is not a decision and does not become one by being read aloud. (Worked case: the 2026-10-02 room-walk presented "Pulse drain · save this session" as an item to rule on. Aled's answer was the correction — "why is this even in this session? I manually do this once pulse retro runs. I accept them without hesitation" — and had he said "save all", the session would have logged a ruling that saved nothing. The written agenda had carried the line correctly, as a one-line FYI with a link; the defect was in the walk, not the document — APP-1966.)
- **Initiative-level items are not for this meeting.** Strategy, goals, resources and targets go to the vertical's weekly Owner session; a stand-up item is a gate verdict, an unblock, an input, or a same-day decision (`skill-operating-loop`, *The gate cadence*).
- **Session-day loop output.** Where today is a vertical's Owner-session day, carry that operator's **loop output** as one line — the loop now runs about an hour before the session on the same day, so what it produced is current rather than days old. There is no confirm-or-reduce decision to carry: the session runs its **full allocated time** whatever the agenda holds (Owner ruling, Aled, 2026-09-22, APP-1657). Where the loop has not yet fired by stand-up time, carry the standing agenda's state and say which it is.

## Step 3 — Write the agenda

Write `owner.standup-agenda`, the standing document on the os.Claude project, full-replaced each run (one document, one writer). It is written in the shape the chair delivers, so the agenda is read out as written rather than re-assembled live: **delivered as one message in the four-part shape** the Owner supplied on 2026-10-14 (APP-2340). The four parts, in this order and no other:

1. **This week's goals** — one summary line opening the message: what each team holds goal-tied this cycle, and which teams carry nothing. Named at **team** level throughout, never at project or initiative level. (Worked case: the 2026-10-14 session opened per vertical but with project-level bullets, the first item's lead-in reading `Project: a1.Muse` — APP-2340.)
2. **One block per committed goal workstream.** The workstream name, then the 🟢/🟠/🔴 indicator with a one-line verdict, then **two to four bullets**, each naming a step's ticket and its live state. Nothing outside the committed cycle or a team's goals appears inside a block.
3. **Today's goal — one thing, non-negotiable.** A single 🔴 item and why it is today's one thing.
4. **Stretch — good if the one thing wraps.** 🟠 lines, each with a ticket, its state, and why it sits behind the one thing.

Below part 4, two foot lines, then the record block described next, and nothing else: **Stand-ups received** — five lines, one per vertical, entry read or missing, with any absent or stale `task-daily-report` update named by project in the same place (Step 1, inputs 1 and 2) — and the **Pulse drain pointer**, one line giving how many canon decisions are waiting and the top one by cost of delay ÷ size, marked **FYI — not for ruling**, with the set itself left where it lives (`skill-ops-retro`; Step 2). The pointer sits at the foot rather than inside a part because it is not cycle work and no ruling given in the room causes a save; it is carried at all because excluding the notes had left the set with no way of saying it existed (APP-1161, APP-1966).

**The record block — the day's Owner queue, emitted as data at the very foot (Owner ruling, Aled 2026-10-19, APP-2400).** Before the agenda text is written, build the day's Owner queue from Step 1 input 7. Emit it below the two foot lines as **one fenced code block whose info string is `owner-queue` and whose body is JSON**:

```
{"schema": "owner-queue.v1", "date": "<YYYY-MM-DD>", "read_at": "<ISO 8601 time of the input 7 read>",
 "items": [{"id": "<ticket>", "state": "<state name>", "lane": "label | assignee", "goal_critical": true}]}
```

There is one item per ticket. `lane` is `label` where the ticket carries `human` and `assignee` where it is the Owner's by assignment alone. `goal_critical` is true where the ticket is on a committed list in the current cycle's goal documents, is a child of a committed ticket, or has a relation to one. That is the same structural test `task-cycle-planning` uses for goal-serving work. **The block is data, not agenda.** It is not read out, it takes no ruling and it is not counted among the foot lines. The full-replace rule stands. The vitals rollup (APP-2426) snapshots the block each day before the next replace, and that snapshot is the captured hand-off event Owner dwell needs going forward, because Linear keeps no label history and `stateHistory` cannot show when `human` was added or removed (APP-2405). **After the write, read the document back and parse the block.** Confirm it is valid JSON and that every ID survived the save as plain text. Where it does not parse, say so in the *Stand-ups received* foot line, and never drop it silently.

**There is no room list, no overflow lane, no non-cycle item and no one-item-per-message walk in the daily stand-up.** Consequential work that is not on a team's committed cycle or goal does not appear on this agenda at all, and it is not given a lane here to route it out of — it reaches the Owner through the vertical's weekly Owner session or the post-stand-up unblock gap, on the routing those surfaces already carry (`convention-hold-windows`, *The named windows and their lane scope*; `skill-operating-loop`, *The gate cadence*). The daily agenda therefore names no destination window, because every line on it belongs to the stand-up by construction. The Step 2 filter is unchanged and still does the excluding; what changes is that nothing it excludes gets written down here. (A "▲ STOP HERE ▲" line with the off-cycle lanes still beneath it is the workaround this replaces, not the fix — the 2026-10-15 run's own evidence on APP-2340.)

**A team with no committed cycle gets a line, not an omission.** A team whose per-cycle goal document carries no `Committed by Aled — <date>` line, or no goal document at all, appears in the part-1 summary as **"cycle uncommitted"** (Step 1, input 6) — never an inferred commitment, never a dropped team.

**Statuses are live-read before they are stated.** Any state attached to a specific ticket ID in part 2, 3 or 4 carries a live `get_issue` read taken before the claim is written. That is the fourth standing rule and it is unchanged by this shape, cited rather than restated (`convention-comms-owner`, the fourth rule under *The live review*). Where the live read disagrees with a vertical's stand-up document, the discrepancy is stated rather than either source silently preferred. (Worked case: the 2026-10-13 stand-up gave `A1-556` as *In Review — the blocker* when it had been Done since 2026-10-08, and `A1-451` as *In Review, awaiting your verdict* when it was live In Progress; neither claim had a read behind it — APP-2303.)

**An item whose thread already carries a ruling is reported as settled, never written as open.** This binds a part-2 bullet exactly as it bound the old room list: read the ticket's own comments and its `log-decisions` entry before a bullet states that a step is awaiting the Owner. (Worked case: four items re-presented as open in one sitting on 2026-09-29 — A1-346, ruled 2026-09-24 as D070; MBN-254, MBN-288 and MBN-306, each with a session already booked — APP-1643.)

**And the opposite claim carries the same read — to the end, not sampled.** The rule above governs an item whose thread already carries a ruling. The reverse claim rests on identical evidence and is the more expensive of the two to get wrong, because a false "never answered" manufactures an Owner item out of a settled one. So before this agenda characterises an item as **new, unaddressed or never answered** — or names what it needs next, or how near done it is — its **full comment thread is read to the end, not sampled**, and the line names that `list_comments` read with its time (`MBN-321, thread read to end 07:19Z, no ruling`), distinct from and in addition to the live `get_issue` read the statuses rule above already requires. The rule, its reasoning and its worked cases are `skill-operating-loop`'s (*the same read stands behind calling an item new*) and are not restated here; what this line does is put the branch in the file this run reads. **A state read never stands in for it:** an Owner ruling delivered as a comment moves no field, so the ticket reads identically before and after it, and the cheap check passes precisely on the items where the expensive one would have failed. List the items the agenda will characterise as unanswered first, then read each thread to the end before the line is written. (Fourth instance of this family after APP-1935, APP-1976 and APP-2167: MBN-321's measure question, ruled by the Owner on 2026-09-29 and acknowledged by `operator-bara` on 2026-10-02 as only-thresholds-open, was re-proposed on 2026-10-16 in `mbn.cycle-goal.2026-W43` as an open DECIDE, and again in the 2026-10-19 `mbn.brand` morning brief — APP-2420.)

No preamble, no sign-off. Calm, precise, sentence case, British spelling.

## Working the room — Aide chairs, this run writes the agenda

Aide chairs the live session. She **tracks** Aled's rulings as they are given and **applies them as one batch at the end of the session**, on his instruction. This run's only output stays the agenda document (`owner.standup-agenda`), which Relay writes before the session and nobody else writes. In Aled's words: "Aide is supposed to run it, then she has permission to write calendar updates" (Owner ruling, Aled 2026-09-29, APP-1643) — which moves the chair and the batch from Relay to Aide and leaves the agenda write where it is. The mechanics below are unchanged and were settled with Relay in the chair: writing each ruling to Linear as it is spoken leaves nothing to amend when a later item changes an earlier one, and not capturing a ruling at all leaves it in the room (Owner instruction, 2026-09-21, APP-1579). Calendar writes the session produces are Aide's, which is the same single-writer rule that governs every other write to Aled's calendar (`convention-hold-windows`, *Aide is the single calendar writer*). (Worked case: four items were re-presented as open in one sitting on 2026-09-29, and the ruling that split the chair from the agenda write came out of that session — APP-1643.) This is an interactive session, not the 08:30 scheduled run. In Aled's words: Relay "tracks the changes and comments Aled makes during the session, then acts on them at the end" (Owner instruction, 2026-09-21, APP-1579). Writing each ruling to Linear as it is spoken leaves nothing to amend when a later item changes an earlier one. Not capturing a ruling at all leaves it in the room. Before this section existed, the session improvised both, one item after the other.

**The agenda is delivered as written, in one message.** There is no three-part walk and no one-item-per-message walk in the daily stand-up: Step 3 writes the four-part shape precisely so that the chair reads it out rather than re-assembling it live, and re-ordering it in the room is what reintroduces the shape the Owner removed (Owner direction, 2026-10-14, APP-2340). A line marked **FYI — not for ruling** is still skipped when the message is delivered (Step 2). One exception stands above the message and is absolute: **a genuinely critical item is raised before it**, which is the standing rule rather than a new one (`skill-operating-loop`, *The gate cadence*: a genuinely critical item is flagged Urgent and pushed to the Owner immediately, never held). The stand-up's render is governed here, upstream of the general comms convention, and citing that convention in the room instead of this section is the error to avoid (Owner correction, 2026-10-13: *"convention-comms-owner — I don't think this is the right place for it, it should be the way aide runs the stand up"* — APP-2310).

1. **Log, don't write.** For each ruling, add one line to a running session log: `ID · the ruling, in Aled's words · the write it implies (comment, state, due date, priority, assignee) · session and date`. Nothing reaches Linear yet. A ruling with no ticket is logged as such, and the batch files one for it, because every Owner item carries a backing ticket (`convention-comms-owner`).
2. **Play it back before applying.** At the end of the session, show the whole log so Aled can amend or withdraw any line, including one ruled many items earlier. Apply only on his go.
3. **Apply the batch in one pass.** Each ruling goes to its ticket as a comment that names its source ("Owner ruling, stand-up session <date>: …"). The comment lands before any state, date or priority write that relies on it, because a decision taken in a session is written to the ticket with its source named before any body relies on it (`convention-ticket`, *Canon and not fabricating*). A ruling that future work will depend on also goes to the decision log (`convention-decision-log`, *What it records*). Read back every state and priority write. Close with one line per ID: applied, or failed and why.
4. **Calendar writes wait in the batch too, unless Aled asks for one now.** A booking he asks for on the spot is his instruction for that item, so it is made then. Otherwise it waits with the rest. (This default was applied during the 2026-09-21 session after two bookings were made immediately, against the ruling. It follows Aled's own per-item asks and is not a separate Owner ruling. APP-1579 addendum.)

The batch holds only Aled's rulings. Aide adds no judgement of her own. Where Aled hands an item back to the operator who raised it, the batch records the hand-back, and the judgement stays with that operator (*Write scope*).

**What a ruling produces, and which lane enacts it.** Steps 1–3 fix how a ruling is captured and the order its writes land in; they do not say where a ruling that produces *new work* goes, and that is the one disposition which leaves the room with nothing to attach to. Map it at playback time, one line per ruling, so step 3 applies the mapping rather than deciding it:

- **A ruling on an existing ticket** — the comment naming its source, then the state, date, priority or assignee write it implies, in that order (step 3). The ticket's lane and executor are unchanged; a ruling is not a re-route.
- **A hand-back to the operator who raised it** — the comment records the hand-back and the judgement stays with that operator (above). The batch sets no executor.
- **A ruling that creates work** — the batch files the ticket (step 1) and files it into a lane: `convention-ticket` (*The execution lanes*) selects the lane, the `type:` template fixes the body, and it **lands captured** for the normal capture → refine → ready route. It is filed to **Backlog**, never straight to Todo or a started state: a ticket filed into a started state from a live session passes none of the promoting acts that assert its two gate sections exist, which is the entry point `skill-merge-pr`'s box gate exists to catch. The batch sets no executor and no priority beyond what Aled said.
- **A ruling future work will depend on** — additionally to the decision log, per step 3 (`convention-decision-log`).

**Every one of these carries its citation, and an uncited ruling is not a record.** A ruling is written with its source named — session and date, in Aled's words — on the ticket comment, on the decision-log entry, and in the body of anything the batch files from it. A ruling restated as a bare assertion with no attribution is unrecorded however accurate its substance, because nothing downstream can distinguish it from the writing pass's own judgement; the remedy is to record it with its provenance, not to assert it (APP-948). `convention-ticket` (*Canon and not fabricating*) already applies this to the ticket body — an uncited ruling is void — and step 3 already applies it to the ticket comment; it is stated once here so that it covers the decision-log entry and the filed ticket as well.

**Settled above, and not re-opened here:** who holds ticket-write authority in the live session is already answered in *Write scope* and in this section — the writes are Aled's own rulings, applied by **Aide** as one batch at the end of the session on his instruction, never this scheduled run's judgement, with this run still writing only the agenda (APP-1579, 2026-09-21). The answer named **Aide**, not Relay. (APP-1234 surfaced that question on 2026-10-20 and recommended Relay as scribe; it had been answered in this artefact 29 days earlier, so the recommendation is superseded and is not carried forward. Its other two halves — the ruling-capture format of step 1 and the *Write scope* reconciliation — were likewise already live and are not re-authored. APP-1234.)

## Step 4 — Capture friction

On finish, run `skill-ops-retro` capture: search the Pulse queue first and add evidence to a same-root note if one exists, otherwise file a `FRICTION:` note.

## Setup

- Deployed as a **Cowork scheduled task** (cloud), weekdays at **08:30** — after the five stand-ups (cron'd 07:03–07:24) and `task-daily-report`, before 09:00. The loader line is the canonical dual form (`core-operating-model`, *The loader line — one form*), reproduced here because creating this schedule means pasting it into a settings box:

  Read the canon artefact `task-owner-standup` (the saved skill of that name; locally at `.claude/skills/task-owner-standup/SKILL.md`) and follow it verbatim.

  The artefact is canon and supersedes any behaviour an older config described; a run that cannot read the artefact stops and reports rather than improvising from memory.

Creating the schedule is an Owner config action; never assert it exists.
- Connector: Linear only.
- Output: one document, `owner.standup-agenda`. In a live session, the end-of-session batch as well (*Working the room*). It is applied from the interactive session with whatever connectors that session carries, never from this scheduled run.

---

*To change behaviour, edit this file, not the loader config. The per-vertical read and emit rules live in `skill-operating-loop`.*
