Use when ending a turn, finishing a slice, blocked on another agent's work, or escalating to a human — durable work handoff via queue items so the system keeps moving across compactions, missed messag
1---2name: queue-handoff3description: Use when ending a turn, finishing a slice, blocked on another agent's work, or escalating to a human — durable…4---56# packages/daemon/assets/plugins/openrig-core/skills/queue-handoff/SKILL.md
Q
SKILL.mdAgent skill
Transport
File
Status
Listed
SKILL.md
Install
The skill file stays in the publisher's repository.
Paste the copied command in a terminal. It installs this SKILL.md into that agent.
shterminal
1npx skills add mvschwarz/openrig --skill queue-handoff -a cursor -y
Paste the copied command in a terminal. It installs this SKILL.md into that agent.
Use when ending a turn, finishing a slice, blocked on another agent's work, or escalating to a human — durable work handoff via queue items so the system keeps moving across compactions, missed messages, and interruptions. Covers the hot-potato terminal-turn-rule (active work ends by passing the ball, not by going idle), default-nudge semantics, and when `--no-nudge` is appropriate for intentional cold park or human gate.
Download packages/daemon/assets/plugins/openrig-core/skills/queue-handoff/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
Where does queue-handoff live?
The publisher keeps it at https://github.com/mvschwarz/openrig.
Which agents can use queue-handoff?
Claude, Cursor, Codex, and Grok Build can read a SKILL.md you add from the publisher's repository. Grok Bot installs it when you send the skill's GitHub folder link in a chat.
From the publisher
SKILL.md
name
queue-handoff
description
Use when ending a turn, finishing a slice, blocked on another agent's work, or escalating to a human — durable work handoff via queue items so the system keeps moving across compactions, missed messages, and interruptions. Covers the hot-potato terminal-turn-rule (active work ends by passing the ball, not by going idle), default-nudge semantics, and when `--no-nudge` is appropriate for intentional cold park or human gate.
Durable work handoff via queue items. Lets the system keep moving
through compactions, missed messages, and interruptions by passing the
ball forward instead of leaving work suspended in chat or in-flight
without an owner.
Use this when
Ending a turn on substantive work. Active work should end by
passing the ball to an owner or to the human — never by going idle
with the rig appearing dormant.
Finishing a slice that has a clear next step. Default-nudge:
receiver gets a wake-ping plus the durable queue item.
Blocked on another agent's work. Use rig queue block <id> --on <child>
(or rig queue update <id> --state blocked --blocked-on <child>). The item
stays active and returns to pending when its blocker completes. Waiting on
something outside the queue, such as CI or a long job? Park the row:
rig queue block <id> --on external:<what> --wake-after <duration> --continuation "<what resumes>". It stays yours and reads parked, not
stalled, and the timer wakes you.
Escalating to the human. Make the escalation a durable attention
item, not just a chat message.
Don't use this when
The work is genuinely complete and there's no follow-on owner. Use
closure_reason: no-follow-on (terminal completion) or
canceled/denied as appropriate.
The handoff would be too small and turn work into bureaucracy. Bundle
the work into a coherent slice instead of decomposing every step.
The handoff would be too broad and lose ownership/proof/closure
criteria. Shape the qitem so the receiver knows the expected next
action and closure evidence.
The hot-potato terminal-turn-rule
Active work ends by passing the ball to a named next owner or to the
human. The qitem state machine enforces this:
pending → in-progress → done requires closure_reason from one of:
handed_off_to — work continues at a different seat (target = new owner)
escalation — kicked up to a higher tier (target = escalation target)
superseded — replaced by another qitem (target = successor qitem id)
Two of those (handed_off_to, escalation) additionally
require closure_target. The daemon enforces this at the domain layer;
every surface (CLI, MCP, future UI) inherits the same guarantee.
done is terminal. closure_reason: blocked_on is valid only on an active
state=blocked park record, as used by workflow writers; combining it with
state=done is rejected. Use the block command above to wait on another qitem.
The drafted-park failure (draft ≠ throw). The rule is about the actual pass, not the
intention to pass. A turn that ends with a self-instruction typed into your own prompt but left
unsent — a drafted go-ahead, a next-atom note you never sent — has not handed off; it has
parked, and the seat sits idle for as long as nobody notices. Drafting the handoff feels like
doing it; it isn't. Your last act on a turn must be an EDIT or a SEND — a committed change, a
rig send, a rig queue handoff — never a drafted prompt line left in the buffer. If your
final output is an instruction addressed to yourself, you haven't ended the turn, you've stalled it.
The dispatcher's other half — supersession closes your own outbox. Ending your turn cleanly is
only half the rule; the other half fires when you move the world. When a phase transition or a
fold receipt supersedes work you dispatched, close those dispatches yourself — with a citation to the
event that superseded them. Closure-on-supersession belongs to the dispatcher, never the
receiver. Make it a habit: after every fold receipt / phase transition, run an outbox audit —
which of my open dispatches did this just make moot? — and close them with the citation.
Why it must live with you: stale dispatch-debt is invisible to the dispatcher because it lands
on someone else's queue — the cost is externalized, so no feedback loop ever fires to make you clean
it up. The receiver inherits debt they did not create and must burn cycles verifying it before they
can hold cleanly; a queue full of stale-pending makes check-before-holding — the discipline you
most want cheap — expensive, and it degrades the idle-detector's signal (a real owner looks the same
as a stale dispatch). Close it at the source: the moment your own transition mooted it.
And after you hand off, PULL — don't idle with a stocked queue. Handing the baton off ends the
sequential thread; it does not end your turn if your own queue still holds work. The circulation
pattern: finish → (1) hand the baton off so sequential work continues → (2) check your OWN queue and
pull the next item rather than going idle → (3) go truly idle only when your queue is exhausted,
then wait for the baton. An agent idling on top of a stocked queue is the single biggest utilization
leak (see orchestration-team → queue depth is the orchestrator's product). This is pull-not-push at
the seat level and needs no new machinery — the last act after a handoff is a PULL.
Default-nudge semantics (the syntax footgun)
Command
Nudges by default?
When to use
rig queue create
yes
New qitem created from scratch
rig queue handoff
yes
Transactional close-as-handed-off + create-new
rig queue handoff-and-complete
yes
Atomic close + create-new; default nudge wakes the new owner
Footgun: --no-nudge accidentally added to a live-loop handoff.
The shipped 0.3.1 CLI nudges by default on every queue write surface
(rig queue create, rig queue handoff, AND rig queue handoff-and-complete).
The only suppression flag is --no-nudge — appropriate for intentional
cold park, human-gate signal, or a deliberate poll-driven workflow, but
NOT for live-loop handoffs where motion matters.
Rule: in a live loop, omit --no-nudge and trust the default.
--no-nudge is the opt-out, not the opt-in. If you find yourself
reaching for --notify, stop — that flag does not exist on the
shipped 0.3.1 CLI; you may be following a stale instruction that
inverted the default-nudge polarity.
Every queue row
--summary "<what it is and why this seat>" on every create, handoff and handoff-and-complete: one or two plain sentences. It is the row's subject in RECENT, the story and the needs-you view, and a handoff does not inherit it from the source row.
Scope tags project:<id>, mission:<id>, slice:<id> on project work, set when you create the row (--tags; create also takes --mission and --slice). Tags can't be edited afterwards. A handoff keeps the source row's tags unless you pass --tags or --gate, either of which replaces them; repeat the scope tags in --tags when you use --gate.
Pass work on with handoff-and-complete. It closes your row as done and records the next row as its successor in one step. A create followed by update --state done --closure-reason handed_off_to records no successor, and the stuck sweep raises a recovery item for it.
Close what you hold. A row you claimed ends in a handoff or an update --state done --closure-reason …; rig queue overdue lists claimed rows past their deadline.
Use the write's response. Read the row back only when the response doesn't show what you need (an indeterminate outcome, a field the compact output left out, downstream wake or pickup, a team custody rule): openrig-user, "After a queue write".
Brief for the model that will read it. Before handing a peer open-ended work, check which model it runs: delegating-work, "Check what kind of agent you're handing it to".
Write so the receiver can act after one read. Open with the request, decision or change that affects their next step. Use full words and ordinary spacing. Keep the limits that change that step in the message; link the supporting detail. Put reference IDs and paths after the action. Send an additional message when it changes what the receiver should do. Put the complete request near the start of the task body; its summary helps discovery and does not replace reading the body.
This is writing guidance, not a delivery filter or length limit. Preserve uncertainty and limits that affect the action. Necessary early references, acknowledgements, requested progress updates and completion returns remain allowed. The sender judges how much context is useful.
Queue-body hygiene (token + parse safety)
The qitem body is durable DATA the daemon stores and replays on every
rig queue show <id> / --json read. Keep it small and parse-safe — a
bloated or malformed body costs every future reader, not just the
recipient.
No large command output in bodies. Do NOT paste rig ps/--nodes
dumps, big JSON blobs, full proof output, diffs, or transcript chunks
into a qitem body. Link the artifact PATH (e.g.
missions/<m>/<slice>/proof.md) or summarize in prose, then point
at the file for the detail. A pasted dump makes rig queue show <id> --full --json large. Compact defaults limit a preview, but the stored body
still costs readers who need full detail. Keep evidence in its durable artifact.
Substantive bodies go through --body-file, not inline --body.
For anything beyond a short line, write the body to a file and pass
--body-file <path> (or - for stdin). Inline --body with shell
metacharacters is fragile.
No raw backticks in bodies. Backticks in an inline body are shell
command-substitution and corrupt the payload (or execute). If you need
code/command spans, use --body-file, or drop the backticks and write
the command in plain text.
Heuristic: if the thing you want to include is more than a few lines or
contains shell metacharacters (backticks, $, quotes, newlines-with-pipes),
it belongs in a file you LINK, not in the body you paste.
The current rig queue show returns a bounded body preview by default;
--full returns the complete body and chain fields. Preview truncation does
not truncate the stored work. Check bodyTruncated and bodyBytes, then request
full content when needed; keep large supporting evidence in linked artifacts.
Failure modes (6; verbatim)
Agent ends a turn without a handoff, so the rig appears idle.
Agent creates a queue item with --no-nudge inside a live loop, intending suppression of attention but breaking immediate motion. --no-nudge is for intentional cold park / human gate, not for routine live-loop handoffs. The opposite footgun — adding a --notify flag that does not exist on the shipped 0.3.1 CLI — comes from following stale instructions; the default already nudges.
Queue item is too small and turns work into bureaucracy.
Queue item is too broad and loses ownership, proof, or closure criteria.
Human escalation happens in chat but not as a durable attention item.
Agent pastes a large command dump (ps/nodes, big JSON, proof blob) into the qitem body, bloating the stored DATA so every full-body read is large. Link the proof PATH or summarize in prose; substantive bodies go through --body-file; no raw backticks inline.
handed_off_from — predecessor qitem id (the source session is source_session)
state — one of: pending | in-progress | done | blocked | failed | denied | canceled | handed-off
closure_reason + closure_target — set on terminal closure per hot-potato rule
(0.5.0) --body-context <ref> — context riding the handoff.rig queue create … --body-context <ref> attaches a composed context pack to the qitem. The snapshot rule: the qitem stores the resolved content in its body plus the ref for provenance — the handoff carries what was actually sent, and a later edit to the library never silently rewrites a past handoff's history. (The rig context noun composes the ref; the queue delivers it — the noun has no send.) See openrig-user → "Context packs and paced delivery."
The fields are auditable on the daemon-backed rig queue surface. Watchdog
policies and workflow runtime project new owners off these fields.
If a daemon-backed coordination command fails, debug the command/runtime/schema
edge directly — don't fall back to stale pre-upgrade assumptions.