[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DMRCR8JFVH9A91N0T71A70":3,"skill-same:01M7DMRCR8JFVH9A91N0T71A70":59},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":36,"commitSha":37,"skillDirectory":38,"forksCount":39,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":41,"ownerBlogUrl":42,"ownerDescription":43,"updatedAt":44,"install":45,"resources":58},"01M7DMRCR8JFVH9A91N0T71A70","queue-handoff",null,"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.","mvschwarz\u002Fopenrig-world","mvschwarz","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F171890339?v=4","01M7DM95A4N5936P8G2FTSPMY7","Mike Schwarz","01M7DM95AX80NY8HZA7XXDYAZR",16,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Frigs\u002Fworkshop\u002Fagents\u002Fworkshop\u002Fskills\u002Fqueue-handoff\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: queue-handoff\ndescription: 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.\nmetadata:\n  cli_surfaces_referenced:\n    - queue\n    - queue create\n    - queue handoff\n    - queue handoff-and-complete\n  openrig:\n    stage: factory-approved\n    sibling_skills:\n      - watchdog\n      - refocusing\n      - human-in-the-loop\n---\n\n# Queue Handoff\n\nDurable work handoff via queue items. Lets the system keep moving\nthrough compactions, missed messages, and interruptions by passing the\nball forward instead of leaving work suspended in chat or in-flight\nwithout an owner.\n\n## Use this when\n\n- **Ending a turn on substantive work.** Active work should end by\n  passing the ball to an owner or to the human — never by going idle\n  with the rig appearing dormant.\n- **Finishing a slice that has a clear next step.** Default-nudge:\n  receiver gets a wake-ping plus the durable queue item.\n- **Blocked on another agent's work.** Use `rig queue block \u003Cid> --on \u003Cchild>`\n  (or `rig queue update \u003Cid> --state blocked --blocked-on \u003Cchild>`). The item\n  stays active and returns to pending when its blocker completes. Waiting on\n  something outside the queue, such as CI or a long job? Park the row:\n  `rig queue block \u003Cid> --on external:\u003Cwhat> --wake-after \u003Cduration>\n  --continuation \"\u003Cwhat resumes>\"`. It stays yours and reads parked, not\n  stalled, and the timer wakes you.\n- **Escalating to the human.** Make the escalation a durable attention\n  item, not just a chat message.\n\n## Don't use this when\n\n- The work is genuinely complete and there's no follow-on owner. Use\n  `closure_reason: no-follow-on` (terminal completion) or\n  `canceled`\u002F`denied` as appropriate.\n- The handoff would be too small and turn work into bureaucracy. Bundle\n  the work into a coherent slice instead of decomposing every step.\n- The handoff would be too broad and lose ownership\u002Fproof\u002Fclosure\n  criteria. Shape the qitem so the receiver knows the expected next\n  action and closure evidence.\n\n## The hot-potato terminal-turn-rule\n\nActive work ends by passing the ball to a named next owner or to the\nhuman. The qitem state machine enforces this:\n\n`pending → in-progress → done` requires `closure_reason` from one of:\n\n- `handed_off_to` — work continues at a different seat (target = new owner)\n- `denied` — receiver rejected the work\n- `canceled` — sender or receiver withdrew\n- `no-follow-on` — terminal completion, nothing else needed\n- `escalation` — kicked up to a higher tier (target = escalation target)\n- `superseded` — replaced by another qitem (target = successor qitem id)\n\nTwo of those (`handed_off_to`, `escalation`) additionally\nrequire `closure_target`. The daemon enforces this at the domain layer;\nevery surface (CLI, MCP, future UI) inherits the same guarantee.\n\n`done` is terminal. `closure_reason: blocked_on` is valid only on an active\n`state=blocked` park record, as used by workflow writers; combining it with\n`state=done` is rejected. Use the block command above to wait on another qitem.\n\n**The drafted-park failure (draft ≠ throw).** The rule is about the *actual* pass, not the\nintention to pass. A turn that ends with a self-instruction **typed into your own prompt but left\nunsent** — a drafted go-ahead, a next-atom note you never sent — has **not** handed off; it has\n**parked**, and the seat sits idle for as long as nobody notices. Drafting the handoff feels like\ndoing it; it isn't. **Your last act on a turn must be an EDIT or a SEND** — a committed change, a\n`rig send`, a `rig queue` handoff — **never a drafted prompt line left in the buffer.** If your\nfinal output is an instruction addressed to yourself, you haven't ended the turn, you've stalled it.\n\n**The dispatcher's other half — supersession closes your own outbox.** Ending your turn cleanly is\nonly half the rule; the other half fires when *you* move the world. **When a phase transition or a\nfold receipt supersedes work you dispatched, close those dispatches yourself — with a citation to the\nevent that superseded them.** Closure-on-supersession belongs to the **dispatcher, never the\nreceiver.** Make it a habit: after every fold receipt \u002F phase transition, run an **outbox audit** —\n*which of my open dispatches did this just make moot?* — and close them with the citation.\n\n*Why it must live with you:* stale dispatch-debt is **invisible to the dispatcher** because it lands\non someone else's queue — the cost is externalized, so no feedback loop ever fires to make you clean\nit up. The receiver inherits debt they did not create and must burn cycles verifying it before they\ncan hold cleanly; a queue full of stale-pending makes *check-before-holding* — the discipline you\nmost want cheap — expensive, and it degrades the idle-detector's signal (a real owner looks the same\nas a stale dispatch). Close it at the source: the moment your own transition mooted it.\n\n**And after you hand off, PULL — don't idle with a stocked queue.** Handing the baton off ends the\n*sequential* thread; it does not end *your* turn if your own queue still holds work. The circulation\npattern: finish → (1) hand the baton off so sequential work continues → (2) **check your OWN queue and\npull the next item** rather than going idle → (3) go truly idle only when your queue is **exhausted**,\nthen wait for the baton. An agent idling on top of a stocked queue is the single biggest utilization\nleak (see `orchestration-team` → *queue depth is the orchestrator's product*). This is pull-not-push at\nthe seat level and needs no new machinery — the last act *after a handoff* is a **PULL**.\n\n## Default-nudge semantics (the syntax footgun)\n\n| Command | Nudges by default? | When to use |\n|---|---|---|\n| `rig queue create` | yes | New qitem created from scratch |\n| `rig queue handoff` | yes | Transactional close-as-handed-off + create-new |\n| `rig queue handoff-and-complete` | yes | Atomic close + create-new; default nudge wakes the new owner |\n\n**Footgun**: `--no-nudge` accidentally added to a live-loop handoff.\nThe shipped 0.3.1 CLI nudges by default on every queue write surface\n(`rig queue create`, `rig queue handoff`, AND `rig queue handoff-and-complete`).\nThe only suppression flag is `--no-nudge` — appropriate for intentional\ncold park, human-gate signal, or a deliberate poll-driven workflow, but\nNOT for live-loop handoffs where motion matters.\n\n**Rule**: in a live loop, omit `--no-nudge` and trust the default.\n`--no-nudge` is the opt-out, not the opt-in. If you find yourself\nreaching for `--notify`, stop — that flag does not exist on the\nshipped 0.3.1 CLI; you may be following a stale instruction that\ninverted the default-nudge polarity.\n\n## Every queue row\n\n- **`--summary \"\u003Cwhat 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.\n- **Scope tags `project:\u003Cid>`, `mission:\u003Cid>`, `slice:\u003Cid>`** 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`.\n- **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.\n- **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.\n- **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\".\n- **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\".\n\n**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.\n\nThis 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.\n\n## Queue-body hygiene (token + parse safety)\n\nThe qitem body is durable DATA the daemon stores and replays on every\n`rig queue show \u003Cid>` \u002F `--json` read. Keep it small and parse-safe — a\nbloated or malformed body costs every future reader, not just the\nrecipient.\n\n- **No large command output in bodies.** Do NOT paste `rig ps`\u002F`--nodes`\n  dumps, big JSON blobs, full proof output, diffs, or transcript chunks\n  into a qitem body. **Link the artifact PATH** (e.g.\n  `missions\u002F\u003Cm>\u002F\u003Cslice>\u002Fproof.md`) or **summarize in prose**, then point\n  at the file for the detail. A pasted dump makes `rig queue show \u003Cid>\n  --full --json` large. Compact defaults limit a preview, but the stored body\n  still costs readers who need full detail. Keep evidence in its durable artifact.\n- **Substantive bodies go through `--body-file`, not inline `--body`.**\n  For anything beyond a short line, write the body to a file and pass\n  `--body-file \u003Cpath>` (or `-` for stdin). Inline `--body` with shell\n  metacharacters is fragile.\n- **No raw backticks in bodies.** Backticks in an inline body are shell\n  command-substitution and corrupt the payload (or execute). If you need\n  code\u002Fcommand spans, use `--body-file`, or drop the backticks and write\n  the command in plain text.\n\nHeuristic: if the thing you want to include is more than a few lines or\ncontains shell metacharacters (backticks, `$`, quotes, newlines-with-pipes),\nit belongs in a file you LINK, not in the body you paste.\n\nThe current `rig queue show` returns a bounded body preview by default;\n`--full` returns the complete body and chain fields. Preview truncation does\nnot truncate the stored work. Check `bodyTruncated` and `bodyBytes`, then request\nfull content when needed; keep large supporting evidence in linked artifacts.\n\n## Failure modes (6; verbatim)\n\n1. Agent ends a turn without a handoff, so the rig appears idle.\n2. 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 \u002F 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.\n3. Queue item is too small and turns work into bureaucracy.\n4. Queue item is too broad and loses ownership, proof, or closure criteria.\n5. Human escalation happens in chat but not as a durable attention item.\n6. Agent pastes a large command dump (ps\u002Fnodes, 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.\n\n## Durable handoff field shape\n\nEvery qitem carries:\n\n- `handed_off_to` — destination session (qualified `pod-member@rig` form)\n- `handed_off_from` — predecessor qitem id (the source session is `source_session`)\n- `state` — one of: `pending | in-progress | done | blocked | failed | denied | canceled | handed-off`\n- `closure_reason` + `closure_target` — set on terminal closure per hot-potato rule\n\n**(0.5.0) `--body-context \u003Cref>` — context riding the handoff.** `rig queue create … --body-context \u003Cref>` 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.\"\n\nThe fields are auditable on the daemon-backed `rig queue` surface. Watchdog\npolicies and workflow runtime project new owners off these fields.\n\nIf a daemon-backed coordination command fails, debug the command\u002Fruntime\u002Fschema\nedge directly — don't fall back to stale pre-upgrade assumptions.\n","# Queue Handoff\n\nDurable work handoff via queue items. Lets the system keep moving\nthrough compactions, missed messages, and interruptions by passing the\nball forward instead of leaving work suspended in chat or in-flight\nwithout an owner.\n\n## Use this when\n\n- **Ending a turn on substantive work.** Active work should end by\n  passing the ball to an owner or to the human — never by going idle\n  with the rig appearing dormant.\n- **Finishing a slice that has a clear next step.** Default-nudge:\n  receiver gets a wake-ping plus the durable queue item.\n- **Blocked on another agent's work.** Use `rig queue block \u003Cid> --on \u003Cchild>`\n  (or `rig queue update \u003Cid> --state blocked --blocked-on \u003Cchild>`). The item\n  stays active and returns to pending when its blocker completes. Waiting on\n  something outside the queue, such as CI or a long job? Park the row:\n  `rig queue block \u003Cid> --on external:\u003Cwhat> --wake-after \u003Cduration>\n  --continuation \"\u003Cwhat resumes>\"`. It stays yours and reads parked, not\n  stalled, and the timer wakes you.\n- **Escalating to the human.** Make the escalation a durable attention\n  item, not just a chat message.\n\n## Don't use this when\n\n- The work is genuinely complete and there's no follow-on owner. Use\n  `closure_reason: no-follow-on` (terminal completion) or\n  `canceled`\u002F`denied` as appropriate.\n- The handoff would be too small and turn work into bureaucracy. Bundle\n  the work into a coherent slice instead of decomposing every step.\n- The handoff would be too broad and lose ownership\u002Fproof\u002Fclosure\n  criteria. Shape the qitem so the receiver knows the expected next\n  action and closure evidence.\n\n## The hot-potato terminal-turn-rule\n\nActive work ends by passing the ball to a named next owner or to the\nhuman. The qitem state machine enforces this:\n\n`pending → in-progress → done` requires `closure_reason` from one of:\n\n- `handed_off_to` — work continues at a different seat (target = new owner)\n- `denied` — receiver rejected the work\n- `canceled` — sender or receiver withdrew\n- `no-follow-on` — terminal completion, nothing else needed\n- `escalation` — kicked up to a higher tier (target = escalation target)\n- `superseded` — replaced by another qitem (target = successor qitem id)\n\nTwo of those (`handed_off_to`, `escalation`) additionally\nrequire `closure_target`. The daemon enforces this at the domain layer;\nevery surface (CLI, MCP, future UI) inherits the same guarantee.\n\n`done` is terminal. `closure_reason: blocked_on` is valid only on an active\n`state=blocked` park record, as used by workflow writers; combining it with\n`state=done` is rejected. Use the block command above to wait on another qitem.\n\n**The drafted-park failure (draft ≠ throw).** The rule is about the *actual* pass, not the\nintention to pass. A turn that ends with a self-instruction **typed into your own prompt but left\nunsent** — a drafted go-ahead, a next-atom note you never sent — has **not** handed off; it has\n**parked**, and the seat sits idle for as long as nobody notices. Drafting the handoff feels like\ndoing it; it isn't. **Your last act on a turn must be an EDIT or a SEND** — a committed change, a\n`rig send`, a `rig queue` handoff — **never a drafted prompt line left in the buffer.** If your\nfinal output is an instruction addressed to yourself, you haven't ended the turn, you've stalled it.\n\n**The dispatcher's other half — supersession closes your own outbox.** Ending your turn cleanly is\nonly half the rule; the other half fires when *you* move the world. **When a phase transition or a\nfold receipt supersedes work you dispatched, close those dispatches yourself — with a citation to the\nevent that superseded them.** Closure-on-supersession belongs to the **dispatcher, never the\nreceiver.** Make it a habit: after every fold receipt \u002F phase transition, run an **outbox audit** —\n*which of my open dispatches did this just make moot?* — and close them with the citation.\n\n*Why it must live with you:* stale dispatch-debt is **invisible to the dispatcher** because it lands\non someone else's queue — the cost is externalized, so no feedback loop ever fires to make you clean\nit up. The receiver inherits debt they did not create and must burn cycles verifying it before they\ncan hold cleanly; a queue full of stale-pending makes *check-before-holding* — the discipline you\nmost want cheap — expensive, and it degrades the idle-detector's signal (a real owner looks the same\nas a stale dispatch). Close it at the source: the moment your own transition mooted it.\n\n**And after you hand off, PULL — don't idle with a stocked queue.** Handing the baton off ends the\n*sequential* thread; it does not end *your* turn if your own queue still holds work. The circulation\npattern: finish → (1) hand the baton off so sequential work continues → (2) **check your OWN queue and\npull the next item** rather than going idle → (3) go truly idle only when your queue is **exhausted**,\nthen wait for the baton. An agent idling on top of a stocked queue is the single biggest utilization\nleak (see `orchestration-team` → *queue depth is the orchestrator's product*). This is pull-not-push at\nthe seat level and needs no new machinery — the last act *after a handoff* is a **PULL**.\n\n## Default-nudge semantics (the syntax footgun)\n\n| Command | Nudges by default? | When to use |\n|---|---|---|\n| `rig queue create` | yes | New qitem created from scratch |\n| `rig queue handoff` | yes | Transactional close-as-handed-off + create-new |\n| `rig queue handoff-and-complete` | yes | Atomic close + create-new; default nudge wakes the new owner |\n\n**Footgun**: `--no-nudge` accidentally added to a live-loop handoff.\nThe shipped 0.3.1 CLI nudges by default on every queue write surface\n(`rig queue create`, `rig queue handoff`, AND `rig queue handoff-and-complete`).\nThe only suppression flag is `--no-nudge` — appropriate for intentional\ncold park, human-gate signal, or a deliberate poll-driven workflow, but\nNOT for live-loop handoffs where motion matters.\n\n**Rule**: in a live loop, omit `--no-nudge` and trust the default.\n`--no-nudge` is the opt-out, not the opt-in. If you find yourself\nreaching for `--notify`, stop — that flag does not exist on the\nshipped 0.3.1 CLI; you may be following a stale instruction that\ninverted the default-nudge polarity.\n\n## Every queue row\n\n- **`--summary \"\u003Cwhat 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.\n- **Scope tags `project:\u003Cid>`, `mission:\u003Cid>`, `slice:\u003Cid>`** 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`.\n- **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.\n- **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.\n- **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\".\n- **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\".\n\n**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.\n\nThis 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.\n\n## Queue-body hygiene (token + parse safety)\n\nThe qitem body is durable DATA the daemon stores and replays on every\n`rig queue show \u003Cid>` \u002F `--json` read. Keep it small and parse-safe — a\nbloated or malformed body costs every future reader, not just the\nrecipient.\n\n- **No large command output in bodies.** Do NOT paste `rig ps`\u002F`--nodes`\n  dumps, big JSON blobs, full proof output, diffs, or transcript chunks\n  into a qitem body. **Link the artifact PATH** (e.g.\n  `missions\u002F\u003Cm>\u002F\u003Cslice>\u002Fproof.md`) or **summarize in prose**, then point\n  at the file for the detail. A pasted dump makes `rig queue show \u003Cid>\n  --full --json` large. Compact defaults limit a preview, but the stored body\n  still costs readers who need full detail. Keep evidence in its durable artifact.\n- **Substantive bodies go through `--body-file`, not inline `--body`.**\n  For anything beyond a short line, write the body to a file and pass\n  `--body-file \u003Cpath>` (or `-` for stdin). Inline `--body` with shell\n  metacharacters is fragile.\n- **No raw backticks in bodies.** Backticks in an inline body are shell\n  command-substitution and corrupt the payload (or execute). If you need\n  code\u002Fcommand spans, use `--body-file`, or drop the backticks and write\n  the command in plain text.\n\nHeuristic: if the thing you want to include is more than a few lines or\ncontains shell metacharacters (backticks, `$`, quotes, newlines-with-pipes),\nit belongs in a file you LINK, not in the body you paste.\n\nThe current `rig queue show` returns a bounded body preview by default;\n`--full` returns the complete body and chain fields. Preview truncation does\nnot truncate the stored work. Check `bodyTruncated` and `bodyBytes`, then request\nfull content when needed; keep large supporting evidence in linked artifacts.\n\n## Failure modes (6; verbatim)\n\n1. Agent ends a turn without a handoff, so the rig appears idle.\n2. 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 \u002F 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.\n3. Queue item is too small and turns work into bureaucracy.\n4. Queue item is too broad and loses ownership, proof, or closure criteria.\n5. Human escalation happens in chat but not as a durable attention item.\n6. Agent pastes a large command dump (ps\u002Fnodes, 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.\n\n## Durable handoff field shape\n\nEvery qitem carries:\n\n- `handed_off_to` — destination session (qualified `pod-member@rig` form)\n- `handed_off_from` — predecessor qitem id (the source session is `source_session`)\n- `state` — one of: `pending | in-progress | done | blocked | failed | denied | canceled | handed-off`\n- `closure_reason` + `closure_target` — set on terminal closure per hot-potato rule\n\n**(0.5.0) `--body-context \u003Cref>` — context riding the handoff.** `rig queue create … --body-context \u003Cref>` 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.\"\n\nThe fields are auditable on the daemon-backed `rig queue` surface. Watchdog\npolicies and workflow runtime project new owners off these fields.\n\nIf a daemon-backed coordination command fails, debug the command\u002Fruntime\u002Fschema\nedge directly — don't fall back to stale pre-upgrade assumptions.\n",{"name":5,"metadata":24,"description":7},{"openrig":25,"cli_surfaces_referenced":31},{"stage":26,"sibling_skills":27},"factory-approved",[28,29,30],"watchdog","refocusing","human-in-the-loop",[32,33,34,35],"queue","queue create","queue handoff","queue handoff-and-complete","main","60438a272b68d091eddb01aad6e399af4996d536","rigs\u002Fworkshop\u002Fagents\u002Fworkshop\u002Fskills\u002Fqueue-handoff",4,"https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world","https:\u002F\u002Fgithub.com\u002Fmvschwarz","https:\u002F\u002Fopenrig.dev","Building OpenRig. Running rogue AI civilizations. Debugging their coordination problems.","2026-11-12 13:31:38",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add mvschwarz\u002Fopenrig-world --skill queue-handoff",{"tool":51,"command":52},"bunx","bunx skills add mvschwarz\u002Fopenrig-world --skill queue-handoff",{"tool":54,"command":55},"pnpm","pnpm dlx skills add mvschwarz\u002Fopenrig-world --skill queue-handoff","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Frigs\u002Fworkshop\u002Fagents\u002Fworkshop\u002Fskills\u002Fqueue-handoff\u002FSKILL.md",true,[],[60,67,74,81,88,95],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7DMSEDCRREMBJF57RQB59HC","notes","Use when taking notes.","https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Ftools\u002Ftest\u002Ffixtures\u002Finstall-verify\u002Fbundle\u002Fagents\u002Fteam\u002Fskills\u002Fnotes\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7DMSBZP9WE8MC09JDXFCR2F","software-for-agents","Use when older OpenRig instructions name software-for-agents or describe agent-in-the-middle or studio software under the former skill name.","https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Frigs\u002Fworkshop\u002Fagents\u002Fworkshop\u002Fskills\u002Fsoftware-for-agents\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7DMS55VHEAGPXMHZJ7FX94R","session-compaction-and-restore","Use when reasoning about what survives compaction\u002Fcontext-loss\u002Frestart\u002Fseat-refresh, designing a high-fidelity restore packet, or distinguishing native runtime resume vs fork vs artifact-backed mental-model rebuild. Covers the 4 failure modes that prevent honest restore (compacted seat drops hot potato; restore packet preserves details but loses product intent; runtime resume mistaken for handover or fork; rebuilt seat starts with stale instructions).","https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Frigs\u002Fworkshop\u002Fagents\u002Fworkshop\u002Fskills\u002Fsession-compaction-and-restore\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7DMRYQK0JTV7MMVHFWZ0BW0","seat-continuity-and-handover","Use when replacing a seat's occupant (rebuild\u002Fhandover\u002Fswap), reasoning about stable-seat-identity vs fluid-occupant-identity, choosing an old-occupant disposition (retire\u002Fadvise\u002Fshadow), or recording provenance for an occupant change. Two independent outcomes (continuityOutcome + seatBindingOutcome) and the 5 failure modes that prevent silent dishonesty.","https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Frigs\u002Fworkshop\u002Fagents\u002Fworkshop\u002Fskills\u002Fseat-continuity-and-handover\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7DMRP6RRGCJZSH9CE3PC1MY","retiring-and-inheriting-a-seat","Use when you are a sitting agent near your context threshold (~85%) and a PLANNED seat transition is due — retire deliberately and hand your seat to a fresh successor primed from a packet, rather than let compaction degrade you. Covers the handover packet, the append-only lineage ledger (one row per tenure), physical-seat continuity, the do-not-over-inherit framing, the optional warm-handoff window, and wake-v0 (consulting a retired predecessor). NOT for unplanned compaction\u002Fcrash recovery (session-compaction-and-restore \u002F claude-compaction-restore) and NOT the seat-binding primitive mechanics (seat-continuity-and-handover).","https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Frigs\u002Fworkshop\u002Fagents\u002Fworkshop\u002Fskills\u002Fretiring-and-inheriting-a-seat\u002FSKILL.md",[],[],{"skillNo":96,"name":29,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7DMRJGN6Z8TZDR7JNHXH6KX","Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.","https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Frigs\u002Fworkshop\u002Fagents\u002Fworkshop\u002Fskills\u002Frefocusing\u002FSKILL.md",[],[]]