[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DMRP6RRGCJZSH9CE3PC1MY":3,"skill-same:01M7DMRP6RRGCJZSH9CE3PC1MY":64},{"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":35,"commitSha":36,"skillDirectory":37,"forksCount":38,"repositoryHtmlUrl":39,"repositoryHomepageUrl":6,"ownerHtmlUrl":40,"ownerBlogUrl":41,"ownerDescription":42,"updatedAt":43,"install":44,"resources":57},"01M7DMRP6RRGCJZSH9CE3PC1MY","retiring-and-inheriting-a-seat",null,"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).","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\u002Fretiring-and-inheriting-a-seat\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: retiring-and-inheriting-a-seat\ndescription: 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).\nmetadata:\n  openrig:\n    stage: provisional\n    sibling_skills:\n      - orienting-to-an-inherited-seat\n      - session-compaction-and-restore\n      - seat-continuity-and-handover\n      - claude-compaction-restore\n      - agent-starters\n      - queue-handoff\n      - openrig-user\n---\n\n# Retiring and Inheriting a Seat\n\nA **planned** seat transition. A long-lived seat accumulates context; as it nears the\nwindow's edge, don't wait for compaction to degrade you into a cold-started agent —\n**retire deliberately** and hand the seat to a fresh successor primed from a packet plus\nthe seat's accumulated lineage. The **seat address is stable; its occupants are a lineage.**\nKeep the transition and its authority explicit.\n\n## Use this when\n\n- You are a sitting agent near your context threshold (~85%) with a **planned** transition\n  (or a deliberate role change), and want the successor to start clean.\n- You are priming a fresh successor into an **existing** seat.\n- You are recording a tenure in the seat's lineage ledger \u002F writing your tombstone.\n- You are **inheriting** a seat and need the do-not-over-inherit framing.\n- You want to consult the agent who sat in this seat before you.\n\n## Don't use this when\n\n- Unplanned compaction or a crash already happened — that is the backstop path:\n  `session-compaction-and-restore` \u002F `claude-compaction-restore`.\n- You need the seat-binding **primitive mechanics** (rebuild\u002Ffork\u002Ffresh, the two-outcome\n  honesty model, the provenance schema) — `seat-continuity-and-handover`.\n- The seat is fresh with no occupant to retire — `rig launch` \u002F `agent-starters`.\n\n## Why planned handover beats riding compaction\n\nCompaction is the **crash-class backstop** (it stays that). A **planned** handover is\ndeliberate: you author the packet with a clear head *before* degradation sets in, the\nsuccessor starts on a clean context, and the transition is auditable. Reach for this at a\nthreshold you can see coming; fall back to compaction only when a transition wasn't planned.\n\n## The handover sequence\n\n1. **Trigger** — the selected continuity threshold or a deliberate role transition.\n   Use the configured policy and named transition owner; a context estimate alone\n   does not authorize a cutover.\n2. **Author the handover packet, deliberately** — a composed context pack carrying current\n   work + next owner, the seat's durable pointers, constraints and authority boundaries, and\n   the accumulated **lineage wisdom** (\"those before you learned X\"). This IS a restore packet\n   in the `session-compaction-and-restore` 16-field contract — **reuse that contract, don't\n   reinvent it.** Compose it with `rig context compose` (see openrig-user → \"Context packs and\n   paced delivery\").\n   **Enumerate the seat's standing duties as first-class packet content:** what recurs, at what\n   cadence, on which surface, and who will hold it after cutover. Carry each duty both in this\n   packet and in durable seat state, because recurring duties are the content most often lost at\n   a generation boundary while urgent one-off work carries cleanly.\n   **Write the seat's recap too:** run `rig context recap-write --file \u003Cdraft>`\n   alongside updating `LEARNED.md`. A `rebuild` reads `RECAP.md` before anything else. The format\n   the store checks is in `seat-continuity-and-handover`, \"Write the seat's recap before a handover\".\n3. **Prime the fresh successor** — `rig walk` the packet into the seat (paced delivery lets the\n   successor absorb it in order), or launch-with-packet. The successor reads it as\n   *inheritance*, not *identity*. **The packet's first-read line MUST point the successor at\n   `orienting-to-an-inherited-seat`** — its world model of what a handover *is*. Carry that\n   pointer **in the durable packet artifact itself**; never inject it as a runtime prompt keyed\n   to the seat name (that runtime mechanism is the **ghost-prompt** class the orientation skill\n   teaches successors to refuse). Artifact-carried\n   survives the swap for free and needs no enabled gate.\n4. **Assess before cutover.** If an apprenticeship or warm handoff is selected,\n   use that staged window for questions and domain work before the owner decides.\n   The incumbent retains authority until the owner-worded cutover; do not retire\n   it merely to free a name while waiting for that decision.\n5. **Preserve the physical seat at cutover** — follow the portable SOP linked from\n   `seat-continuity-and-handover`. Keep the canonical tmux session, window and pane;\n   resume the exact accepted successor history there and reconcile binding,\n   environment, queue identity and attached clients. Preserve the incumbent's\n   exact token as a cold-advisor handle when that is the selected disposition.\n   Renaming tmux sessions is a repair fallback, not the default sequence.\n6. **Write the lineage-ledger row and tombstone** (below). Record the actual\n   outcomes and transfer each standing duty explicitly. Complete the successor's\n   post-cutover self-check before unfreezing authority.\n\n## Apprentice mode — incumbent\n\nAn `apprentice-handover` policy gives you an early preparation boundary, not permission to\nautomate the succession decision. Create a fresh, staged, unbound successor; prove the pinned\nmodel before installing context; then open a **conversation, not a gauntlet**. Give coached\nerrands, answer questions, and judge work in the real domain. Scored probes are optional tools whose rigor must match the stakes, not\nmandatory ceremony.\n\nStay the authority-bearing incumbent until the named owner words the gate and the mechanic records\nthe effect receipt. Before that word, the apprentice may observe, ask, and produce evidence but may\nnot act as the seat. Enumerate deposits and transfer every standing duty explicitly, **because\nrecurring duties** are otherwise easy to lose while visible one-off work appears complete. Put the\nmechanical cutover in the portable SOP linked from `seat-continuity-and-handover`; do not duplicate\nor improvise it here.\n\n## The lineage ledger (append-only, one row per tenure)\n\nThe seat's tenure record, written at handover **by the retiring agent**. One tiny row per\ntenure:\n\n- **generation** — `v1`, `v2`, … (a seat accumulates 20–40 tenures over months)\n- **harness session id** — **captured AT BOOT**, not at retirement (a crash never gets the\n  chance to write it later)\n- **started \u002F retired** timestamps\n- **handover-packet pointer** — the pack ref\n- **tombstone** — one line: what this tenure did, written by the retiring agent itself\n\n**Why it works (zero search infrastructure):** any timestamped record — a git commit, a\nqitem, a NOTES.md line, a stream item — joins to the seat's ledger by interval match →\ngeneration + session token → wake that tenure. One row per handover, append-only. The\nledger is the tenure record; work-tree notes remain lived context, not identity state.\n\n**Crash-ended tenures** get their row appended **post-hoc** by the crash-cart \u002F restore path,\nflagged **honest-approximate** (the boot-captured session id is what makes this recoverable).\n\n## Inherit the seat, not the predecessor's identity\n\n**You are inheriting a seat, not becoming your predecessor.** Frame it explicitly to the\nsuccessor: *\"agents sat here before you and learned X; you carry the seat's mission, not their\nidentity.\"* Do not claim a predecessor's work as your own or use its stale identity\nas the current binding. Inherit the\nseat's **mission and hard-won lessons**; keep your own **fresh identity and session**.\n\n## Reach back to a retained predecessor\n\nA retired tenure is a cold advisor you can consult. Look up the seat's ledger → get that\ngeneration's session token → resume it for **one question**, then let it sleep again:\n\n- Claude: `claude -p --resume \u003Csession>`\n- Codex: `codex exec` (resume the rollout)\n\nUse `rig ask \u003Crig> \"\u003Cq>\" --wake \u003Ctarget>` for an explicit bounded consultation\n(introduced in CLI 0.5.1). Wake seat targets must include the rig: `member@rig` or\n`member@rig@N` (1 = newest tenure). Values without `@` go unchanged to the runtime\nas a session ID or title; a bare member name is not resolved within `\u003Crig>`.\nCheck `rig ask --help` for `--runtime`\nand `--wake-timeout`. The wrapper uses a runtime resume; its presence is not\nproof that a particular retained history is available. For a Claude history,\n`claude -p --resume \u003Cfull-uuid>` is the runtime-level fallback when supported.\nDiagnose the specific failure before declaring the channel unavailable.\n\n**What to write in your packet about reaching you** — your successor asking you questions is the\nreason this is a handover and not a compaction:\n\n- **Give your verbatim resume handle and known availability limits.** Retirement alone\n  does not expire retained history. Resuming still depends on that history, runtime\n  access and remaining context; distinguish these failure modes. The advisor\n  supplies testimony and does not regain the live seat's authority.\n- **Pre-form the questions.** Inventory what only you hold and write the questions out. An affordance\n  needs a trigger: name the tradeoff, missing rationale or conflict that should prompt a question.\n\n**Wake-tenancy — the identity halves (a woken tenure can mistake itself for the live seat).** The\nhardest thing to apply *checked-not-believed* to is your own identity — a retired tenure resumed for a\nquestion can answer, and act, as if it still held the seat. Two rules close it:\n\n- **Waker: disclose the target's tenure status in the wake prompt.** Open with *\"you are retired; gen-N\n  holds this seat now — I'm consulting you for one question.\"* An oriented tenure gives honest testimony;\n  an un-oriented one may reason as the live occupant.\n- **Woken: verify your OWN tenancy before your first act.** If you are being resumed \u002F woken (a parked or\n  retired session, or any session waking on a seat that already issued READY), your **first** check is\n  `rig whoami` + a **successor check** — confirm whether you are still the live occupant or a successor\n  now holds the seat, *before* you do anything. Answer the question; do not resume the job.\n\n## Failure modes\n\n1. **Riding compaction when a planned handover was available** — a degraded agent authors a\n   degraded packet. Retire deliberately at the threshold you can see coming.\n2. **Over-inheriting** — the successor believes it *is* the predecessor (stale self-model,\n   mis-claimed history). Frame inheritance explicitly; keep a fresh identity.\n3. **Session id captured at retirement, not boot** — a crash then leaves no row, or an\n   unfindable tenure. Capture at boot.\n4. **Suffixing the LIVE seat** (`\u003Cseat>-v2` as the active address) — lineage leaking into\n   identity, the wrong shape. The live address stays clean; generation belongs in the ledger.\n5. **Tombstone omitted or vague** — the ledger can no longer answer \"who did this \u002F who to\n   wake.\" One honest line, every tenure.\n\n## Checks around a planned transition\n\n- **Stage and assess before the owner calls cutover.** Use startup context when the\n  successor is unbound; check its actual address before relying on registry-routed\n  delivery. Keep incumbent authority and physical-pane custody until the selected\n  SOP's cutover steps apply. A rejected candidate does not require renaming the\n  incumbent back into a seat it should still hold.\n- **Preserve exact resume handles.** A retained advisor may have no managed node or\n  live pane. The ledger identifies its history independently of the live-seat\n  registry; absence from `rig ps` alone does not prove that history is gone.\n- **Recheck work at the boundary.** Queue items can arrive after the packet was\n  frozen. The successor reads its current owned queue, reconciles transition-window\n  work and staged inputs, and records every remaining obligation.\n- **Verify identity across surfaces.** Canonical binding, provider history,\n  process environment, queue identity and attached clients must agree. Correct a\n  staged identity residue through the supported cutover\u002Freconciliation path;\n  renaming a tmux session alone is not proof that those surfaces agree.\n- **Keep incomplete evidence explicit.** Flag unavailable activity telemetry as\n  unavailable, and mark a tombstone written by someone else as approximate.\n- **Coordinate the maintenance window.** Tell the routing\u002Fmonitoring owner the\n  target and expected window before an authorized cutover. Only an explicitly\n  configured suppression changes monitoring behavior; close the window with the\n  actual effect receipt, deviations and unresolved gaps.\n\nThese are verification prompts, not a claim that a particular runtime transition\nhas passed. Use the linked portable SOP for mechanics and record the actual run.\n\n## See also\n\n- `orienting-to-an-inherited-seat` — the **successor-side** world model your packet points\n  them at (loaded at boot); the load-bearing counterpart to this driver-side mechanic.\n- `session-compaction-and-restore` — the 16-field packet contract this practice reuses, and\n  the UNPLANNED-compaction backstop it replaces for *planned* transitions.\n- `seat-continuity-and-handover` — the seat-binding primitive mechanics + stable-seat-identity\n  architecture; the lineage ledger is the concrete form of its abstract provenance record.\n- `openrig-user` → \"Context packs and paced delivery\" — `rig context compose` + `rig walk`, to\n  author and deliver the packet.\n- `claude-compaction-restore` — the Claude crash-class restore SOP.\n- `agent-starters` — composing a primed starting point for the successor.\n","# Retiring and Inheriting a Seat\n\nA **planned** seat transition. A long-lived seat accumulates context; as it nears the\nwindow's edge, don't wait for compaction to degrade you into a cold-started agent —\n**retire deliberately** and hand the seat to a fresh successor primed from a packet plus\nthe seat's accumulated lineage. The **seat address is stable; its occupants are a lineage.**\nKeep the transition and its authority explicit.\n\n## Use this when\n\n- You are a sitting agent near your context threshold (~85%) with a **planned** transition\n  (or a deliberate role change), and want the successor to start clean.\n- You are priming a fresh successor into an **existing** seat.\n- You are recording a tenure in the seat's lineage ledger \u002F writing your tombstone.\n- You are **inheriting** a seat and need the do-not-over-inherit framing.\n- You want to consult the agent who sat in this seat before you.\n\n## Don't use this when\n\n- Unplanned compaction or a crash already happened — that is the backstop path:\n  `session-compaction-and-restore` \u002F `claude-compaction-restore`.\n- You need the seat-binding **primitive mechanics** (rebuild\u002Ffork\u002Ffresh, the two-outcome\n  honesty model, the provenance schema) — `seat-continuity-and-handover`.\n- The seat is fresh with no occupant to retire — `rig launch` \u002F `agent-starters`.\n\n## Why planned handover beats riding compaction\n\nCompaction is the **crash-class backstop** (it stays that). A **planned** handover is\ndeliberate: you author the packet with a clear head *before* degradation sets in, the\nsuccessor starts on a clean context, and the transition is auditable. Reach for this at a\nthreshold you can see coming; fall back to compaction only when a transition wasn't planned.\n\n## The handover sequence\n\n1. **Trigger** — the selected continuity threshold or a deliberate role transition.\n   Use the configured policy and named transition owner; a context estimate alone\n   does not authorize a cutover.\n2. **Author the handover packet, deliberately** — a composed context pack carrying current\n   work + next owner, the seat's durable pointers, constraints and authority boundaries, and\n   the accumulated **lineage wisdom** (\"those before you learned X\"). This IS a restore packet\n   in the `session-compaction-and-restore` 16-field contract — **reuse that contract, don't\n   reinvent it.** Compose it with `rig context compose` (see openrig-user → \"Context packs and\n   paced delivery\").\n   **Enumerate the seat's standing duties as first-class packet content:** what recurs, at what\n   cadence, on which surface, and who will hold it after cutover. Carry each duty both in this\n   packet and in durable seat state, because recurring duties are the content most often lost at\n   a generation boundary while urgent one-off work carries cleanly.\n   **Write the seat's recap too:** run `rig context recap-write --file \u003Cdraft>`\n   alongside updating `LEARNED.md`. A `rebuild` reads `RECAP.md` before anything else. The format\n   the store checks is in `seat-continuity-and-handover`, \"Write the seat's recap before a handover\".\n3. **Prime the fresh successor** — `rig walk` the packet into the seat (paced delivery lets the\n   successor absorb it in order), or launch-with-packet. The successor reads it as\n   *inheritance*, not *identity*. **The packet's first-read line MUST point the successor at\n   `orienting-to-an-inherited-seat`** — its world model of what a handover *is*. Carry that\n   pointer **in the durable packet artifact itself**; never inject it as a runtime prompt keyed\n   to the seat name (that runtime mechanism is the **ghost-prompt** class the orientation skill\n   teaches successors to refuse). Artifact-carried\n   survives the swap for free and needs no enabled gate.\n4. **Assess before cutover.** If an apprenticeship or warm handoff is selected,\n   use that staged window for questions and domain work before the owner decides.\n   The incumbent retains authority until the owner-worded cutover; do not retire\n   it merely to free a name while waiting for that decision.\n5. **Preserve the physical seat at cutover** — follow the portable SOP linked from\n   `seat-continuity-and-handover`. Keep the canonical tmux session, window and pane;\n   resume the exact accepted successor history there and reconcile binding,\n   environment, queue identity and attached clients. Preserve the incumbent's\n   exact token as a cold-advisor handle when that is the selected disposition.\n   Renaming tmux sessions is a repair fallback, not the default sequence.\n6. **Write the lineage-ledger row and tombstone** (below). Record the actual\n   outcomes and transfer each standing duty explicitly. Complete the successor's\n   post-cutover self-check before unfreezing authority.\n\n## Apprentice mode — incumbent\n\nAn `apprentice-handover` policy gives you an early preparation boundary, not permission to\nautomate the succession decision. Create a fresh, staged, unbound successor; prove the pinned\nmodel before installing context; then open a **conversation, not a gauntlet**. Give coached\nerrands, answer questions, and judge work in the real domain. Scored probes are optional tools whose rigor must match the stakes, not\nmandatory ceremony.\n\nStay the authority-bearing incumbent until the named owner words the gate and the mechanic records\nthe effect receipt. Before that word, the apprentice may observe, ask, and produce evidence but may\nnot act as the seat. Enumerate deposits and transfer every standing duty explicitly, **because\nrecurring duties** are otherwise easy to lose while visible one-off work appears complete. Put the\nmechanical cutover in the portable SOP linked from `seat-continuity-and-handover`; do not duplicate\nor improvise it here.\n\n## The lineage ledger (append-only, one row per tenure)\n\nThe seat's tenure record, written at handover **by the retiring agent**. One tiny row per\ntenure:\n\n- **generation** — `v1`, `v2`, … (a seat accumulates 20–40 tenures over months)\n- **harness session id** — **captured AT BOOT**, not at retirement (a crash never gets the\n  chance to write it later)\n- **started \u002F retired** timestamps\n- **handover-packet pointer** — the pack ref\n- **tombstone** — one line: what this tenure did, written by the retiring agent itself\n\n**Why it works (zero search infrastructure):** any timestamped record — a git commit, a\nqitem, a NOTES.md line, a stream item — joins to the seat's ledger by interval match →\ngeneration + session token → wake that tenure. One row per handover, append-only. The\nledger is the tenure record; work-tree notes remain lived context, not identity state.\n\n**Crash-ended tenures** get their row appended **post-hoc** by the crash-cart \u002F restore path,\nflagged **honest-approximate** (the boot-captured session id is what makes this recoverable).\n\n## Inherit the seat, not the predecessor's identity\n\n**You are inheriting a seat, not becoming your predecessor.** Frame it explicitly to the\nsuccessor: *\"agents sat here before you and learned X; you carry the seat's mission, not their\nidentity.\"* Do not claim a predecessor's work as your own or use its stale identity\nas the current binding. Inherit the\nseat's **mission and hard-won lessons**; keep your own **fresh identity and session**.\n\n## Reach back to a retained predecessor\n\nA retired tenure is a cold advisor you can consult. Look up the seat's ledger → get that\ngeneration's session token → resume it for **one question**, then let it sleep again:\n\n- Claude: `claude -p --resume \u003Csession>`\n- Codex: `codex exec` (resume the rollout)\n\nUse `rig ask \u003Crig> \"\u003Cq>\" --wake \u003Ctarget>` for an explicit bounded consultation\n(introduced in CLI 0.5.1). Wake seat targets must include the rig: `member@rig` or\n`member@rig@N` (1 = newest tenure). Values without `@` go unchanged to the runtime\nas a session ID or title; a bare member name is not resolved within `\u003Crig>`.\nCheck `rig ask --help` for `--runtime`\nand `--wake-timeout`. The wrapper uses a runtime resume; its presence is not\nproof that a particular retained history is available. For a Claude history,\n`claude -p --resume \u003Cfull-uuid>` is the runtime-level fallback when supported.\nDiagnose the specific failure before declaring the channel unavailable.\n\n**What to write in your packet about reaching you** — your successor asking you questions is the\nreason this is a handover and not a compaction:\n\n- **Give your verbatim resume handle and known availability limits.** Retirement alone\n  does not expire retained history. Resuming still depends on that history, runtime\n  access and remaining context; distinguish these failure modes. The advisor\n  supplies testimony and does not regain the live seat's authority.\n- **Pre-form the questions.** Inventory what only you hold and write the questions out. An affordance\n  needs a trigger: name the tradeoff, missing rationale or conflict that should prompt a question.\n\n**Wake-tenancy — the identity halves (a woken tenure can mistake itself for the live seat).** The\nhardest thing to apply *checked-not-believed* to is your own identity — a retired tenure resumed for a\nquestion can answer, and act, as if it still held the seat. Two rules close it:\n\n- **Waker: disclose the target's tenure status in the wake prompt.** Open with *\"you are retired; gen-N\n  holds this seat now — I'm consulting you for one question.\"* An oriented tenure gives honest testimony;\n  an un-oriented one may reason as the live occupant.\n- **Woken: verify your OWN tenancy before your first act.** If you are being resumed \u002F woken (a parked or\n  retired session, or any session waking on a seat that already issued READY), your **first** check is\n  `rig whoami` + a **successor check** — confirm whether you are still the live occupant or a successor\n  now holds the seat, *before* you do anything. Answer the question; do not resume the job.\n\n## Failure modes\n\n1. **Riding compaction when a planned handover was available** — a degraded agent authors a\n   degraded packet. Retire deliberately at the threshold you can see coming.\n2. **Over-inheriting** — the successor believes it *is* the predecessor (stale self-model,\n   mis-claimed history). Frame inheritance explicitly; keep a fresh identity.\n3. **Session id captured at retirement, not boot** — a crash then leaves no row, or an\n   unfindable tenure. Capture at boot.\n4. **Suffixing the LIVE seat** (`\u003Cseat>-v2` as the active address) — lineage leaking into\n   identity, the wrong shape. The live address stays clean; generation belongs in the ledger.\n5. **Tombstone omitted or vague** — the ledger can no longer answer \"who did this \u002F who to\n   wake.\" One honest line, every tenure.\n\n## Checks around a planned transition\n\n- **Stage and assess before the owner calls cutover.** Use startup context when the\n  successor is unbound; check its actual address before relying on registry-routed\n  delivery. Keep incumbent authority and physical-pane custody until the selected\n  SOP's cutover steps apply. A rejected candidate does not require renaming the\n  incumbent back into a seat it should still hold.\n- **Preserve exact resume handles.** A retained advisor may have no managed node or\n  live pane. The ledger identifies its history independently of the live-seat\n  registry; absence from `rig ps` alone does not prove that history is gone.\n- **Recheck work at the boundary.** Queue items can arrive after the packet was\n  frozen. The successor reads its current owned queue, reconciles transition-window\n  work and staged inputs, and records every remaining obligation.\n- **Verify identity across surfaces.** Canonical binding, provider history,\n  process environment, queue identity and attached clients must agree. Correct a\n  staged identity residue through the supported cutover\u002Freconciliation path;\n  renaming a tmux session alone is not proof that those surfaces agree.\n- **Keep incomplete evidence explicit.** Flag unavailable activity telemetry as\n  unavailable, and mark a tombstone written by someone else as approximate.\n- **Coordinate the maintenance window.** Tell the routing\u002Fmonitoring owner the\n  target and expected window before an authorized cutover. Only an explicitly\n  configured suppression changes monitoring behavior; close the window with the\n  actual effect receipt, deviations and unresolved gaps.\n\nThese are verification prompts, not a claim that a particular runtime transition\nhas passed. Use the linked portable SOP for mechanics and record the actual run.\n\n## See also\n\n- `orienting-to-an-inherited-seat` — the **successor-side** world model your packet points\n  them at (loaded at boot); the load-bearing counterpart to this driver-side mechanic.\n- `session-compaction-and-restore` — the 16-field packet contract this practice reuses, and\n  the UNPLANNED-compaction backstop it replaces for *planned* transitions.\n- `seat-continuity-and-handover` — the seat-binding primitive mechanics + stable-seat-identity\n  architecture; the lineage ledger is the concrete form of its abstract provenance record.\n- `openrig-user` → \"Context packs and paced delivery\" — `rig context compose` + `rig walk`, to\n  author and deliver the packet.\n- `claude-compaction-restore` — the Claude crash-class restore SOP.\n- `agent-starters` — composing a primed starting point for the successor.\n",{"name":5,"metadata":24,"description":7},{"openrig":25},{"stage":26,"sibling_skills":27},"provisional",[28,29,30,31,32,33,34],"orienting-to-an-inherited-seat","session-compaction-and-restore","seat-continuity-and-handover","claude-compaction-restore","agent-starters","queue-handoff","openrig-user","main","60438a272b68d091eddb01aad6e399af4996d536","rigs\u002Fworkshop\u002Fagents\u002Fworkshop\u002Fskills\u002Fretiring-and-inheriting-a-seat",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":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add mvschwarz\u002Fopenrig-world --skill retiring-and-inheriting-a-seat",{"tool":50,"command":51},"bunx","bunx skills add mvschwarz\u002Fopenrig-world --skill retiring-and-inheriting-a-seat",{"tool":53,"command":54},"pnpm","pnpm dlx skills add mvschwarz\u002Fopenrig-world --skill retiring-and-inheriting-a-seat","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Frigs\u002Fworkshop\u002Fagents\u002Fworkshop\u002Fskills\u002Fretiring-and-inheriting-a-seat\u002FSKILL.md",true,[58],{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"CHANGELOG.md","REFERENCE","参考文档",1216,"https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Frigs\u002Fworkshop\u002Fagents\u002Fworkshop\u002Fskills\u002Fretiring-and-inheriting-a-seat\u002FCHANGELOG.md",[65,72,79,85,91,98],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"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":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":29,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7DMS55VHEAGPXMHZJ7FX94R","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":86,"name":30,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7DMRYQK0JTV7MMVHFWZ0BW0","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":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M7DMRJGN6Z8TZDR7JNHXH6KX","refocusing","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",[],[],{"skillNo":99,"name":33,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":19},"01M7DMRCR8JFVH9A91N0T71A70","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.","https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Frigs\u002Fworkshop\u002Fagents\u002Fworkshop\u002Fskills\u002Fqueue-handoff\u002FSKILL.md",[],[]]