- name
SKILL.md
स्किल फ़ाइल पब्लिशर की रिपॉज़िटरी में ही रहती है।
कॉपी की गई कमांड टर्मिनल में पेस्ट करें। यह इस SKILL.md को उस एजेंट में इंस्टॉल करती है।
npx skills add mvschwarz/openrig --skill seat-continuity-and-handover -a cursor -yकॉपी की गई कमांड टर्मिनल में पेस्ट करें। यह इस SKILL.md को उस एजेंट में इंस्टॉल करती है।
npx skills add mvschwarz/openrig --skill seat-continuity-and-handover -a claude-code -yकॉपी की गई कमांड टर्मिनल में पेस्ट करें। यह इस SKILL.md को उस एजेंट में इंस्टॉल करती है।
npx skills add mvschwarz/openrig --skill seat-continuity-and-handover -a codex -yकॉपी की गई कमांड टर्मिनल में पेस्ट करें। यह इस SKILL.md को उस एजेंट में इंस्टॉल करती है।
npx skills add mvschwarz/openrig --skill seat-continuity-and-handover -a grok -yकॉपी किया गया संदेश Grok Bot चैट में भेजें। Bot यह SKILL.md GitHub से लाता है और उसे उन स्किल में जोड़ देता है जो आपके सभी Bot साझा करते हैं।
Install this skill: https://github.com/mvschwarz/openrig/tree/HEAD/packages/daemon/assets/plugins/openrig-core/skills/seat-continuity-and-handoverपब्लिशर से
A pair of primitive families that separate who is sitting in a seat from what the seat itself is:
resume, fork, rebuild, fresh — produce a candidate new occupant. Answer: "where did the new occupant come from?"Core architectural decision: stable seat identity, fluid occupant identity, explicit provenance. Do not encode successive occupants into live seat names. Keep the stable address and record lineage separately.
rig launch / rig expand directlyEvery seat-binding operation produces two independent outcomes:
continuityOutcome: rebuilt | resumed | forked | fresh | failed
seatBindingOutcome: handed_over | partial | failed | unchanged
These can disagree honestly. Examples:
continuityOutcome: failed + seatBindingOutcome: unchanged — new occupant didn't materialize; seat correctly retains old occupant.continuityOutcome: rebuilt + seatBindingOutcome: failed — candidate created OK; bind failed mid-flight; provenance records the gap.Don't collapse these into one outcome. The system can describe what actually happened only if the two are recorded independently.
Every handover writes:
resume/fork/rebuild/fresh)handed_over / partial / failed)This is the system's truth-source for "how did the current occupant get there." Without it, the control plane shows the current occupant but not the legitimacy of the transition.
rig seat handover's receipt reports it under sideEffects:
provenanceRecordWritten says whether this handover's lineage record (its
occupant tenure) exists, and departingProcess says how the old process
ended (ended-graceful, ended-forced, or not-touched for a discovered
successor). If provenanceRecordWritten is false, the seat is already bound
to the successor and only its lineage record is missing: check the daemon
log, which names the first such failure since the daemon started, and don't
run the handover again, which would replace the occupant a second time.
continuityOutcome: failedA seat stays Stable even if multiple candidate-occupants were produced and discarded.
rebuild couldn't synthesize from artifacts; fork couldn't resolve session_source; fresh couldn't launch. Action: bind operation does not begin; seat unchanged; provenance records the failed candidate-creation step. If the failure came after the in-place respawn, with the successor launched (its readiness closed, its context packet didn't land, or finalization refused), the previous occupant is already ended and the successor may be running in the pane, not adopted: another handover ends it. When the failure recorded the attempt, its guidance names rig seat handover <seat> --recover --reason <why>, which proves the pane's one Claude is that launch and adopts it, keeping its conversation and typing nothing into it (successor_identity_unproven changes nothing; handover_attempt_superseded means another launch or handover took the seat since; Claude Code only).Binding state with explicit "halted" sub-status; operator alerted. Do NOT auto-rollback by reattaching old-occupant if detach didn't complete cleanly.provenanceRecordWritten: false. Action: the binding is committed and the successor is the occupant; only its lineage record is missing. Report it as bound with the record missing, check the daemon log (it names the first such failure since the daemon started), and don't run the handover again.advise (keep alive as advisor) but runtime can't keep old alive. Action: degrade to retire with explicit notification, OR fail if operator passed strict-disposition flag.Do NOT collapse rebuild and seat handover into one primitive. The design specifically separates them so the system can describe what actually happened.
Do NOT introduce successor-suffix seat names (lead2/lead3). Stable seat identity is the architectural goal. The live address stays stable. A retired tenure is distinguished by its ledger
generation and exact history token; preserving it does not require a renamed live pane.
Do NOT report a handover's provenance record as written unless its receipt says provenanceRecordWritten: true; a bound seat whose record is missing is reported as exactly that (failure mode 3).
Do NOT auto-rollback a half-completed handover by re-attaching the old occupant unless detach completed cleanly first.
A fork can create a candidate occupant; handover binds it into an existing seat.
The continuity outcome is forked; the binding outcome is independent.
The packaged rig handover <seat> and rig seat handover <seat> accept fresh,
discovered:<id>, fork:<seat> and rebuild sources. Use --dry-run to request
planning only. Without it, these surfaces can execute; do not infer read-only
behavior from the shorter seat command's planning-oriented description.
rig seat status <seat> is the read-only observability surface.
Source support is declared by the running daemon and depends on actual identity, history and artifact prerequisites. Read the returned source, continuity, binding and provenance results independently. A help listing or dry-run is not proof of a successful transition. The linked cutover SOP supplies the operator mechanics and required effect checks after the named owner authorizes the action.
A rebuild primes the successor from the seat's durable artifacts, highest trust
first:
RECAP.md;LEARNED.md;The superseded recaps follow, newest first, as optional history: the successor reads them only when it needs the seat's history.
A missing RECAP.md is recorded as a gap. The successor is directed to the remaining
available artifacts in that order. So before a handover, a compaction or a long pause,
the sitting occupant writes its recap alongside LEARNED.md:
rig context recap-write --file <draft.md>
--rig and --seat it writes the calling seat's recap (from OPENRIG_SESSION_NAME).
For another seat, --seat is its folder under rigs/<rig>/seats/, the part of its session
name before @. A seat's recorded logical id or member id maps to its folder when the daemon
can check it against the rig's seats.topology.root and doesn't need the daemon.recap-superseded/ chain,
which later rebuilds list as history. Write through this command, not a file tool, so
the chain is kept.The store refuses the write, and writes nothing, when a section can't be
addressed. Only H2 and H3 headings are sections. Addresses lowercase the title,
remove Markdown formatting markers, replace remaining runs outside a-z/0-9 with
a hyphen, and trim edge hyphens. Duplicate section paths, a nonblank H2/H3 title
that normalizes to an empty slug, and an unclosed code fence are refused. A
duplicate path is two H2s with the same address, or two H3s with the same address
under one H2. Blank headings are retained as scope boundaries.
It writes, with an advisory on stderr, when:
UNVERIFIED:.A recap that passes the first time has:
## Decisions, with reasons section, each decision with its reason;UNVERIFIED: line for each fact you haven't checked yourself.Any recursive seat-refresh loop must be able to replace an occupant while keeping topology stable. Without these primitives, RSI loops will either accumulate suffixed seat names (lineage leaking into identity) or destabilize topology references on each cycle. Provenance must be durable AND queryable so RSI loops can decide whether a seat is fresh enough to receive new work or needs re-handover.
A retired advisor's history can remain available without a managed node or live
pane. Query current binding and the lineage ledger separately: one answers who
holds the seat, the other identifies the retained history and exact resume token.
Do not infer that a predecessor is unreachable from registry absence alone, or
that a preserved token proves a successful resume. Check the actual runtime and
history when consultation is needed; see retiring-and-inheriting-a-seat.
references/apprentice-successor-seat-cutover.md — the portable mechanic SOP used only after the owner-worded gatereferences/orchestrator-role.md — the orchestration judgment, authority, custody, and receipt contractreferences/apprentice-evidence-toolkit.md — optional evidence apparatus selected only when the stakes earn itsession-source-fork skill — fork occupant-creation primitive (sibling)agent-starters skill — composes occupant-creation + binding into named reusable starting pointscross-host-rig-commands skill — remote addressing and transport; verify lifecycle support on the targetUse when replacing a seat's occupant (rebuild/handover/swap), reasoning about stable-seat-identity vs fluid-occupant-identity, choosing an old-occupant disposition (retire/advise/shadow), or recording
---name: seat-continuity-and-handoverdescription: Use when replacing a seat's occupant (rebuild/handover/swap), reasoning about stable-seat-identity vs…---# packages/daemon/assets/plugins/openrig-core/skills/seat-continuity-and-handover/SKILL.mdओवरव्यू
Use when replacing a seat's occupant (rebuild/handover/swap), reasoning about stable-seat-identity vs fluid-occupant-identity, choosing an old-occupant disposition (retire/advise/shadow), or recording provenance for an occupant change. Two independent outcomes (continuityOutcome + seatBindingOutcome) and the 5 failure modes that prevent silent dishonesty.
FAQ
पब्लिशर से packages/daemon/assets/plugins/openrig-core/skills/seat-continuity-and-handover/SKILL.md डाउनलोड करें, या पाथ कॉपी करके रिपॉज़िटरी खोलें। PlugMCP स्किल को सूचीबद्ध करता है, फ़ाइल होस्ट नहीं करता।
पब्लिशर इसे https://github.com/mvschwarz/openrig पर रखता है।
Claude, Cursor, Codex और Grok Build वह SKILL.md पढ़ सकते हैं जिसे आप पब्लिशर की रिपॉज़िटरी से जोड़ते हैं। जब आप चैट में स्किल के GitHub फ़ोल्डर का लिंक भेजते हैं, तो Grok Bot उसे इंस्टॉल कर देता है।