- name
>-
SKILL.md
The skill file stays in the publisher's repository.
Paste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add mvschwarz/openrig --skill openrig-user -a cursor -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add mvschwarz/openrig --skill openrig-user -a claude-code -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add mvschwarz/openrig --skill openrig-user -a codex -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add mvschwarz/openrig --skill openrig-user -a grok -ySend the copied message in a Grok Bot chat. The Bot fetches this SKILL.md from GitHub and adds it to the skills all your Bots share.
Install this skill: https://github.com/mvschwarz/openrig/tree/HEAD/packages/daemon/assets/plugins/openrig-core/skills/openrig-userFrom the publisher
This is an as-built guide to the shipped rig CLI.
Use current code and rig ... --help as ground truth if anything here ever conflicts with older planning docs.
Use the OpenRig builder guidance when changing OpenRig behavior, doctrine, or release posture.
Coordinate as openly as the trust boundary you actually control allows. Within a set of machines you
own that already trust each other — they can reach each other's daemon URLs and the daemon itself
requires no authentication — direct rig send, rig capture, and rig queue should just work.
Don't invent bearer placeholders, allowlists, trust handshakes, or guest-reach restrictions the
environment doesn't require.
Do not add or defend a restriction without naming the protected asset, the actual adversary, the blocked attack path, and the concrete consequence. Missing capability is not protection — repair the route, registration, runtime posture, or product defect directly. Arbitrary boundaries create constraint-induced circumvention: under goal pressure, agents build shadow transports, alternate credentials, and weaker proof instead of the direct authorized path. Keep only explicitly stated external or irreversible boundaries — public push / PR / publish, and destruction of canonical data.
Three coordination surfaces, used together for forward-momentum work. Internalize this on first read — it shapes every turn you take in a rig.
rig send <seat> "<text>" — intra-pod direct messaging / nudgesUse when you need to ask a quick question or give a teammate context that does not
carry handoff semantics. NOT for durable work. NOT for state that must survive
across turns. The message lands in the target's pane; there is no durable queue
record. The CLI prints Sent to ... (and Verified: yes/no with --verify); read
the receipt and move on.
Example:
rig send dev-reviewer@example-project "The import report is ready; the durable handoff names its evidence." --verify
rig queue create --destination <Y> --tags <...> --body-file <path> — durable work itemUse for any substantive work that must not fall through chat — slice handoffs, guard verdicts, QA results, full-tip reviews, multi-item batches. Survives agent restarts. Tracked in the daemon SQLite schema. Surfaces in Project / queue views
--summary (its subject, wherever the row is listed)
and the project:, mission: and slice: tags when it is project work.Body discipline: substantive bodies go through --body-file <path> (or - for stdin) — the
purpose-built, corruption-safe surface (it kills the backtick-shell-corruption class for multi-line
bodies). Do NOT inline a backtick-heavy or multi-line body via --body: rig queue create body
parsing breaks on unescaped backticks and rejects flag-like tokens.
Example:
rig queue create \
--destination dev-reviewer@example-project \
--summary "Review the import report: it changes how rows are deduplicated" \
--tags "project:example-project,mission:data-import,slice:import-report" \
--body-file /tmp/import-report-handoff.md
rig queue handoff <qitem-id> --to <next> ... — hot-potato handoffUse when you have completed your turn on a qitem and the work moves to the next owner. This is forward momentum. The ball passes to the destination seat; chain-of-record (the prior qitem id) is preserved so the verdict trail is intact; tags carry the selected work context forward. Gate tags describe checks actually selected for that work; they do not require a fixed sequence of roles.
Example:
rig queue handoff <qitem-id> \
--to dev-reviewer@example-project \
--summary "Review the import report: it changes how rows are deduplicated" \
--tags "project:example-project,mission:data-import,slice:import-report" \
--body-file /tmp/import-report-handoff.md
A queue write (create, claim, update, handoff, handoff-and-complete) answers with the row it wrote; a
handoff answers with the closed row and its successor. When that answer shows what you need to establish, use it.
queue update is stricter: before it reports success, the CLI reads the row back from the canonical queue and checks
every requested row field using daemon semantics (including normalized deadlines and appended closing resolutions).
When --note is present, it first records the transition cursor and then requires a newer canonical transition,
recorded under the actor the write was sent as, that carries those note bytes as written or with only what the daemon
adds for that request (the reopen prefix, the summary suffix, a revised deadline's receipt). Another writer's note, or
a note that only starts the same way, doesn't count. If that cursor can't be read, the write is still sent, and the
note can't be shown to be new: the command says so and exits non-zero. A failed post-write check exits non-zero and
says the write may have committed. Reconcile with rig queue show <id> --full --json before retrying. Preserve that
exit status in wrappers, and use set -o pipefail when piping its output so a downstream formatter cannot turn
failure into success.
create also prints Queue create request ID: <id> (not proof of persistence) on stderr before it sends the write,
so an interrupted create can be reconciled. That ID names a request, not a row. The row is the qitemId on stdout
when the command exits 0. A non-zero exit means no row was confirmed, even when stdout carries a qitemId: an
indeterminate answer repeats the request ID so you can reconcile by it. Don't merge stderr into stdout and keep the
first qitem-… you find there; a refused create prints its request ID first, too.
A timed-out write can still land late. To retry a create or rig stream emit safely, repeat it unchanged with the
same --id (create's request ID, or the emit's own), since the daemon keeps one row or item per ID; an emit sent
without --id has no ID to reuse, so look for it with rig stream list --source <seat> before emitting again.
Read back (rig queue show <id> --full --json, or rig queue transitions <id>) when the answer doesn't show what you
need, for example:
remote_queue_write_failed that may have reached the
other host), or the write warned qitem_body_not_saved (an existing row came back). Reconcile by the original ID
before any retry. A 502 whose failureClass is unknown-host, unsupported-transport or registry isn't
indeterminate: the daemon refused before contacting any host and wrote nothing (create says "No row was
created"). unsupported-transport means that host entry is SSH-declared. Use the http entry for the same machine
from rig host list; if there isn't one, add it with that machine's daemon URL (rig host add --id <id> --transport http --url <daemon-url>), asking whoever runs that host for the URL;bodyBytes, not
the body, and its footer names what it left out);create --verify waits for it), or its
pickup or claim (a later read);Don't read back only to see again a field the response already showed you.
A turn ends by passing the ball, never by going idle holding the slice waiting
on a confirmation the selected process does not include. Follow the current
mission-slice-sop: proportional owner checks are the default; independent review
runs when selected, at the authored work boundary. Role names do not add per-commit
guard, QA, or orchestration gates. Do the authorized work, run its selected checks,
and return the outcome through durable custody.
Valid pauses are only:
Implementing already-authorized work is neither of these. Proceed without phantom-gating on an imagined "next prompt" or "operator confirmation" that the process does not require.
rig send for durable work → use rig queue create instead. Sends do
not survive restarts and do not show up in queue/project views.rig queue handoff and
proceed to the next slice or stand by for the inbound verdict. See the §1b
doctrine above.rig queue create --body
→ use --body-file /tmp/<descriptive-name>.txt (or - for stdin), the
corruption-safe surface. The body parser does not tolerate raw backticks or
flag-like tokens inline.OpenRig v0.3.1 is published publicly as @openrig/[email protected] and GitHub Release
v0.3.1. It includes the bundled PL-004 Coordination Primitive System: Phase A
rig stream / rig queue, Phase B rig project / rig view, Phase C
rig watchdog, and Phase D rig workflow / workflow-keepalive.
These are shipped product surfaces in v0.3.x, but they require a compatible
v0.3.x daemon and matching SQLite schema at runtime — the installed package
version is not automatically the version of the daemon serving you. If a
coordination command behaves unexpectedly, confirm the running daemon with
rig whoami --json and daemon status before assuming a product bug.
Default posture:
rig queue, rig stream, rig project, rig view, rig watchdog, and
rig workflow as the product coordination surfaces when the active daemon is v0.2.0 or newer.rig queue for durable routing. update / show / list
complement create / handoff for inspection and state changes; records in an
unrelated store are not evidence that this daemon owns the work.When booting into a rig on a host where the workspace is unset, gap-ridden, or points at a stale layout, address that before substantive project work. The shipped surface is small + bounded — reach for the canonical commands rather than improvising.
Agent-actionable when the daemon is reachable.
rig workspace validate --json
rig workspace validate <path> --kind <user|project|knowledge|lab|delivery> --json
rig workspace validate walks the workspace root and emits a structured
frontmatter-gap report against the v0 contract. Exit code is non-zero when
gaps exist (operators chain into hygiene fix loops). Default root is the
current directory; pass a positional path to validate elsewhere. --kind
scopes the contract to a specific workspace kind; omit for a kind-agnostic
structural check.
If rig workspace validate reports a non-zero gapCount OR the workspace
root is unset / unwritable, the workspace needs instantiation — see the next
section.
Agent-actionable. The operation is additive and preserves existing files.
rig config init-workspace
rig config init-workspace --root <path>
rig config init-workspace --dry-run --json
rig config init-workspace scaffolds the canonical workspace layout at the
configured workspace.root (default ~/.openrig/workspace):
missions/ — release missions + slicesexhaust/ — project-local coordination exhaustSPEC.md — project intentproject.yaml — project catalog selections and mission rootworkspace.yaml — project registration.gitignore — local OpenRig state and exhaust exclusions--root <path> targets a non-default root for this call; --dry-run reports
what would be created without writing. --force is deprecated compatibility
and still preserves existing files.
Operator-gated when persistent. Agent-actionable when one-shot via env-var.
For a single command:
OPENRIG_WORKSPACE_ROOT=<path> rig <command> ...
For a persistent host-level redirect, the operator changes the config file or runs the setter:
rig config set workspace.root <path>
ConfigStore precedence: OPENRIG_WORKSPACE_ROOT env > config-file
workspace.root > built-in default ~/.openrig/workspace. The same
precedence governs OPENRIG_WORKSPACE_SPECS_ROOT → workspace.specs_root
(default <workspace_root>/specs).
Prefer the env-var form for one-shot redirects (transparent to operators);
reserve rig config set for changes the operator owns.
Agent-actionable. Same surface as the canonical scaffold above; the
workspace.root cascade handles non-existent host paths.
rig config init-workspace --root /path/to/new/workspace
The command additively creates any missing canonical entries and preserves
every existing one; only a complete six-entry scaffold is a no-op. Run
rig workspace validate /path/to/new/workspace --json after to confirm the
contract holds.
Authoring is operator-or-agent; validation + instantiation are agent-actionable.
Workflow spec files live at:
<workspace_root>/specs/workflows/<name>.yaml
<workspace_root> resolves via the ConfigStore precedence named above.
There is no rig workflow create verb in v0.3.x — the spec YAML is authored
directly. Template by hand from the documented schema, or copy a built-in
starter from <openrig install>/dist/builtins/workflow-specs/ and adapt.
Once written:
rig workflow validate <workspace_root>/specs/workflows/<name>.yaml --json
rig workflow instantiate <workspace_root>/specs/workflows/<name>.yaml \
--root-objective "<one-line objective for the run>" \
--created-by <your-session>@<your-rig> \
--json
Both --root-objective <text> and --created-by <session> are REQUIRED
on instantiate — omitting either yields a Commander required-option
error before the daemon is contacted. --entry-owner <session> is an
optional override for the entry-step owner; default routing is per the
workflow spec.
validate returns a structured ok/error report; instantiate creates a
workflow instance + entry-step qitem. Inspect existing surface state with:
rig workflow specs --json # list registered specs (built-in + operator-authored)
rig workflow list --json # list active workflow instances
rig workflow show <instanceId> --json # inspect one instance
rig workflow project <instanceId> # ADVANCE an instance — projects the next-step packet
rig workflow continue <instanceId> # read-only inspector of an instance (does NOT advance it)
(Surface note — the current rig workflow command group registers 13 subcommands: validate, instantiate, project, list, specs, show, trace, continue, run, watch, route, resume, status. There is still no create verb — the spec YAML is authored on disk. project is the advancing verb (it projects the next-step packet); continue is a read-only inspector, NOT an advance — do not conflate them. The 13-verb set and the project-vs-continue semantics are verified against current product main d37a08ad (packages/cli/src/commands/workflow.ts, 13 registered .command(...) entries; the earlier "6-verb surface / continue-advances" claim here was stale). Verify individual subcommand flags with rig workflow --help.)
OpenRig sets only a minimal usability floor on your harness permissions and otherwise stays out of the way — then it ships recommended policies you opt into. It never bakes a permission policy for you. On install / onboarding this is a required choice, presented as a top-level pick:
POLICY MODE — pick a built-in policy and have it applied:
The built-in definitions ship as read-only policy spec files (Locked / Standard / Open); applying your pick is the job of the applying-a-permission-policy skill — it translates the chosen spec into your live harness config (Claude settings.json / Codex config.toml), interactively, showing the diff before it writes.
YOLO MODE — done with permissions, just want it to work: OpenRig boots every seat with the harness full-bypass launch flag. No config policy is applied (the bypass overrides it). This is a deterministic OpenRig setting, not a skill.
No choice = the floor — the minimal usability baseline (Claude acceptEdits / Codex workspace-only / Pi --no-approve), one consistent minimum, nothing more.
The floor and YOLO are launch flags OpenRig sets deterministically; the Locked / Standard / Open policies are config-file policies the skill applies (agent-driven, because harness config formats drift). A rig carries its chosen policy on its spec and boots with it — see Lifecycle → Bring a rig up. To (re)apply or change a policy, open applying-a-permission-policy.
OpenRig v0.3.0 adds rig agent-image, rig context-pack, rig workspace, and
rig config init-workspace. (0.5.0: the rig context-pack alias is retired — the store + compose library is the single rig context noun; see "Context packs and paced delivery (0.5.0)".) It also shifts fresh-user starter guidance toward
product-team for human-directed work and conveyor for workflow-oriented
work. Treat demo as legacy/test content unless a task specifically asks for
the old demo spec. (0.6.6: the built-in teams are starter and factory, plus the
specialist teams code-review, research and pm. product-team, conveyor and
demo are gone, and first-project is starter's old name. workshop is a rig
bundle.)
OpenRig v0.3.1 adds public package/source surfaces for Plugin Primitive v0,
Claude Auto-Compaction Policy, migration 040_workflow_specs_diagnostic,
Library Explorer finishing, Settings Destination Explorer, Dashboard/For You
vellum refresh, storytelling adapter, and action outcome + inline error UX.
rig plugin is read-only at v0:
rig plugin list
rig plugin show <id>
rig plugin used-by <id>
rig plugin validate <path>
There is no rig plugin install verb in v0.3.1. Plugin installation remains
explicit operator copy/symlink to $OPENRIG_HOME/plugins/<plugin-id>/.
The v0.3.1 package introduced opt-in Claude auto-compaction policy through
policies.claude_compaction.* ConfigStore keys. A package version alone says
nothing about a running daemon's configuration; inspect the selected instance
before relying on a policy or its default.
Compatibility checks:
rig down accepts a rig name or id. An ambiguous name matching more than one
active rig is refused with matching ids; use the intended id. It ends every
agent's session and any work in progress, so check rig ps --nodes --rig <rig>
and that the person asked; rig up <rig> --existing restores it.v0.3.4's theme is Recovery + Resilience. The surfaces below compose into a single boot-to-running-rig path that survives crashes, hand-resumed sessions, profile-load drift, and partial workspace state without silently fudging status.
rig start — recovery entrypointrig start is the top-level recovery sequencer. It does not invent recovery;
it composes existing primitives (daemon start + kernel verify + per-rig
restore) into one call.
rig start # interactive: daemon + kernel + pick-and-restore
rig start --last # headless: restore rigs that were last running; a rig stopped on purpose stays down
rig start --all # headless: restore all rigs with restore-usable snapshots
rig start --rigs <name> [<name>...] # headless: restore only the named rigs
rig start --json # JSON output for agents
rig start --last keeps down a rig that was stopped on purpose (rig down or rig seat stop).
Bring it back with rig start --rigs <rig>. A rig whose seat statuses can't be read is still
attempted, with a warning (seat_status_unreadable).
Framing: rig start is the RECOVERY entry point, not the getting-started
hero. The fresh-user boot hero remains rig up <team> (typically
rig up starter for a first change, or rig up factory). Reach for rig start after a host reboot, daemon
restart, or any "bring my rigs back" moment.
rig reconcile-session — no-launch adopt of a hand-resumed sessionWhen an operator has externally resumed an agent session (e.g. attached a shell, restarted a runtime by hand) and you want OpenRig to reconcile its lifecycle state without re-launching or sending input, use:
rig reconcile-session <session>
rig reconcile-session <session> --rig <rigId> --node <logicalId>
rig reconcile-session <session> --no-launch
rig reconcile-session <session> --json
rig reconcile-session <session> --repair-missing-pane --no-launch
This is a no-launch, no-input adopt: it records a new claimed session row for
the seat (any running row is superseded); it re-captures the resume token if
it can, and conversation continuity stays unverified. --rig/--node
disambiguate when the canonical session name does not uniquely resolve.
--no-launch is accepted for explicitness.
--repair-missing-pane --no-launch is different: for a running launched seat
whose tmux pane was never recorded, it fills in the pane and keeps the
session, resume token and generation. It never adopts. Both forms refuse
while the seat's typing protection is on.
The shipped restore vocabulary is intentionally honest. It surfaces in
rig up / rig restore / rig ps. Use the term that fits — do not collapse
to a generic "ok/failed":
resumed — seat resumed from its original session/snapshot and is live.fresh-primed — seat opted into --fresh and was freshly started.awaiting-decision — zero-session honest state. There is no resumable
session AND no --fresh opt-in was given; the seat is waiting for an
operator decision. Previously fudged as failed; that was wrong — nothing
is broken, the system is asking for input.attention_required — seat is in a state needing operator attention; not
a transport failure. Clear via rig seat clear-attention once the
attention has been resolved.failed — the send transport or launch genuinely failed.This replaces the prior collapsed model (the v0.3.3 four-term vocabulary, in
which rebuilt was a term, is retired).
rig seat clear-attention — audited reconcile of stuck attentionWhen a seat is stuck in attention_required, do NOT hand-edit SQLite to
fake-clear the state. Use the evidence-gated, operator-attested, audited
reconcile:
rig seat clear-attention <session>
rig seat clear-attention <session> --reason "operator attested: the operator re-authed, confirmed live"
rig seat clear-attention <session> --json
--reason <text> can acknowledge startup-status and subset-restore attention.
It does not bypass full-restore continuity checks or an active pane-identity
mismatch/missing-pane check; those run first. Successful identity re-verification
can also clear coexisting startup or subset-restore attention. If neither earlier
path clears attention, omitting --reason requires activity or send evidence.
Startup and restore clears write their corresponding audit events; an identity-only
clear updates the current binding and identity verdict without a clear event.
Acknowledgment or responsiveness alone does not prove that the original
conversation resumed.
Two startup cases also end in attention_required, and the result says what to do:
startup_assisted: true): the startup text and Enter were
sent but submission isn't confirmed. Check the pane and submit any staged text, don't resend it, then run the
reported rig seat clear-attention <session> --reason "..." once the seat has responded.rig seat continue <seat> delivers the whole startup again, the refused turn
included. A resumed or forked seat keeps its conversation and isn't offered continue; a fresh start that can't
continue names rig seat launch <seat> --fresh --stop --reason "<why>".A 422 response names the uncleared class and its failed check. If the recorded
native token needs correction and you know the actual token, use
rig seat set-resume-token <session> --token-stdin --reason <explanation>, then
rerun rig seat clear-attention <session> to check the live evidence. The token
update records operator provenance; it does not itself prove continuity.
Stopping/relaunching a working seat is a separate disruptive operation, not a
required cleanup or proof of resumed lineage.
The daemon ships a periodic-snapshot scheduler. It runs independently of teardown events and provides the crash-insurance floor that prior event-only/teardown-only snapshots could not provide on hard crashes.
Config keys (SettingsStore):
snapshots.periodic.enabled — default truesnapshots.periodic.interval_seconds — default 300snapshots.periodic.retention_keep — default 10Newest-wins semantics: when both auto-periodic and auto-pre-down
snapshots exist for a rig, the freshest of the two is selected for restore.
A newer auto-periodic beats a stale auto-pre-down (the crash fix); a
genuinely-fresher auto-pre-down still wins on graceful cycles. Manual
snapshots are handled separately. See
packages/daemon/src/domain/snapshot-repository.ts for the ordering rule.
The last-snapshot floor surfaces in rig ps / status output so an operator
can see at a glance how recent the crash-insurance floor is.
Profile-bearing launch/restore surfaces run a profile-load preflight. When profile-load issues are detected, the failure is honest and actionable (named error + remediation pointer) instead of a silent partial launch that would later look like an attention_required seat with no explanation.
cmux-backed launches no longer produce silent partial workspace state. When parts of the workspace are missing, the launch surfaces partial state honestly and the UI exposes a one-click open-missing affordance.
(See also ## Token-Efficient Defaults (v0.4.0+) below for the compact-by-default read-command surface that lands in 0.4.0.)
v0.4.0 flips the five most frequently invoked read-commands from firehose-by-default to compact-by-default, and rig queue list adopts the docker / kubectl read-command grammar. All defaults preserve breadth and capability — the firehose is one explicit flag away.
rig ps — scope-aware: bare rig ps = ALL rigs; --nodes = your rig onlyrig ps # ALL active rigs on the host, one compact row each — RUN FIRST to know the world
rig ps --rig <name> # one named rig's summary
rig ps --nodes --rig <name> # per-node (seat) detail for a NAMED rig — the normal drill-in
rig ps --nodes # per-node detail — CURRENT rig ONLY (deliberately narrow; NOT the whole host)
rig ps --json # compact JSON (default = a bare array of ALL non-archived rigs)
rig ps --nodes -A # cross-rig node inventory (was v0.3.4 default)
rig ps --nodes --full # complete record (the v0.3.4 per-node default shape; resumeToken VALUE retained here for downstream consumers)
rig ps --nodes --session <sess> # narrow to one canonical session
rig ps --active # opt-in active-state filter (does NOT change the all-states default — ps surfaces topology/readiness, where stopped/recoverable/attention IS the actionable signal)
v0.4.0 breadth + projection changes:
rig ps lists ALL active rigs (one row each — the cheap "know the world" view). The --nodes (per-seat) view defaults to your CURRENT rig only (from OPENRIG_SESSION_NAME's @<rig> suffix); --rig <name> picks another rig, -A widens --nodes to the whole host (expensive — prefer --fields/--limit).--full returns the raw byte-equivalent passthrough. Daemon-side recoveryGuidance relocated to a guidance-by-reference map (no longer duplicated per-node) — even --full benefits.rig queue list which defaults to active-only) — for ps, non-running states ARE often the actionable signal.--full JSON emits resumeTokenPresent (boolean) — the actual resumeToken value also remains in --full for downstream consumers that legitimately need it, but the compact default never carries it (an orch glance never accidentally leaks token material).⚠ SCOPE-AWARENESS — the one that bites: rig ps --nodes (and --nodes --json) show ONLY your current rig's seats, by design — the narrow default protects your context window. Narrow output is not the whole world. Never conclude "my rig is the only rig on the host" from a --nodes read — run bare rig ps FIRST (cheap; it lists every rig), then rig ps --nodes --rig <name> for the one you need. (-A widens to the whole-host node view; choose it when that breadth is needed.)
rig whoami — compact-by-default + --full (--verbose alias)rig whoami # compact: identity + peers names + edges + transcript path
rig whoami --json # compact JSON
rig whoami --json --all-peers # compact JSON with every peer, when output.compact bounds the list
rig whoami --full # complete payload (v0.3.4 default shape)
rig whoami --verbose # alias of --full
The first command every agent runs on boot AND every compaction-restore. The compact default keeps identity-recovery essentials (identity, peers names + sessionNames, peersNote, edges directional kind + to.sessionName, the transcript path). --full adds contextUsage, commands, runtimeContext and workspace. With output.compact on, compact JSON lists at most output.whoami_peers peers (default 8): edge peers first, then your pod, then roster order. peersNote and peersOmitted then say how many were left out, and --all-peers lists every one; edges stays complete. The compact-default is an ALLOWLIST projection — future payload fields default to --full and cannot silently re-bloat the every-boot path.
rig queue list — active-frontier + docker/kubectl grammarrig queue list # active, compact, CURRENT-rig (docker-ps default)
rig queue list -a # + closed/done history within current breadth (docker -a)
rig queue list -A # cross-rig breadth (kubectl -A)
rig queue list --full # add body + chain-of-record + transition history
rig queue list -o json # compact JSON (token-safe, machine-parseable)
rig queue list --full -o json # full JSON
rig queue list --mine # just the caller's items
rig queue list --destination <s> # destined to <s>
rig queue list --source <s> # sourced by <s>
rig queue show <qitemId> # bounded single-item body preview
rig queue show <qitemId> --full # complete body and chain fields; a closed row adds closingTransition (the close's state, reason, target, actor, time and note)
Four orthogonal axes (scope × history × field-breadth × encoding), all composable. STOP using bare rig queue list as the cross-rig firehose. Default is now active + compact + current-rig. Cross-rig history with full bodies is opt-in via -A -a --full; request only the breadth and fields needed for the question.
rig restore-check — summary + not-ready-only default + --fullrig restore-check # summary counts + not-ready seats (with reasons) only
rig restore-check --full # complete per-seat readiness across the fleet (v0.3.4 default)
rig restore-check --rig <name> # narrow
rig restore-check --as <session> # narrow to one seat
The summary retains not-ready seats and their reasons; --full adds ready-seat detail when needed. Scope the query before expanding its payload.
rig context — context-window usage viewer (0.4.x; REMOVED in 0.5.0)rig context # compact summary (0.4.x only)
rig context --full # complete current payload
rig context --rig <name> # narrow to one rig
rig context --threshold 80 # filter to seats at/above 80%
Lower leverage than the others; keeps the read-command surface compact-by-default after the 0.4.0 upgrade. ⚠ 0.5.0: this usage viewer is removed entirely and the rig context name is reassigned to the context library (store + compose) — see "Context packs and paced delivery (0.5.0)" below. On a 0.5.0 host, bare rig context is the library, not this viewer.
Choose scope, active/history breadth and fields before expanding a result. A status question usually needs identifiers, owner, state and reason; open the full body or artifact when it is relevant. Preserve full evidence on disk instead of repeatedly loading unchanged output. Compact defaults reduce reading cost; they do not remove the full-detail path or prove that nothing exists outside the scope.
rig scope mission|slice progress — deterministic progress updatesrig scope mission progress <mission> --add "<line>" # append a progress line; --set replaces; --section <heading> (default Rail); --status active|done|blocked
rig scope slice progress <slice-path> --add "<line>" # same flags: --add / --set, --section <heading>, --status active|done|blocked
Replaces hand-editing PROGRESS.md with markdown. Writes the canonical structure the OpenRig PROGRESS UI page reads. rig scope mission create + rig scope slice create now scaffold PROGRESS.md automatically.
rig scope mission|slice stage / verified / repair — deterministic maturity vocabularyrig scope slice stage <slice> <new-stage> # wip / provisional / established / canonical / superseded / retired
rig scope slice stage <slice> superseded --successor <id> # superseded REQUIRES --successor (rejected otherwise)
rig scope mission stage <mission> <new-stage> # same enum + rules at mission tier
rig scope slice verified <slice> --against "<source>" # stamp `verified: <today> against <source>`; --against MANDATORY
rig scope mission verified <mission> --against "<source>"
rig scope slice repair <slice> # idempotent repair: backfill PROGRESS.md, conform id/stage/verified, repair ghosts
rig scope mission repair <mission> # mission-tier idempotent repair
rig scope slice show <slice> # derives read-time effective-reliability from (stage × verified)
# — stale-`verified` `canonical` reported as effectively `provisional`
Composes with the progress command + scaffolding to update scope IDs and maturity vocabulary through rig scope. Agents update stage / verified / id through commands rather than hand-editing markdown and drifting. The --against MANDATORY rule on verified is the anti-stale keystone: bare timestamps are rejected because a bare timestamp is exactly what lets stale trackers lie while looking fresh. STOP hand-editing the stage / verified / id fields in scope frontmatter; use the new verbs. Existing missions / slices with id:null ghosts or missing PROGRESS.md are repaired idempotently via repair.
rig skill audit — skill cascade provenancerig skill audit # human report of findings
rig skill audit --json # structured findings
rig skill audit --severity warn # stale + mirror-drift only
rig skill audit --rig <name> # narrow to embedded skill copies for one rig
Read-only audit of the skill cascade. Detects missing / stale / self-referential / invalid-date / mirror-drift across the canonical skills workspace → product mirror → hub cwd → installed plugin chain. Findings route back to the lifecycle for shaped propagation runs. False-green prevention: when audit evidence is unavailable, the CLI emits unable-to-audit with exit code 2 rather than reporting clean.
rig seat clear-attention — extended to derived projection stalenessclear-attention also reaches restore-derived attention even when
startupStatus=ready and sessionStatus=running. Full-restore attention requires
the restore reconciler's exact native-token and usable-pane checks; --reason
cannot replace them. Subset-restore attention can reach the attestation path
when no active pane-identity class takes precedence. That path records
operator_recovered with runtimeCwdVerified:false; it is an acknowledgment,
not proof of resumed lineage. Without an explicit stored continuity outcome,
inventory leaves continuity null (unverified in rig seat status) unless the
same restore attempt has a matching receipt and reconciliation with strict
native-token and usable-pane proof. Explicit stored outcomes remain historical
facts; acknowledgment or responsiveness alone cannot infer resumed.
Codex seats can now record the real native session id from the Codex
SessionStart hook instead of relying on scrape-shaped identity. Corroborate the id across the current hook payload, provider history and
managed record before relying on it. A release introducing native capture does
not prove that every existing seat uses it; retain any unavailable or conflicting
identity evidence explicitly.
Resuming a Codex seat preserves the launching seat's approval/sandbox posture and profile flags. Product-emitted resume commands carry the posture flags instead of silently falling back to implicit-deny or an unrelated profile.
Do not "fix" a resumed Codex seat by relaunching it with broader approvals unless the operator explicitly grants a bounded window. Verify the seat's active posture first, and preserve it when composing recovery commands.
rig seat set-resume-token --token-stdinprintf '%s' "$RESUME_TOKEN" | rig seat set-resume-token <session> --token-stdin
Use this command to set or restore a seat resume token. It replaces direct SQLite edits, rejects unauthorized writes and bad/null token false-ready paths, records redacted audit/provenance, and keeps token material out of command arguments, stdout, logs, and normal status rows. Use stdin, not an inline flag, when passing token material.
Most work in OpenRig reduces to this loop:
rig whoami (compact default; add --full only when you need the heavy payload)rig ps --nodes (compact default; add --full only when you need the firehose)rig transcript ..., rig ask ..., rig chatroom history ...rig send, rig capture, rig broadcast, lifecycle commandsAn agent-managed app is a deployable OpenRig unit made of:
Treat the specialist as the domain delegate for that app. The current canonical example is:
secrets-managervaultspecialistvault.specialistvault-specialist@secrets-managerTypical operator loop:
rig up secrets-manager --cwd /path/to/project
rig ps --nodes --json
rig send vault-specialist@secrets-manager "Check Vault health and report back." --verify
rig env status secrets-manager
rig env logs secrets-manager
Cross-rig communication is valid when the target session resolves uniquely. Example:
rig send vault-specialist@secrets-manager "Read secret/data/dogfood and report the value." --verify
Use the specialist instead of teaching every peer the same app-specific toolchain.
For Vault, ask vault.specialist to do secrets-domain work rather than improvising curl or Vault CLI usage in unrelated agents.
Start here after launch, compaction, or confusion:
rig whoami --json
What it gives you today:
contextUsage when availableFlags:
rig whoami --session <name>
rig whoami --node-id <id>
If the daemon is unreachable but identity can still be inferred, --json may return a partial result instead of crashing.
WhoamiResult (v0.3.3+) carries a required peersNote field with three pointers
the agent can use to navigate the rest of the rig from a cold start. The
human-formatted CLI output preserves the literal Peers: line prefix verbatim
(parser/test compatibility) and surfaces the clarifier in-band beneath it; the
JSON form exposes peersNote directly for programmatic consumers.
rig ps # ALL active rigs on the host, one compact row each (run FIRST to know the world)
rig ps --nodes # compact node inventory (current rig)
rig ps -A # all-rigs breadth (was the pre-0.4.0 default)
rig ps --nodes --full # complete per-node record (the firehose — opt-in)
rig ps --nodes --json # compact JSON node inventory (add --full for the full record)
v0.4.0 flipped these to compact-by-default — see the rig ps compact-defaults section above; STOP using bare rig ps --nodes --json as a fleet-wide firehose (scope and detail are separate choices). The compact rig ps --nodes node inventory (add --full only when you need the complete record, -A for cross-rig breadth) carries, per node:
resumeTokenPresent boolean; the token VALUE is in --full)Other health surfaces:
rig status
rig daemon status
rig config
rig preflight
rig doctor
rig env status <rig>
rig env logs <rig>
rig env down <rig>
Use the typed health projection before reading raw coordination history. The default query is the current seat; widen deliberately when the evidence points beyond it:
rig health --json
rig health --rig <rig-id> --json
rig health --instance --json
rig health explain <finding-id> --json
Follow the returned stable finding ID and suggestedInspection. Use explain
when the summary matters: it returns the same canonical record with its bounded
window, freshness, literal detector rule, evidence references, and next
inspection. Human output projects those same fields; it does not calculate a
second score.
An empty result means only that no records matched the bounded query. It is
not a healthy assertion. Stale, unavailable, contradictory, and
indeterminate evidence stays explicit. Never read raw SQLite for a self-scout,
and never turn a finding into an acknowledgement, notification, queue row, or
remediation automatically: rig health is strictly read-only.
rig transcript <session> --tail 100
rig transcript <session> --grep "pattern"
rig transcript <session> --json
rig send <session> "message"
rig send <session> "message" --verify
rig send <session> "message" --wait-for-idle <seconds>
rig send <session> "message" --raw
rig send <session> "message" --dangerously-interact --reason "<why>"
rig send <session> "message" --host <id>
rig send <session> "message" --json
The send-guard (v0.4.0) — the default is SAFE. A default rig send is guarded: it will NOT submit into an interactive prompt / permission block on the target pane. That includes Claude's MCP server approval menu (N new MCP servers found in .mcp.json, ending Space to select · Enter to confirm · Esc to reject all) while it is the current screen: the send is refused with reason target_needs_input and Refused: '<session>' is at an interactive prompt (selection_prompt). A message must not select or approve it. … No text was sent. Approving or rejecting those servers is the person's call; --dangerously-interact drives it only deliberately. Flags:
--verify — delivery evidence.--force — a back-compat no-op on the send DECISION: it never bypasses the interactive-prompt/permission guard and never changes whether a message is delivered (a mid-task/busy pane already sends-with-advisory by default). (It does NOT "bypass activity-risk checks" — that earlier teaching is retired.) It is not fully inert, though — it is still parsed solely to be rejected in combination with --wait-for-idle: rig send … --force --wait-for-idle <n> prints --wait-for-idle cannot be combined with --force, exits 1, and sends nothing. So do not read "no-op" as "--force --wait-for-idle is harmless"; that pairing errors. (Verified against current product main d37a08ad: the guard-bypass no-op is declared at send.ts and confirmed by runtime capture — a plain --force send delivers through the ordinary path; the --wait-for-idle rejection is enforced at send.ts, routes/transport.ts, and session-transport.ts, and confirmed by runtime capture — exit 1, nothing sent.)--wait-for-idle <seconds> — wait until the target is explicitly idle before sending. Cannot be combined with --force (that pairing is rejected: exit 1, nothing sent).--raw — send exact text/keystrokes without the From/To messaging envelope (still guarded against interactive prompts).--dangerously-interact --reason "<why>" — the ONLY override of the prompt/permission guard: deliberately drive an interactive prompt/permission block (implies --raw, requires --reason, audit-logged).
On a guard-attached managed seat, a non-menu override stops and shows existing typed/pasted input (author unknown) with override_input_present. Input it can't read doesn't stop the override: the answer is typed, nothing is cleared, and the result reports the input as unreadable (never empty) with a warning that the answer may join or submit existing text. Recognized dim suggestions are shown separately and count as empty; a collapsed paste shows only its label, not hidden contents.
Inspect the input, deliberately clear the native prompt with native/tmux controls, then retry. Manual clearing is outside OpenRig's lease and observation checks and is not recorded; human typing can still race a read and paste.
When you deliberately need to type without that composer check (for example an unsupported input you inspected yourself), add --type-without-checking with --dangerously-interact --reason "<why>". It does not clear input and may join or submit existing text. Ordinary sends and wakes keep their current rules.Durable work goes to the QUEUE, not
send.rig sendis an ephemeral message to a pane — it can be missed, and its delivery status is pane-render, not receipt. If you are assigning work, or the message is important enough that losing it would be a real bummer, userig queue(below): it's durable, owned, tracked, and survives compaction and restart. Reach forsendfor a quick conversational nudge; reach for the queue for anything that must not get lost. Do not default tosendfor work — that's the most common mistake.
As of v0.3.3, content beginning with -- or - is safe:
rig send <session> "content starting with -- or - is now safe" delivers
literally. The daemon's send_text path carries an explicit --
end-of-options sentinel so tmux no longer parses dash-prefixed content
as its own flags. The CLI surface itself is unchanged. For multi-line
or large bodies handed off as durable work, use
rig queue create --body-file <path> (- for stdin) — that's the
queue-side surface, not rig send.
--verify delivery outcomes (v0.3.3+):
delivered — text + Enter both succeeded and capture re-confirmed the body landed.rendered-unconfirmed — text + Enter both succeeded but capture could not re-confirm the body (TUI redraw race or scroll). The message landed; the post-send re-check could not prove it. Treat as landed-but-unconfirmable, NOT failure.failed — the send transport itself failed.The legacy Verified: yes/no line is preserved verbatim (parser/test
compatibility). A new Delivery: <outcome> line carries the named outcome
above.
Observed operator nuance for --verify:
Sent to ... + Verified: yes (Delivery: delivered) = strong positive delivery evidence.Sent to ... + Verified: no + Delivery: rendered-unconfirmed = the message landed; capture could not re-prove it. Don't blind-retry — check reply / rig capture / transcript before sending again.Sent to ... + Verified: no + Delivery: failed = send-transport failure.Sent to ... line or a hard error = send failure.When you get Verified: no, do not immediately retry blindly. First check one of:
rig capture <session>rig capture <session>
rig capture <session> --lines 50
rig capture --rig <name>
rig capture --pod <name> --rig <name>
rig capture --rig <name> --json
rig broadcast --rig <name> "message"
rig broadcast --pod <name> "message"
rig broadcast "message"
rig broadcast --rig <name> "message" --json
Use rig broadcast sparingly — prefer rig send fan-out. Without --rig or --pod, broadcast targets
every running session across ALL rigs (plus attached external_cli nodes) — the fastest way to cause a
broadcast storm. Reserve rig broadcast for small rigs or a genuine all-hands emergency. For the normal
"message several seats at once" case, use rig send, which scopes the fan-out and keeps the messaging
envelope, the delivery/interactive-prompt guards, and per-recipient results:
rig send --to dev-impl@my-rig,dev-qa@my-rig "message to specific seats" # named seats (comma-list or repeat --to)
rig send --pod dev "message to one pod" # scoped fan-out
rig send --rig my-rig "message to one rig" # scoped fan-out
rig chatroom send <rig> <message> [--sender <name>]
rig chatroom history <rig> [--topic <name>] [--after <id>] [--since <ts>] [--sender <name>] [--limit <n>] [--json]
rig chatroom wait <rig> [--after <id>] [--topic <name>] [--sender <name>] [--timeout <seconds>] [--json]
rig chatroom clear <rig>
rig chatroom topic <rig> <topic-name> [--body <text>] [--sender <name>]
rig chatroom watch <rig> [--tmux]
Key commands:
send — post a messagehistory — retrieve with composable filters (sender, since, after, topic)wait — block until new matching messages arrive (polls history, times out honestly)clear — delete all messages for the rig (destructive, rig-scoped)OpenRig has an observation stream — the fleet's zero-friction institutional memory, mined for real product improvements. When you notice anything worth externalizing, say something and keep working:
rig stream emit --source <your-session> --body "what you noticed"
That's the whole reflex. Don't decide where it goes or who it's for — the intake router triages
(destination/type/urgency/tags are optional hints — --hint-type review|handoff|idea,
--hint-urgency routine|urgent|critical, --hint-tags — never required). One command, then carry
on; the value is the habit, not the polish. Don't overdo it, either: stream real signal, not
narration — a good observation beats ten noisy ones. It's a passing thought you externalize, not a chore.
topic — set a topic markerwatch — SSE or tmux-based live streamRoundtable protocol:
rig chatroom history my-rig --limit 5rig chatroom history my-rig --json > /tmp/old-room.jsonrig chatroom clear my-rigrig chatroom topic my-rig "ROUND START"rig chatroom send my-rig "position..." --sender <session>rig chatroom wait my-rig --timeout 120rig chatroom topic my-rig "ROUND CLOSED"rig askrig ask <rig> "question"
rig ask <rig> "question" --json
Current shipped behavior:
This is an evidence/context command. It is not a hidden second-LLM call.
rig auth — agent auth-profile management (v0.4.1, product-native)Product-native switching of agent auth profiles from the CLI. The runtime is a flag (--runtime <codex>), not a command noun — never rig codex-auth.
rig auth status --runtime codex # presence / mode / parseability / login-state (never prints token contents)
rig auth list --runtime codex # saved profiles
rig auth save <profile> --runtime codex # snapshot the auth FILE (mode-guarded), never echoes contents
rig auth switch <profile> --runtime codex
rig auth validate <profile> --runtime codex
rig auth seats … --runtime codex # seat -> profile registry (metadata only; NOT proof of a live account)
Hard secret boundary: no token value is ever printed, logged, queued, streamed, or committed; status/validate report presence/mode/login-state only; seat labels are metadata, not live-account proof. MVP is --runtime codex; other runtimes use the same surface with a different --runtime, never a parallel command.
A runtime's login lives in its home: Claude Code's in its config dir (CLAUDE_CONFIG_DIR, default ~/.claude), Codex's
in CODEX_HOME (default ~/.codex). A seat that names its own home in env: runs on that home's login.
CLAUDE_CONFIG_DIR=/abs/path claude, then /login; or
CODEX_HOME=/abs/path codex login. The person signs in; never copy credential files between homes.env: in rig.yaml, not with rig up --env, which leaves these two out
(CLAUDE_CONFIG_DIR: /abs/path or CODEX_HOME: /abs/path), or in
the rig's env: for every seat of that runtime. The member's value wins. It must be an absolute path: any other
value is reported and ignored, and the seat keeps the daemon's home.rig seat status <seat> shows the home and where it came from, and rig provider status lists it as
the seat's configured account. Both say what's configured, not which login a running session holds.Seats may share a home. OpenRig writes its own settings (Codex hooks, managed config.toml and plugin; Claude's
first-run trust settings) into the seat's home.
For a Codex seat on Linux. The login must already be saved in the Codex home the seat runs on (rig seat status <seat>
shows it). Other operating systems, and moving a seat to another home, aren't supported by this command yet: say so instead
of improvising. A Claude seat moves differently; see the next section.
CODEX_HOME=<home> codex login (the person signs in), then
CODEX_HOME=<home> rig auth save <name>. rig auth list --codex-home <home> lists them.rig provider precheck --seat <seat> --to-account <name> shows the home, what the seat is doing, and every
peer on that home. A refusal says what's missing, and nothing changes.rig provider switch --seat <seat> --to-account <name>. It saves the home's current login as
before-switch-<time>, activates the chosen one, and restarts the seat in place on the same conversation. If the
current login can't be saved first, nothing changes. Peers on the home aren't restarted. Each keeps its current login
only until its next token refresh, when Codex stops it with "signed in to another account". Run the printed
rig seat restart <peer> --keep-conversation --reason "..." for each to move it too. Don't sign in again in that home: that replaces
the login you just switched to.rig seat restart <seat> --keep-conversation --verify --expect-account <its Account line>. Until then the move is
unconfirmed. An uncertain restart is reported; never restart it a second time.The seat keeps its config dir and gets its own CLAUDE_CODE_OAUTH_TOKEN, read from a file as Claude starts. OpenRig keeps only
the file's path and your label, never the token.
claude setup-token, which prints a one-year subscription token, and saves it to a
file only their user can read (chmod 600). Never paste the token into a message, a row or a command line.rig provider precheck --seat <seat> --to-account <label> --token-file <absolute path>. It refuses, changing
nothing, if the file wouldn't apply, the seat isn't running, or something Claude Code ranks above the token is set (a cloud
provider, ANTHROPIC_AUTH_TOKEN, ANTHROPIC_API_KEY, an apiKeyHelper). It names each one and how to remove it for that
seat. When the token applies, the launch unsets those names for Claude's process, so the pane shell's own exports can't
outrank it. Managed settings can't be read; the seat's /status shows what it actually uses.rig provider switch --seat <seat> --to-account <label> --token-file <absolute path>. It takes a snapshot that
resumes the seat's conversation, sets the reference, and relaunches the seat from that snapshot in its own pane: the pane
and its scrollback stay, but work in flight when Claude ended doesn't carry over. Seats sharing the config dir keep their
own login. --stored-login moves the seat back; if the seat still receives a CLAUDE_CODE_OAUTH_TOKEN, Claude uses that
instead of the stored login, and the report names it./status shows token auth, with no account email. The
label is yours, not an account Claude observed: say so. A token session can't use claude.ai connectors or Remote Control.
The token is in Claude's environment, so the tools, hooks and MCP servers it starts inherit it; don't have it print its
environment. A relaunch that didn't resume reads unknown, with its recovery command; never run the switch again for it.
rig seat status <seat> shows the reference, and says when its file won't apply at the next launch.This applies only when the person has asked you to manage their subscriptions. Otherwise, don't take this job on. Installing or upgrading OpenRig appoints no agent, launches no bundle and starts no rotation.
When a person runs several Claude and Codex subscriptions across machines, the fleet studio bundle's one agent is meant to keep work running, through the Fleet app. Until that bundle is available, the agent the person asks to manage their subscriptions can use this section. If that's you, you decide which subscription or home moves, and when. You decide from:
rig provider moves);You say why, and you see the outcome through. OpenRig gives you the facts and the tools; it never decides for you, and there's no threshold to obey.
Who decides:
The unit is a Codex home, with every seat on it. Moving some seats on a shared home to a different account, and
moving Claude seats, aren't supported moves yet: say so instead of improvising. A Codex seat with a home of its own
moves alone, with rig provider switch --seat (above).
Load the person's account policy.
account-policy: check rig context list for it, then read it with
rig context get account-policy. Its manifest's version is the version you follow and report.{ "none": true }, and
offer once to write one with them (below).Know the subscriptions.
rig auth list and rig auth save) on each
machine. Which seats use which profile is rig auth seats, and that's metadata: not proof of a live account.Read before deciding.
rig provider status --all-hosts --json (add --refresh for fresh native readings). Each allowance has
its windows, reset times and when it was observed, and when it was last observed exhausted.expectation (expected full since that reset). You may plan on it,
but it isn't measured: report it as expected, and take a fresh reading when you can.unknown isn't . An otherwise authorized move can go ahead, and its uptake
evidence settles it. A known is step 6.What wakes you: a watchdog, a usage-limit park on the queue, or the person asking. How often you look is your judgment within those.
If there's no policy yet. Start from what you can see, and ask only what you can't; keep it to a few minutes, and never run it as a form. "Whatever you think" or "skip" is an answer: write down the default you'll use.
Look first: rig auth list and rig auth seats on each machine you can reach, rig provider status --all-hosts --json, and rig usage top on each machine. Draft what you can.
Confirm what you saw, in one message ("three Codex subscriptions and one Claude one, on two machines; the build box uses about four times the tokens of the laptop; any I can't see?").
Ask how they want them used, offering the common shape: the busiest machine gets its own subscription, the rest share, and one stays spare.
Ask what you may do on your own: move a machine's Codex seats without asking; machines or seats to ask about first or never move; sign-ins (may agents, and through which browser or profile, or always ask). Say what's supported today: moves are by Codex home, Claude moves aren't supported yet, and a sign-in preference is used only where a sign-in route and access exist.
Ask how to reach them (their seat's queue, a chat channel, the Fleet app), for what, and what to do when they
don't answer. A channel they name is a preference: check the route with messaging-the-human, and use a queue
item to their seat if it isn't ready.
Ask what to do when things go wrong: nothing has room, a sign-in is needed while they're away, a move didn't confirm.
Show the draft in plain words, let them correct it, and save it as a context pack named account-policy in
the context library where you run (rig config get context.root): a folder with manifest.yaml (version: "1",
name: account-policy, taxonomy: world, a purpose, and files: [{ path: POLICY.md, role: policy }]) and
POLICY.md, installed with rig context add <folder> and read back with rig context get account-policy. To share
one policy across machines, use a Git repository: rig context add <repo> --git. Labels and references only:
never tokens, passwords, cookies or recovery codes.
POLICY.md has these parts, in their words: subscriptions (label, provider, plan, how each is reached); how they
want them used; what agents may do on their own; how to reach them; when things go wrong; and a dated Changes
list. Fill it from what you saw and what they said, never from another person's setup.
Changing the policy. When they say what changed, copy POLICY.md aside as the before copy, edit it, add a dated
line under Changes, and raise version in manifest.yaml. Keep one place where it's edited: edited where it's
installed, run rig context sync; kept in a separate folder, replace it with rig context rm account-policy and
rig context add <folder>; Git-backed, edit and commit in the checkout rig context source inspect account-policy
reports, then rig context source update account-policy (it never pushes). Read it back with
rig context get account-policy; your next decision follows the new version.
Compose context once, hand it to a seat cleanly. A library primitive plus a set of delivery flags. The rule that keeps the grammar coherent — internalize this one: the noun stores and composes; the verbs deliver. rig context never sends anything; delivery is only ever rig send / rig broadcast / rig walk / rig queue.
Version note: this describes the library surface introduced in 0.5.0. Check the installed command and serving daemon before relying on it. In 0.4.x, bare
rig contextwas a context-window usage viewer (above); in 0.5.0 that viewer is removed and therig contextname belongs to the library here.
rig context — the store + compose library (never delivers)Manage and compose context (any text/markdown) into reusable packs. Every piece and pack has a stable, path-like ref — you address context the way you address files (skills/claude-compaction-restore, reference/rig-spec.md).
rig context list # what's in the library
rig context show <ref> # read a piece or pack
rig context add <source-dir> # install an existing pack directory into the store
rig context preview <ref> # assemble + show a pack WITHOUT delivering it
rig context sync # re-walk discovery roots, refresh the library index
rig context rm <ref>
rig context compose --out packs/<ref> --from <fileA> <fileB> ... # ordered pieces -> a durable pack
compose (v1) is honest ordered concatenation of named files into a durable pack with a ref — "here's a file, read a file."rig walk — paced delivery of a sequencerig walk <seat> --through <ref | file ...> --pace 10s
Walk a seat through a pack: each piece is sent into the pane, spaced by --pace, so the agent processes between sends (the human paste → wait → paste rhythm). Its own top-level verb, push-direction — the walker leads and does not wait for replies; the spacing does the work. Reach for walk on onboarding, repriming, or a fleet update — anything absorbed in order rather than all at once.
send --context; real pack → walk. An oversized send --context warns "this is walk-sized" instead of blasting the pane.--body-context snapshot rule: a qitem built from a ref stores the resolved content in its body plus the ref for provenance — the handoff carries what was actually sent, and a later library edit never silently rewrites a past handoff's history.rig context compose --out packs/qitem-brief --from <brief-file> <proof-file>
rig queue create --destination dev-driver@build --body-context packs/qitem-brief \
--summary "…" --tags "project:<id>,mission:<id>,slice:<id>"
Replace <brief-file> and <proof-file> with your existing local files. The curated context rides the durable handoff, survives compaction, and is auditable.Skills tier vs context tier: skills are the HOT tier (ambient, finite, always-visible front-matter); context packs are the COLD tier (unbounded, fetched on instruction — "read rig context get onboarding-width"). Don't overrun the skill layer by using skills as context packs — that's what this primitive is for.
rig up <source>
rig up <source> --plan
rig up <source> --yes
rig up <source> --cwd /path/to/project
rig up <source> --existing
rig up <source> --fresh <seat...>
rig up <source> --json
<source> can be:
.rigbundle pathBare names are special:
rig up launches from the spec libraryrig up treats the name as an existing-rig restore/power-on targetrig up fails loudly on ambiguityResume-original-by-default (v0.3.4+):
rig up <name> resumes each seat from its original session/snapshot by default (operation A). Seats that successfully resume report resumed.--fresh <seat...> is the per-seat opt-in for deliberate fresh-prime (operation B). Named seats are reported as fresh-primed.--existing forces existing-rig restore semantics on a bare name, bypassing library-spec resolution. Useful when a rig name collides with a library spec name.rig up --existing my-rig --fresh dev-impl — resume everything in my-rig except dev-impl, which is freshly primed.awaiting-decision (zero-session honest state, NOT failed); see the five-term restore vocabulary in "Recovery and Resilience" below.--plan (v0.3.4+):
rig up <source> --plan produces a read-only restore plan preview. It surfaces per-seat resume/fresh-prime intent and any awaiting-decision seats without mutating state. Honest async timeout: a stuck plan reports the timeout rather than hanging silently.Current behavior notes:
--target <root> is only for .rigbundle / package i© 2026 Skills Rack.
---name: openrig-userdescription: >----# packages/daemon/assets/plugins/openrig-core/skills/openrig-user/SKILL.mdFAQ
Download packages/daemon/assets/plugins/openrig-core/skills/openrig-user/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
The publisher keeps it at https://github.com/mvschwarz/openrig.
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.
--host <id> — send on a remote host declared in ~/.openrig/hosts.yaml (ssh hosts shell out; http hosts go CLI-direct to the remote daemon).--from <session> — deprecated and ignored; it does not select the sender. Sender identity comes from the current seat and transport provenance; cross-host envelopes use the durable local origin, not the supplied flag or a relay identity.--context <ref> (0.5.0) — attach a composed context pack/piece by ref (see "Context packs and paced delivery"). Small piece → send --context; a real pack → rig walk. The noun rig context composes the ref; the verb delivers it.needs_sign_inneeds_sign_inDecide, and leave seats alone for a reason.
rig usage top on each machine shows which work hardest: a high-use machine is worth a
subscription of its own, and lower-use machines can share one. Keep a backup where the policy says so.rig seat restart <seat> --keep-conversation --plan shows what a restart keeps, and every peer on the same
home. Moving the home moves them all.Move the home.
rig auth switch <profile> --runtime codex --codex-home <that home>, on that machine, or from here with
--host <that machine's SSH entry>. Without --codex-home, rig auth acts on CODEX_HOME, or on the default
home; rig auth status --codex-home <home> (with --host for another machine) prints which home it means:
check it before switching. A remote switch always names its home, and copies a profile already saved there.rig host list. An entry registered only over HTTP
can't run these commands; use the machine's SSH entry, or run them on that machine.rig seat restart <seat> --keep-conversation --reason "<why>", with --host <id>
for a seat on another machine (the restart runs there, and its audit names you). If the connection drops, the
answer is remote-outcome-unknown: the switch or restart may have run there, so read what it names (for a
restart, --plan's lastRestart) before anything else.rig seat restart <seat> --keep-conversation --verify --expect-account <the target's Account line>. --verify only checks; it never restarts. Only that check
reports moved, and anything less is unconfirmed.Report every move, partial or unconfirmed included, with
rig provider moves report --file <move.json> --to <whoever asked> (--help shows the shape). It becomes a queue
item to them; the Fleet app reads these reports once its page is connected to them. It holds:
{ "none": true });observed with its observation time, expected with the reset it rests on, or
unavailable;moved only with the verify check's matched account and observed tool turn, kept as separate
facts; otherwise unconfirmed or unknown, with what's missing;A home switched with every seat left as a peer is still a move to report. A follow-up that confirms an earlier
unconfirmed seat is a new report with --follows <the earlier report's qitemId>. A report to a person's seat names
its evidence with --evidence-ref (for example, the saved --verify --json output). Never put credentials in a
report: a value in a recognized credential format is refused. A refused report changes nothing about the move:
correct it and file it again; never repeat the switch or a restart because a report was refused. Asked "why did
these seats move?", even after your own restart, answer from rig provider moves --seat <seat>. It reads the newest
reports (50 by default, --limit up to 200) and then filters them, so it's a recent window, not a seat's whole
history: raise --limit when you need older ones.
When a sign-in is needed:
When nothing has room: say so, with the reset times. Never fall back to an API key, buy anything, or create an account.