Plan how agents retain active work across conversation compaction, context loss, and restarts. Organize restoration packets that preserve purpose, progress, ownership, and constraints, distinguish resume from fork or rebuild, and check whether work actually resumes correctly.
Use when reasoning about what survives compaction/context-loss/restart/seat-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).
Review the instructions the agent will receive before you install.
Preserving useful working state across compaction, context loss, restart, or seat refresh. Includes Claude compaction restore, Codex resume/fork mechanics, transcript-based mental-model rebuilds, and durable handoff packets.
Long-lived seats are valuable only if they can survive context pressure. If compaction turns a senior seat into a cold-started agent, users will avoid persistent topologies and fall back to throwaway agents.
session-source-fork or agent-startersPer the cross-runtime restore/reentry packet standard:
| Mode | What it means | Outcome literal |
|---|---|---|
| Native resume | Continue the same managed seat with native runtime token | resumed |
| Fork | New managed seat from prior native runtime conversation; new post-fork token | forked |
| Rebuild | Fresh-launch seeded with operator-declared artifacts in trust-precedence order | rebuilt |
| Artifact-backed mental-model rebuild | Restored seat derives understanding from a packet rather than native runtime continuity | (case of rebuilt) |
| Fresh launch | New agent without prior continuity | fresh |
These are load-bearing distinctions. Do NOT collapse fork into
artifact-backed reentry; do NOT collapse rebuild into fork.
The outcomes above ride on three DISTINCT mechanisms; keep them separate:
/compact — a Claude Code HARNESS feature, not OpenRig
code. OpenRig only emits the literal /compact toward the pane after a prep
turn; there is no compaction algorithm in the OpenRig repo. Provider-owned.hookSpecificOutput.additionalContext),
seat-isolated. The OpenRig-owned half.codex resume <token>),
a separate path from the Claude mechanisms. Never conflate with Claude restore.Safety boundary (ties to native-session-file-lab-boundary): no supported
OpenRig path EDITS provider-owned native session / auth / transcript files to
inject context. Context enters ONLY through sanctioned channels: the hook
additionalContext, a normal user message via rig send, or Codex resume tokens.
Precise nuance: OpenRig does write ~/.codex/config.toml — but only to install
OpenRig activity hooks and [features], never session or auth state. So the
rule is "never edits native session/auth/transcript files," NOT "never touches any
provider-owned file."
While policies.claude_compaction.enabled is true with a valid threshold (the enforcer treats any other
threshold as off), every Claude session OpenRig launches (fresh, fork, resume and restore; ordinary, kernel,
team-default and full-bypass seats) carries idleCompaction: false in its one --settings value. Claude Code then
doesn't compact an idle session on its own, so managed seats compact through OpenRig's sequence (restore map, then
/compact at the threshold).
idleCompaction: true in user or project settings for those
launches. Claude's managed settings still win.autoCompactEnabled, DISABLE_AUTO_COMPACT). Where the enforcer
has no fresh status-line usage sample for a seat, it doesn't compact that seat, and native auto-compaction is then
the only compaction. Nothing guarantees a native fallback.Managed compaction/restore is driven by five shipped verbs — pick per intent, and stay durable-substrate-first (the packet/artifacts are the truth; the CLI is the trigger):
rig compact <session> — guided managed compaction for ONE Claude seat
(prep → /compact → restore → audit). Non-Claude seats rejected. ~180s.rig compact-plan — READ-ONLY triage; does not compact. Flags --rig,
--refresh, --threshold-tokens, --threshold-percent. (Codex seats flagged
codex_not_managed_by_claude_compact_in_place.)rig restore-check — restore-readiness probe across running rigs; read-only;
exit 0/1/2. Flags --full, --ready, --rig, --no-queue, --no-hooks.rig restore-packet {write,read,validate} — the cross-runtime restore
packet (v0): write / read / validate the durable packet this skill's contract defines.rig restore <snapshotId> --rig <rigId> — ⚠ RIG SNAPSHOT restore (infra), a
DIFFERENT mechanism — NOT session-context restore. Do not conflate.Re-entering project context, on any runtime. A restore packet carries the work in flight, not the project's
declared intent and context files. rig context work-install lists what the project declares; read the pieces the
restored task needs. --deliver prints them all, and when several projects are declared (--json lists the
ids), select one with --project <id> instead of guessing.
Proof should include a deliberate compaction/restart of a seat with active work, followed by measured recovery: identity, current workflow, next owner, relevant files, and constraints all restored without human re-briefing.
The cross-runtime restore/reentry packet standard v0 defines:
Plus a 6-item restored-seat acceptance checklist.
Source-trust ranking applies when restored seat ingests packet evidence:
rig whoami > target rigspec > bounded latest transcript > full
transcript > touched-files > restore-summary.json.
A restore may consume transcripts, durable messages, startup context, checkpoints and a restore packet. Inventory the surfaces actually present for this seat, with their source, freshness and purpose. Do not infer that a named surface exists or grants write authority.
The active project/rig policy and task authorization determine what may be
written. Treat provider-owned conversation records as evidence to read through
supported tooling. For placement and durable context, load
skills/openrig-operating-model/SKILL.md with rig context get; for the
selected startup path, use skills/core/agent-startup-and-context-ingestion/SKILL.md.
A packet or marker proves retained/delivered evidence, not successful provider
restoration; measure the resumed seat against the proof standard above.
Before a planned compaction, restart or long pause, write the seat's authored recap
with rig context recap-write --rig <rig> --seat <seat> --file <draft>. Its format is
in seat-continuity-and-handover, "Write the seat's recap before a handover". A
rebuild reads it before LEARNED.md, and a profile source of seat:RECAP.md serves
it after a restore.
claude-compaction-restore skill — the Claude Code restore SOP (PreCompact hook + JSONL restore script for post-compaction recovery)session-source-fork skill — fork mode for native-runtime-continuity-based restorationseat-continuity-and-handover skill — occupant-creation primitives (resume/fork/rebuild/fresh) that this primitive instantiatesopenrig-operating-model skill — placement and authority of durable contextNo reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Automate website interactions through a command-line browser tool. Navigate pages, fill forms, extract text, save screenshots or PDFs, reuse login sessions, and compare page states to check the effects of actions or website changes.
Design and maintain applications where OpenRig agents help run the system. Organize instructions, shared state, and artifact checks, then trace unexpected behavior to the code, skill, or schema that needs repair.
Design and run bounded procedures in environments where current conditions are uncertain. The skill separates agent judgment from precise tool actions, verifies each effect, and records checkpoints so interrupted work can resume from observed evidence.
Create reusable starting configurations that combine an agent’s role, startup context, and source history. The skill guides registry entries, checks whether their sources are current, and manages their progression from initial capture to recommendation or retirement.
Guides the design and review of agent startup context, including role files and links to authoritative records. It helps identify stale guidance, missing updates, overloaded startup files, and instructions that lose the purpose of the work.
Configure selected OpenRig command permissions in Claude Code or Codex at the agreed project or user scope. Preserve existing restrictions, verify that settings load and behave as intended, and record additions so they can be removed later.