[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DMMK7R9DMZMQ394CG6JWMX":3,"skill-same:01M7DMMK7R9DMZMQ394CG6JWMX":59},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":36,"commitSha":37,"skillDirectory":38,"forksCount":39,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":41,"ownerBlogUrl":42,"ownerDescription":43,"updatedAt":44,"install":45,"resources":58},"01M7DMMK7R9DMZMQ394CG6JWMX","session-compaction-and-restore",null,"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).","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-review-pair\u002Fagents\u002Fworkshop\u002Fskills\u002Fsession-compaction-and-restore\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: session-compaction-and-restore\ndescription: 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).\nmetadata:\n  cli_surfaces_referenced:\n    - whoami\n  openrig:\n    stage: factory-approved\n    sibling_skills:\n      - claude-compaction-restore\n      - agent-startup-and-context-ingestion\n      - agent-starters\n      - session-source-fork\n      - seat-continuity-and-handover\n      - retiring-and-inheriting-a-seat\n---\n\n# Session Compaction and Restore\n\nPreserving useful working state across **compaction, context loss,\nrestart, or seat refresh.** Includes Claude compaction restore, Codex\nresume\u002Ffork mechanics, transcript-based mental-model rebuilds, and\ndurable handoff packets.\n\n**Long-lived seats are valuable only if they can survive context\npressure.** If compaction turns a senior seat into a cold-started\nagent, users will avoid persistent topologies and fall back to\nthrowaway agents.\n\n## Use this when\n\n- A seat is approaching compaction or just compacted\n- Designing a high-fidelity restore packet for an active workflow\n- Distinguishing native runtime resume vs fork vs artifact-backed mental-model rebuild\n- Reasoning about what should be preserved vs reconstructable\n- Auditing a restore for product-intent preservation (not just detail preservation)\n\n## Don't use this when\n\n- The session is fresh and has no working state to preserve\n- The intent is to *create* a new seat from a primed source — that's `session-source-fork` or `agent-starters`\n- The packet is a one-off snapshot for human review — restore packets are for re-entering active work\n\n## The 5 distinctions (do not collapse)\n\nPer the cross-runtime restore\u002Freentry packet standard:\n\n| Mode | What it means | Outcome literal |\n|---|---|---|\n| **Native resume** | Continue the same managed seat with native runtime token | `resumed` |\n| **Fork** | New managed seat from prior native runtime conversation; new post-fork token | `forked` |\n| **Rebuild** | Fresh-launch seeded with operator-declared artifacts in trust-precedence order | `rebuilt` |\n| **Artifact-backed mental-model rebuild** | Restored seat derives understanding from a packet rather than native runtime continuity | (case of `rebuilt`) |\n| **Fresh launch** | New agent without prior continuity | `fresh` |\n\nThese are load-bearing distinctions. **Do NOT collapse `fork` into\nartifact-backed reentry; do NOT collapse `rebuild` into fork.**\n\n## The three mechanisms — who owns each (verified vs main d37a08ad, 2026-07-21)\n\nThe outcomes above ride on three DISTINCT mechanisms; keep them separate:\n\n1. **Claude built-in `\u002Fcompact`** — a Claude Code HARNESS feature, **not OpenRig\n   code**. OpenRig only *emits* the literal `\u002Fcompact` toward the pane after a prep\n   turn; there is no compaction algorithm in the OpenRig repo. Provider-owned.\n2. **OpenRig-managed restore** — the enforcer + hook bridge: a precompact hook\n   WRITES a restore packet; a bridge READER injects exactly ONE restore directive\n   back via the harness hook channel (`hookSpecificOutput.additionalContext`),\n   seat-isolated. The OpenRig-owned half.\n3. **Codex session continuity** — resume\u002Frollout tokens (`codex resume \u003Ctoken>`),\n   a separate path from the Claude mechanisms. Never conflate with Claude restore.\n\n**Safety boundary (ties to `native-session-file-lab-boundary`):** no supported\nOpenRig path EDITS provider-owned native **session \u002F auth \u002F transcript** files to\ninject context. Context enters ONLY through sanctioned channels: the hook\n`additionalContext`, a normal user message via `rig send`, or Codex resume tokens.\nPrecise nuance: OpenRig *does* write `~\u002F.codex\u002Fconfig.toml` — but only to install\nOpenRig activity **hooks** and `[features]`, never session or auth state. So the\nrule is \"never edits native session\u002Fauth\u002Ftranscript files,\" NOT \"never touches any\nprovider-owned file.\"\n\n## Claude's own idle compaction while managed compaction is on\n\nWhile `policies.claude_compaction.enabled` is true with a valid threshold (the enforcer treats any other\nthreshold as off), every Claude session OpenRig launches (fresh, fork, resume and restore; ordinary, kernel,\nteam-default and full-bypass seats) carries `idleCompaction: false` in its one `--settings` value. Claude Code then\ndoesn't compact an idle session on its own, so managed seats compact through OpenRig's sequence (restore map, then\n`\u002Fcompact` at the threshold).\n\n- **Version boundary:** Claude Code supports the key from 2.1.290. Earlier versions ignore it, so idle compaction\n  stays possible there.\n- **Precedence:** it overrides a lower-precedence `idleCompaction: true` in user or project settings for those\n  launches. Claude's managed settings still win.\n- **Native threshold auto-compaction is untouched** (`autoCompactEnabled`, `DISABLE_AUTO_COMPACT`). Where the enforcer\n  has no fresh status-line usage sample for a seat, it doesn't compact that seat, and native auto-compaction is then\n  the only compaction. Nothing guarantees a native fallback.\n- **It applies at the next launch.** Turning the policy off leaves idle compaction off in a running session until\n  that session's next launch. Turning it on doesn't reach sessions already running.\n- **Policy off, or a non-Claude runtime:** the launch command is unchanged.\n\n## Current CLI surface (operator \u002F kernel seats; verified vs main d37a08ad)\n\nManaged compaction\u002Frestore is driven by five shipped verbs — pick per intent, and\nstay durable-substrate-first (the packet\u002Fartifacts are the truth; the CLI is the trigger):\n\n- **`rig compact \u003Csession>`** — guided managed compaction for ONE Claude seat\n  (prep → `\u002Fcompact` → restore → audit). Non-Claude seats rejected. ~180s.\n- **`rig compact-plan`** — READ-ONLY triage; *does not compact*. Flags `--rig`,\n  `--refresh`, `--threshold-tokens`, `--threshold-percent`. (Codex seats flagged\n  `codex_not_managed_by_claude_compact_in_place`.)\n- **`rig restore-check`** — restore-readiness probe across running rigs; read-only;\n  exit 0\u002F1\u002F2. Flags `--full`, `--ready`, `--rig`, `--no-queue`, `--no-hooks`.\n- **`rig restore-packet {write,read,validate}`** — the cross-runtime restore\n  packet (v0): write \u002F read \u002F validate the durable packet this skill's contract defines.\n- **`rig restore \u003CsnapshotId> --rig \u003CrigId>`** — ⚠ RIG SNAPSHOT restore (infra), a\n  DIFFERENT mechanism — NOT session-context restore. Do not conflate.\n\n## Failure modes (4)\n\n1. **A compacted seat forgets active workflow state and drops the hot potato.** Compaction without continuity preservation is silent failure.\n2. **A restore packet preserves details but loses the user's product intent.** Restore must preserve *why this work matters*, not just *what was happening*.\n3. **A runtime resume is mistaken for a seat handover or fork.** These have different continuity outcomes and provenance — don't conflate.\n4. **A rebuilt seat starts with stale instructions that conflict with current workflow mode.** Restore must include current state, not just historical state.\n\n**Re-entering project context, on any runtime.** A restore packet carries the work in flight, not the project's\ndeclared intent and context files. `rig context work-install` lists what the project declares; read the pieces the\nrestored task needs. `--deliver` prints them all, and when several projects are declared (`--json` lists the\nids), select one with `--project \u003Cid>` instead of guessing.\n\n## Proof standard\n\nProof should include a deliberate compaction\u002Frestart of a seat with\nactive work, followed by **measured recovery**: identity, current\nworkflow, next owner, relevant files, and constraints all restored\nwithout human re-briefing.\n\n## Canonical packet contract (16-field, v0)\n\nThe cross-runtime restore\u002Freentry packet standard v0 defines:\n\n- Source\u002Ftarget identity\n- Runtimes\n- Workspace root, default repo, role pointer\n- Bounded latest transcript\n- Touched-path inventory\n- Durable work pointers\n- Current work + next owner\n- Caveats + authority boundaries\n- Omitted classes + redaction policy\n- Source-trust ranking\n- Generated-at + generator version\n\nPlus a 6-item restored-seat acceptance checklist.\n\nSource-trust ranking applies when restored seat ingests packet evidence:\n**`rig whoami` > target rigspec > bounded latest transcript > full\ntranscript > touched-files > `restore-summary.json`.**\n\n## Memory surfaces consumed at restore time\n\nA restore may consume transcripts, durable messages, startup context,\ncheckpoints and a restore packet. Inventory the surfaces actually present for\nthis seat, with their source, freshness and purpose. Do not infer that a named\nsurface exists or grants write authority.\n\nThe active project\u002Frig policy and task authorization determine what may be\nwritten. Treat provider-owned conversation records as evidence to read through\nsupported tooling. For placement and durable context, load\n`skills\u002Fopenrig-operating-model\u002FSKILL.md` with `rig context get`; for the\nselected startup path, use `skills\u002Fcore\u002Fagent-startup-and-context-ingestion\u002FSKILL.md`.\nA packet or marker proves retained\u002Fdelivered evidence, not successful provider\nrestoration; measure the resumed seat against the proof standard above.\n\nBefore a planned compaction, restart or long pause, write the seat's authored recap\nwith `rig context recap-write --file \u003Cdraft>`. Its format is\nin `seat-continuity-and-handover`, \"Write the seat's recap before a handover\". A\nrebuild reads it before `LEARNED.md`, and a profile source of `seat:RECAP.md` serves\nit after a restore.\n\n## See also\n\n- `claude-compaction-restore` skill — the Claude Code restore SOP (PreCompact hook + JSONL restore script for post-compaction recovery)\n- `session-source-fork` skill — `fork` mode for native-runtime-continuity-based restoration\n- `seat-continuity-and-handover` skill — occupant-creation primitives (resume\u002Ffork\u002Frebuild\u002Ffresh) that this primitive instantiates\n- `openrig-operating-model` skill — placement and authority of durable context\n","# Session Compaction and Restore\n\nPreserving useful working state across **compaction, context loss,\nrestart, or seat refresh.** Includes Claude compaction restore, Codex\nresume\u002Ffork mechanics, transcript-based mental-model rebuilds, and\ndurable handoff packets.\n\n**Long-lived seats are valuable only if they can survive context\npressure.** If compaction turns a senior seat into a cold-started\nagent, users will avoid persistent topologies and fall back to\nthrowaway agents.\n\n## Use this when\n\n- A seat is approaching compaction or just compacted\n- Designing a high-fidelity restore packet for an active workflow\n- Distinguishing native runtime resume vs fork vs artifact-backed mental-model rebuild\n- Reasoning about what should be preserved vs reconstructable\n- Auditing a restore for product-intent preservation (not just detail preservation)\n\n## Don't use this when\n\n- The session is fresh and has no working state to preserve\n- The intent is to *create* a new seat from a primed source — that's `session-source-fork` or `agent-starters`\n- The packet is a one-off snapshot for human review — restore packets are for re-entering active work\n\n## The 5 distinctions (do not collapse)\n\nPer the cross-runtime restore\u002Freentry packet standard:\n\n| Mode | What it means | Outcome literal |\n|---|---|---|\n| **Native resume** | Continue the same managed seat with native runtime token | `resumed` |\n| **Fork** | New managed seat from prior native runtime conversation; new post-fork token | `forked` |\n| **Rebuild** | Fresh-launch seeded with operator-declared artifacts in trust-precedence order | `rebuilt` |\n| **Artifact-backed mental-model rebuild** | Restored seat derives understanding from a packet rather than native runtime continuity | (case of `rebuilt`) |\n| **Fresh launch** | New agent without prior continuity | `fresh` |\n\nThese are load-bearing distinctions. **Do NOT collapse `fork` into\nartifact-backed reentry; do NOT collapse `rebuild` into fork.**\n\n## The three mechanisms — who owns each (verified vs main d37a08ad, 2026-07-21)\n\nThe outcomes above ride on three DISTINCT mechanisms; keep them separate:\n\n1. **Claude built-in `\u002Fcompact`** — a Claude Code HARNESS feature, **not OpenRig\n   code**. OpenRig only *emits* the literal `\u002Fcompact` toward the pane after a prep\n   turn; there is no compaction algorithm in the OpenRig repo. Provider-owned.\n2. **OpenRig-managed restore** — the enforcer + hook bridge: a precompact hook\n   WRITES a restore packet; a bridge READER injects exactly ONE restore directive\n   back via the harness hook channel (`hookSpecificOutput.additionalContext`),\n   seat-isolated. The OpenRig-owned half.\n3. **Codex session continuity** — resume\u002Frollout tokens (`codex resume \u003Ctoken>`),\n   a separate path from the Claude mechanisms. Never conflate with Claude restore.\n\n**Safety boundary (ties to `native-session-file-lab-boundary`):** no supported\nOpenRig path EDITS provider-owned native **session \u002F auth \u002F transcript** files to\ninject context. Context enters ONLY through sanctioned channels: the hook\n`additionalContext`, a normal user message via `rig send`, or Codex resume tokens.\nPrecise nuance: OpenRig *does* write `~\u002F.codex\u002Fconfig.toml` — but only to install\nOpenRig activity **hooks** and `[features]`, never session or auth state. So the\nrule is \"never edits native session\u002Fauth\u002Ftranscript files,\" NOT \"never touches any\nprovider-owned file.\"\n\n## Claude's own idle compaction while managed compaction is on\n\nWhile `policies.claude_compaction.enabled` is true with a valid threshold (the enforcer treats any other\nthreshold as off), every Claude session OpenRig launches (fresh, fork, resume and restore; ordinary, kernel,\nteam-default and full-bypass seats) carries `idleCompaction: false` in its one `--settings` value. Claude Code then\ndoesn't compact an idle session on its own, so managed seats compact through OpenRig's sequence (restore map, then\n`\u002Fcompact` at the threshold).\n\n- **Version boundary:** Claude Code supports the key from 2.1.290. Earlier versions ignore it, so idle compaction\n  stays possible there.\n- **Precedence:** it overrides a lower-precedence `idleCompaction: true` in user or project settings for those\n  launches. Claude's managed settings still win.\n- **Native threshold auto-compaction is untouched** (`autoCompactEnabled`, `DISABLE_AUTO_COMPACT`). Where the enforcer\n  has no fresh status-line usage sample for a seat, it doesn't compact that seat, and native auto-compaction is then\n  the only compaction. Nothing guarantees a native fallback.\n- **It applies at the next launch.** Turning the policy off leaves idle compaction off in a running session until\n  that session's next launch. Turning it on doesn't reach sessions already running.\n- **Policy off, or a non-Claude runtime:** the launch command is unchanged.\n\n## Current CLI surface (operator \u002F kernel seats; verified vs main d37a08ad)\n\nManaged compaction\u002Frestore is driven by five shipped verbs — pick per intent, and\nstay durable-substrate-first (the packet\u002Fartifacts are the truth; the CLI is the trigger):\n\n- **`rig compact \u003Csession>`** — guided managed compaction for ONE Claude seat\n  (prep → `\u002Fcompact` → restore → audit). Non-Claude seats rejected. ~180s.\n- **`rig compact-plan`** — READ-ONLY triage; *does not compact*. Flags `--rig`,\n  `--refresh`, `--threshold-tokens`, `--threshold-percent`. (Codex seats flagged\n  `codex_not_managed_by_claude_compact_in_place`.)\n- **`rig restore-check`** — restore-readiness probe across running rigs; read-only;\n  exit 0\u002F1\u002F2. Flags `--full`, `--ready`, `--rig`, `--no-queue`, `--no-hooks`.\n- **`rig restore-packet {write,read,validate}`** — the cross-runtime restore\n  packet (v0): write \u002F read \u002F validate the durable packet this skill's contract defines.\n- **`rig restore \u003CsnapshotId> --rig \u003CrigId>`** — ⚠ RIG SNAPSHOT restore (infra), a\n  DIFFERENT mechanism — NOT session-context restore. Do not conflate.\n\n## Failure modes (4)\n\n1. **A compacted seat forgets active workflow state and drops the hot potato.** Compaction without continuity preservation is silent failure.\n2. **A restore packet preserves details but loses the user's product intent.** Restore must preserve *why this work matters*, not just *what was happening*.\n3. **A runtime resume is mistaken for a seat handover or fork.** These have different continuity outcomes and provenance — don't conflate.\n4. **A rebuilt seat starts with stale instructions that conflict with current workflow mode.** Restore must include current state, not just historical state.\n\n**Re-entering project context, on any runtime.** A restore packet carries the work in flight, not the project's\ndeclared intent and context files. `rig context work-install` lists what the project declares; read the pieces the\nrestored task needs. `--deliver` prints them all, and when several projects are declared (`--json` lists the\nids), select one with `--project \u003Cid>` instead of guessing.\n\n## Proof standard\n\nProof should include a deliberate compaction\u002Frestart of a seat with\nactive work, followed by **measured recovery**: identity, current\nworkflow, next owner, relevant files, and constraints all restored\nwithout human re-briefing.\n\n## Canonical packet contract (16-field, v0)\n\nThe cross-runtime restore\u002Freentry packet standard v0 defines:\n\n- Source\u002Ftarget identity\n- Runtimes\n- Workspace root, default repo, role pointer\n- Bounded latest transcript\n- Touched-path inventory\n- Durable work pointers\n- Current work + next owner\n- Caveats + authority boundaries\n- Omitted classes + redaction policy\n- Source-trust ranking\n- Generated-at + generator version\n\nPlus a 6-item restored-seat acceptance checklist.\n\nSource-trust ranking applies when restored seat ingests packet evidence:\n**`rig whoami` > target rigspec > bounded latest transcript > full\ntranscript > touched-files > `restore-summary.json`.**\n\n## Memory surfaces consumed at restore time\n\nA restore may consume transcripts, durable messages, startup context,\ncheckpoints and a restore packet. Inventory the surfaces actually present for\nthis seat, with their source, freshness and purpose. Do not infer that a named\nsurface exists or grants write authority.\n\nThe active project\u002Frig policy and task authorization determine what may be\nwritten. Treat provider-owned conversation records as evidence to read through\nsupported tooling. For placement and durable context, load\n`skills\u002Fopenrig-operating-model\u002FSKILL.md` with `rig context get`; for the\nselected startup path, use `skills\u002Fcore\u002Fagent-startup-and-context-ingestion\u002FSKILL.md`.\nA packet or marker proves retained\u002Fdelivered evidence, not successful provider\nrestoration; measure the resumed seat against the proof standard above.\n\nBefore a planned compaction, restart or long pause, write the seat's authored recap\nwith `rig context recap-write --file \u003Cdraft>`. Its format is\nin `seat-continuity-and-handover`, \"Write the seat's recap before a handover\". A\nrebuild reads it before `LEARNED.md`, and a profile source of `seat:RECAP.md` serves\nit after a restore.\n\n## See also\n\n- `claude-compaction-restore` skill — the Claude Code restore SOP (PreCompact hook + JSONL restore script for post-compaction recovery)\n- `session-source-fork` skill — `fork` mode for native-runtime-continuity-based restoration\n- `seat-continuity-and-handover` skill — occupant-creation primitives (resume\u002Ffork\u002Frebuild\u002Ffresh) that this primitive instantiates\n- `openrig-operating-model` skill — placement and authority of durable context\n",{"name":5,"metadata":24,"description":7},{"openrig":25,"cli_surfaces_referenced":34},{"stage":26,"sibling_skills":27},"factory-approved",[28,29,30,31,32,33],"claude-compaction-restore","agent-startup-and-context-ingestion","agent-starters","session-source-fork","seat-continuity-and-handover","retiring-and-inheriting-a-seat",[35],"whoami","main","60438a272b68d091eddb01aad6e399af4996d536","rigs\u002Fworkshop-review-pair\u002Fagents\u002Fworkshop\u002Fskills\u002Fsession-compaction-and-restore",4,"https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world","https:\u002F\u002Fgithub.com\u002Fmvschwarz","https:\u002F\u002Fopenrig.dev","Building OpenRig. Running rogue AI civilizations. Debugging their coordination problems.","2026-11-12 13:31:38",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add mvschwarz\u002Fopenrig-world --skill session-compaction-and-restore",{"tool":51,"command":52},"bunx","bunx skills add mvschwarz\u002Fopenrig-world --skill session-compaction-and-restore",{"tool":54,"command":55},"pnpm","pnpm dlx skills add mvschwarz\u002Fopenrig-world --skill session-compaction-and-restore","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Frigs\u002Fworkshop-review-pair\u002Fagents\u002Fworkshop\u002Fskills\u002Fsession-compaction-and-restore\u002FSKILL.md",true,[],[60,67,74,79,85,91],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7DMSEDCRREMBJF57RQB59HC","notes","Use when taking notes.","https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Ftools\u002Ftest\u002Ffixtures\u002Finstall-verify\u002Fbundle\u002Fagents\u002Fteam\u002Fskills\u002Fnotes\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7DMSBZP9WE8MC09JDXFCR2F","software-for-agents","Use when older OpenRig instructions name software-for-agents or describe agent-in-the-middle or studio software under the former skill name.","https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Frigs\u002Fworkshop\u002Fagents\u002Fworkshop\u002Fskills\u002Fsoftware-for-agents\u002FSKILL.md",[],[],{"skillNo":75,"name":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":76,"categories":77,"keywords":78,"publishedAt":19},"01M7DMS55VHEAGPXMHZJ7FX94R","https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Frigs\u002Fworkshop\u002Fagents\u002Fworkshop\u002Fskills\u002Fsession-compaction-and-restore\u002FSKILL.md",[],[],{"skillNo":80,"name":32,"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},"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":86,"name":33,"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},"01M7DMRP6RRGCJZSH9CE3PC1MY","Use when you are a sitting agent near your context threshold (~85%) and a PLANNED seat transition is due — retire deliberately and hand your seat to a fresh successor primed from a packet, rather than let compaction degrade you. Covers the handover packet, the append-only lineage ledger (one row per tenure), physical-seat continuity, the do-not-over-inherit framing, the optional warm-handoff window, and wake-v0 (consulting a retired predecessor). NOT for unplanned compaction\u002Fcrash recovery (session-compaction-and-restore \u002F claude-compaction-restore) and NOT the seat-binding primitive mechanics (seat-continuity-and-handover).","https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Frigs\u002Fworkshop\u002Fagents\u002Fworkshop\u002Fskills\u002Fretiring-and-inheriting-a-seat\u002FSKILL.md",[],[],{"skillNo":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",[],[]]