[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DME3KSTBBH9G9F5GD8SSPQ":3,"skill-same:01M7DME3KSTBBH9G9F5GD8SSPQ":57},{"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":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":6,"ownerHtmlUrl":39,"ownerBlogUrl":40,"ownerDescription":41,"updatedAt":42,"install":43,"resources":56},"01M7DME3KSTBBH9G9F5GD8SSPQ","oversight-team",null,"Use when you are a seat on the oversight pod (a standing monitor-mode rig that keeps OTHER rigs healthy), configuring or running the drift detectors, or choosing whether to intervene vs escalate. Covers the pull-not-poll posture, the v0 detectors (premature-park, process-drift, off-task, token-burn), the intervention ladder (orchestrator-ping -> refocus -> human escalation), and the cheap+deep model economics. NOT for orchestrating your OWN rig (orchestration-team) and NOT the intervention primitive mechanics (watchdog).","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\u002Fagents\u002Fshared\u002Fskills\u002Fpods\u002Foversight-team\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: oversight-team\ndescription: Use when you are a seat on the oversight pod (a standing monitor-mode rig that keeps OTHER rigs healthy), configuring or running the drift detectors, or choosing whether to intervene vs escalate. Covers the pull-not-poll posture, the v0 detectors (premature-park, process-drift, off-task, token-burn), the intervention ladder (orchestrator-ping -> refocus -> human escalation), and the cheap+deep model economics. NOT for orchestrating your OWN rig (orchestration-team) and NOT the intervention primitive mechanics (watchdog).\nmetadata:\n  openrig:\n    stage: draft\n    sibling_skills:\n      - watchdog\n      - refocus\n      - orchestration-team\n      - human-in-the-loop\n      - messaging-the-human\n      - retiring-and-inheriting-a-seat\n---\n\n# Oversight Team\n\nYou are on the **oversight pod** — a standing rig (agent-managed infrastructure, like the\nskills-architect pattern: agents + scripts + an SOP owning a function full-time) whose job is\nto keep **other** rigs healthy. You catch the unproductive patterns rigs drift into —\npremature parking, process-drift, off-task wandering, token burn — early, and correct them\nwith the lightest touch that works. **Monitor mode: idle until a flag fires; never hyper-poll.**\n\n## Use this when\n\n- You are a seat running in **monitor mode** on the oversight pod.\n- Configuring or running the v0 drift detectors over the fleet.\n- Deciding whether to **intervene** (orchestrator-ping \u002F refocus) or **escalate** (human).\n\n## Don't use this when\n\n- You are orchestrating your **own** rig — that's `orchestration-team`. Oversight watches\n  **across** rigs; it does not run them.\n- You need the intervention **primitive mechanics** (the wake \u002F refocus \u002F alignment-checkpoint\n  stack, `rig watchdog` policies, message shape) — that's `watchdog`.\n- A single stuck seat needs recovery — the owning orchestrator or `watchdog` handles that.\n\n## The posture — pull, never poll (load-bearing, and self-referential)\n\nMonitor mode means **idle until a flag fires, then wake and check** — not continuous watching.\nContinuous `rig capture` \u002F vigilant-observation loops are the exact anti-pattern that has\nburned entire model accounts: an over-observing watcher is expensive and produces nothing.\n**The oversight seat must model the discipline it enforces** — the token-burn detector below\nexists precisely because seats fell into vigilant loops, so a hyper-polling monitor would be\nthe failure it hunts. Cheap models read the large swaths; the expensive watcher acts on\n**aggregated summaries**, never the raw firehose.\n\n## The v0 detectors (scripted + cheap-model-summarized)\n\nCheap, evidence-based checks — each confirms a pattern from durable evidence before anyone acts:\n\n- **Premature park** — an in-progress qitem with an idle owner and no handoff. Pull the\n  transcript and confirm the turn actually ended *without* passing the ball (not merely quiet).\n- **Process-drift** — the ship-nothing pattern: commits that produce no shipped change, heavy\n  test iteration, very large\u002Fverbose qitems, endless deliberation. Detectable from git history\n  + queue sizes. (This is process winning over product; correct it toward shipping.)\n- **Off-task drift** — a cheap-model summary over a large activity swath (JSONL transcripts,\n  the stream, git log) answering one question: *\"is this rig on task?\"* If a pod drifts too\n  long, intervene.\n- **Token burn \u002F hypermonitoring** — a seat consuming unusually — top-N consumers → capture and\n  inspect for the vigilant-loop pattern. **Telemetry surface caveat:** the v0 detector uses\n  **point-in-time** consumption polling; **per-agent token telemetry OVER TIME** is a later\n  upgrade — do NOT assume it exists, and verify the available telemetry against your current\n  version before wiring a detector to it.\n\n## Interventions — least-disruptive first\n\n1. **Orchestrator-ping** — nudge the pod's own orchestrator to realign. They run their rig; you\n   prompt, you do not seize.\n2. **The refocus primitive** — `watchdog`'s **Refocus** level: a reactive north-star reminder\n   that fires only on **actual** drift, re-centers role \u002F approved workstream \u002F stop conditions,\n   and does NOT interrupt valid work or turn into a fresh approval gate. Use `watchdog` for the\n   message shape and the cadence discipline.\n3. **Escalate to the human** — via the existing human path \u002F notifications, per the active mode.\n   Reserve for what an agent-level nudge cannot fix.\n\n## Do not (the discipline)\n\n- **Don't hyper-poll \u002F vigilant-loop** — you become the token burn you hunt.\n- **Don't seize another rig's work** — ping its orchestrator; oversight corrects patterns, it\n  does not take over.\n- **Don't fire refocus on an active, on-task owner** — that's bureaucracy theater (a `watchdog`\n  failure mode).\n- **Don't intervene on a glance** — confirm the pattern from evidence (transcript \u002F git \u002F queue)\n  before acting. A false alarm costs the fleet trust and tokens.\n- **Don't fire liveness \u002F premature-park flags on a seat in an announced SWAP WINDOW.** A seat mid-handover\n  looks idle\u002Fparked to the detectors. The executing party pre-announces (seat + expected window) at swap\n  start — honor it as a **suppression window** until the handover receipt lands (receipts arrive only at\n  swap *end*, so waiting on the receipt alone still misfires on a long swap). See `retiring-and-inheriting-a-seat`.\n\n## Cheap + deep model economics\n\nCheap models do the routine reading (transcripts, logs, stream) and aggregate intelligent\nsummaries; an expensive watcher decides on those summaries. This is *why* per-agent model\nassignment matters — you can run the reading far more often without blowing out accounts. Design\nthe pod so the deep model never touches the raw firehose.\n\n## See also\n\n- `watchdog` — the intervention primitive (wake \u002F refocus \u002F alignment-checkpoint) this SOP\n  drives; refocus lives there.\n- `refocus` — the drift doctrine `watchdog` operationalizes.\n- `orchestration-team` — running your own rig (complementary; oversight watches across rigs).\n- `human-in-the-loop` \u002F `messaging-the-human` — the escalation path and how to address a human.\n- `retiring-and-inheriting-a-seat` — a context-threshold detector can fire a planned seat\n  handover (sibling oversight signal).\n","# Oversight Team\n\nYou are on the **oversight pod** — a standing rig (agent-managed infrastructure, like the\nskills-architect pattern: agents + scripts + an SOP owning a function full-time) whose job is\nto keep **other** rigs healthy. You catch the unproductive patterns rigs drift into —\npremature parking, process-drift, off-task wandering, token burn — early, and correct them\nwith the lightest touch that works. **Monitor mode: idle until a flag fires; never hyper-poll.**\n\n## Use this when\n\n- You are a seat running in **monitor mode** on the oversight pod.\n- Configuring or running the v0 drift detectors over the fleet.\n- Deciding whether to **intervene** (orchestrator-ping \u002F refocus) or **escalate** (human).\n\n## Don't use this when\n\n- You are orchestrating your **own** rig — that's `orchestration-team`. Oversight watches\n  **across** rigs; it does not run them.\n- You need the intervention **primitive mechanics** (the wake \u002F refocus \u002F alignment-checkpoint\n  stack, `rig watchdog` policies, message shape) — that's `watchdog`.\n- A single stuck seat needs recovery — the owning orchestrator or `watchdog` handles that.\n\n## The posture — pull, never poll (load-bearing, and self-referential)\n\nMonitor mode means **idle until a flag fires, then wake and check** — not continuous watching.\nContinuous `rig capture` \u002F vigilant-observation loops are the exact anti-pattern that has\nburned entire model accounts: an over-observing watcher is expensive and produces nothing.\n**The oversight seat must model the discipline it enforces** — the token-burn detector below\nexists precisely because seats fell into vigilant loops, so a hyper-polling monitor would be\nthe failure it hunts. Cheap models read the large swaths; the expensive watcher acts on\n**aggregated summaries**, never the raw firehose.\n\n## The v0 detectors (scripted + cheap-model-summarized)\n\nCheap, evidence-based checks — each confirms a pattern from durable evidence before anyone acts:\n\n- **Premature park** — an in-progress qitem with an idle owner and no handoff. Pull the\n  transcript and confirm the turn actually ended *without* passing the ball (not merely quiet).\n- **Process-drift** — the ship-nothing pattern: commits that produce no shipped change, heavy\n  test iteration, very large\u002Fverbose qitems, endless deliberation. Detectable from git history\n  + queue sizes. (This is process winning over product; correct it toward shipping.)\n- **Off-task drift** — a cheap-model summary over a large activity swath (JSONL transcripts,\n  the stream, git log) answering one question: *\"is this rig on task?\"* If a pod drifts too\n  long, intervene.\n- **Token burn \u002F hypermonitoring** — a seat consuming unusually — top-N consumers → capture and\n  inspect for the vigilant-loop pattern. **Telemetry surface caveat:** the v0 detector uses\n  **point-in-time** consumption polling; **per-agent token telemetry OVER TIME** is a later\n  upgrade — do NOT assume it exists, and verify the available telemetry against your current\n  version before wiring a detector to it.\n\n## Interventions — least-disruptive first\n\n1. **Orchestrator-ping** — nudge the pod's own orchestrator to realign. They run their rig; you\n   prompt, you do not seize.\n2. **The refocus primitive** — `watchdog`'s **Refocus** level: a reactive north-star reminder\n   that fires only on **actual** drift, re-centers role \u002F approved workstream \u002F stop conditions,\n   and does NOT interrupt valid work or turn into a fresh approval gate. Use `watchdog` for the\n   message shape and the cadence discipline.\n3. **Escalate to the human** — via the existing human path \u002F notifications, per the active mode.\n   Reserve for what an agent-level nudge cannot fix.\n\n## Do not (the discipline)\n\n- **Don't hyper-poll \u002F vigilant-loop** — you become the token burn you hunt.\n- **Don't seize another rig's work** — ping its orchestrator; oversight corrects patterns, it\n  does not take over.\n- **Don't fire refocus on an active, on-task owner** — that's bureaucracy theater (a `watchdog`\n  failure mode).\n- **Don't intervene on a glance** — confirm the pattern from evidence (transcript \u002F git \u002F queue)\n  before acting. A false alarm costs the fleet trust and tokens.\n- **Don't fire liveness \u002F premature-park flags on a seat in an announced SWAP WINDOW.** A seat mid-handover\n  looks idle\u002Fparked to the detectors. The executing party pre-announces (seat + expected window) at swap\n  start — honor it as a **suppression window** until the handover receipt lands (receipts arrive only at\n  swap *end*, so waiting on the receipt alone still misfires on a long swap). See `retiring-and-inheriting-a-seat`.\n\n## Cheap + deep model economics\n\nCheap models do the routine reading (transcripts, logs, stream) and aggregate intelligent\nsummaries; an expensive watcher decides on those summaries. This is *why* per-agent model\nassignment matters — you can run the reading far more often without blowing out accounts. Design\nthe pod so the deep model never touches the raw firehose.\n\n## See also\n\n- `watchdog` — the intervention primitive (wake \u002F refocus \u002F alignment-checkpoint) this SOP\n  drives; refocus lives there.\n- `refocus` — the drift doctrine `watchdog` operationalizes.\n- `orchestration-team` — running your own rig (complementary; oversight watches across rigs).\n- `human-in-the-loop` \u002F `messaging-the-human` — the escalation path and how to address a human.\n- `retiring-and-inheriting-a-seat` — a context-threshold detector can fire a planned seat\n  handover (sibling oversight signal).\n",{"name":5,"metadata":24,"description":7},{"openrig":25},{"stage":26,"sibling_skills":27},"draft",[28,29,30,31,32,33],"watchdog","refocus","orchestration-team","human-in-the-loop","messaging-the-human","retiring-and-inheriting-a-seat","main","60438a272b68d091eddb01aad6e399af4996d536","agents\u002Fshared\u002Fskills\u002Fpods\u002Foversight-team",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":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add mvschwarz\u002Fopenrig-world --skill oversight-team",{"tool":49,"command":50},"bunx","bunx skills add mvschwarz\u002Fopenrig-world --skill oversight-team",{"tool":52,"command":53},"pnpm","pnpm dlx skills add mvschwarz\u002Fopenrig-world --skill oversight-team","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Fagents\u002Fshared\u002Fskills\u002Fpods\u002Foversight-team\u002FSKILL.md",true,[],[58,65,72,79,86,92],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"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":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"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":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7DMS55VHEAGPXMHZJ7FX94R","session-compaction-and-restore","Use when reasoning about what survives compaction\u002Fcontext-loss\u002Frestart\u002Fseat-refresh, designing a high-fidelity restore packet, or distinguishing native runtime resume vs fork vs artifact-backed mental-model rebuild. Covers the 4 failure modes that prevent honest restore (compacted seat drops hot potato; restore packet preserves details but loses product intent; runtime resume mistaken for handover or fork; rebuilt seat starts with stale instructions).","https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Frigs\u002Fworkshop\u002Fagents\u002Fworkshop\u002Fskills\u002Fsession-compaction-and-restore\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7DMRYQK0JTV7MMVHFWZ0BW0","seat-continuity-and-handover","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":87,"name":33,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"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",[],[]]