[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DMGA0586RRTJG40AF38EF7":3,"skill-same:01M7DMGA0586RRTJG40AF38EF7":56},{"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":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":6,"ownerHtmlUrl":38,"ownerBlogUrl":39,"ownerDescription":40,"updatedAt":41,"install":42,"resources":55},"01M7DMGA0586RRTJG40AF38EF7","agent-operated-software",null,"Use when designing, building, operating, or diagnosing an ongoing application whose live backend or control loop includes OpenRig agents, including applications with a Markdown, YAML, or JSON agent control plane or a thin surface over specialist agent roles.","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\u002Fagent-operated-software\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: agent-operated-software\ndescription: >-\n  Use when designing, building, operating, or diagnosing an ongoing application whose live backend\n  or control loop includes OpenRig agents, including applications with a Markdown, YAML, or JSON\n  agent control plane or a thin surface over specialist agent roles.\nmetadata:\n  openrig:\n    stage: provisional\n    audience: any agent building or operating an agent-backed application\n    sibling_skills:\n      - agent-operated-workflows\n      - forming-an-openrig-mental-model\n      - mission-slice-sop\n      - openrig-user\n---\n\n# Agent-Operated Software\n\n**Agent-Operated Software** is an ongoing application whose functioning runtime includes an OpenRig\nagent or rig in its live backend or control loop. The application surface can be thin: structured\nstate and specialist roles do the work, while the UI makes that work legible and steerable.\n\n## Start with the shared taxonomy\n\n- **AI-enabled software:** application code owns the control loop and calls a model as one capability.\n- **Agent-Operated Workflow:** an agent owns one bounded procedure with a start and stop condition;\n  see `agent-operated-workflows`.\n- **Agent-Operated Software:** agents participate in an ongoing application's functioning runtime.\n\nAn application may compose many Agent-Operated Workflows. A bounded workflow does not by itself make\nits surrounding product Agent-Operated Software, and a model call is neither category unless an agent\nowns part of the control loop.\n\n## Agents are part of the backend\n\nIn this architecture, behavior is not located only in functions. It is distributed across agents,\nskills, instructions, bootstrap files, schemas, Markdown, YAML, JSON, folders, and deterministic\ntools. A surprising result may therefore be a code defect or a coherence gap in this control plane.\nTrace the path that actually produced the behavior before choosing which layer to repair.\n\nThis is not permission to tolerate defects in OpenRig core or another rock-solid substrate. There,\nreproduce the bug, fix the code, and hold the full gate. The faster coherence-first posture belongs\nto recoverable agent-operated application layers whose state and behavior can be inspected and\nrepaired cheaply.\n\n## Markdown is the control plane\n\nMarkdown is maximally useful to an agent while remaining legible enough for a human to steer. Put\nintent, work state, evidence, and decisions into stable addressed artifacts rather than private chat\nor an opaque custom database. Keep schemas and conventions aligned with the running behavior: the\nagent population acts on those files as executable context.\n\nUse **progressive disclosure**. A skill's name and description are the hot trigger; its body is cold\nprocedure. Descriptions say when to load, not how to work. The body should route the reader to exact\nsources instead of copying them into another doctrine fork.\n\nScripts can act as prompts. A good script returns the context or exact effect an agent needs; when it\ncannot, its failure teaches what it observed, why it stopped, and safe next actions. Keep deterministic\nmechanics in tools and judgment in agents.\n\n## Make artifacts self-certifying\n\nWhen a tool produces an artifact, do not make every consumer invent a completeness test:\n\n1. Write to a partial path, never the final path.\n2. Verify the property that can actually be wrong, such as duration, streams, resolution, or schema.\n3. Flush and atomically rename the partial artifact to its final path.\n4. Write the manifest, then a `.done` sentinel last.\n\nConsumers of an artifact fail closed on the shared proof: don't read a file before its sentinel exists,\nbecause it may be half-written. A filename or exit code is not content verification. This rule is for\nartifact integrity only. For delivery, routing and checks, uncertainty fails open: deliver, and report\nwhat couldn't be checked. The hard lines are the exception: when a change can't tell whether it would\nexpose a credential, delete someone's data, spend money or publish, it stops and asks.\n\n## Build with an agent SDLC\n\nSelect the rigor required by the outcome and the project's policy. Scope relationships,\nattributed evidence-backed item judgment, and genuinely distinct higher judgment have separate\nowners. One item judgment derives its upstream readiness; agents do not synchronize parent\ncheckboxes, queue tags, or status prose. Capture alone is not acceptance, and readiness does not\npublish or advance a workflow. Use `openrig-operating-model` and `rig proof --help` for the\nsupported judgment, correction, and read path. Keep historical locks and evidence addressable.\nThe human supplies steering, taste, and decisions the project's authority reserves for them.\n\nFor studio applications, the running product is usually the best iteration surface. A separate mockup\nearns its cost only when it resolves a real design uncertainty that the running app cannot expose as\ncheaply. This removes a redundant artifact, not the visual review or proof contract.\n\n## Repair the narrowest authoritative layer\n\nFind the generator or source that every affected agent actually consumes. Fix a code defect in code;\nfix a missing trigger in the skill; fix a malformed contract in its schema. Then verify through the\nconsumer. Editing a rendered or installed copy creates a temporary fork, not a repair.\n\nThe payoff compounds: a correction to the shared application control plane changes the next agent's\nstarting point. That is how an ongoing agent-operated system improves without making one human its\npermanent router.\n","# Agent-Operated Software\n\n**Agent-Operated Software** is an ongoing application whose functioning runtime includes an OpenRig\nagent or rig in its live backend or control loop. The application surface can be thin: structured\nstate and specialist roles do the work, while the UI makes that work legible and steerable.\n\n## Start with the shared taxonomy\n\n- **AI-enabled software:** application code owns the control loop and calls a model as one capability.\n- **Agent-Operated Workflow:** an agent owns one bounded procedure with a start and stop condition;\n  see `agent-operated-workflows`.\n- **Agent-Operated Software:** agents participate in an ongoing application's functioning runtime.\n\nAn application may compose many Agent-Operated Workflows. A bounded workflow does not by itself make\nits surrounding product Agent-Operated Software, and a model call is neither category unless an agent\nowns part of the control loop.\n\n## Agents are part of the backend\n\nIn this architecture, behavior is not located only in functions. It is distributed across agents,\nskills, instructions, bootstrap files, schemas, Markdown, YAML, JSON, folders, and deterministic\ntools. A surprising result may therefore be a code defect or a coherence gap in this control plane.\nTrace the path that actually produced the behavior before choosing which layer to repair.\n\nThis is not permission to tolerate defects in OpenRig core or another rock-solid substrate. There,\nreproduce the bug, fix the code, and hold the full gate. The faster coherence-first posture belongs\nto recoverable agent-operated application layers whose state and behavior can be inspected and\nrepaired cheaply.\n\n## Markdown is the control plane\n\nMarkdown is maximally useful to an agent while remaining legible enough for a human to steer. Put\nintent, work state, evidence, and decisions into stable addressed artifacts rather than private chat\nor an opaque custom database. Keep schemas and conventions aligned with the running behavior: the\nagent population acts on those files as executable context.\n\nUse **progressive disclosure**. A skill's name and description are the hot trigger; its body is cold\nprocedure. Descriptions say when to load, not how to work. The body should route the reader to exact\nsources instead of copying them into another doctrine fork.\n\nScripts can act as prompts. A good script returns the context or exact effect an agent needs; when it\ncannot, its failure teaches what it observed, why it stopped, and safe next actions. Keep deterministic\nmechanics in tools and judgment in agents.\n\n## Make artifacts self-certifying\n\nWhen a tool produces an artifact, do not make every consumer invent a completeness test:\n\n1. Write to a partial path, never the final path.\n2. Verify the property that can actually be wrong, such as duration, streams, resolution, or schema.\n3. Flush and atomically rename the partial artifact to its final path.\n4. Write the manifest, then a `.done` sentinel last.\n\nConsumers of an artifact fail closed on the shared proof: don't read a file before its sentinel exists,\nbecause it may be half-written. A filename or exit code is not content verification. This rule is for\nartifact integrity only. For delivery, routing and checks, uncertainty fails open: deliver, and report\nwhat couldn't be checked. The hard lines are the exception: when a change can't tell whether it would\nexpose a credential, delete someone's data, spend money or publish, it stops and asks.\n\n## Build with an agent SDLC\n\nSelect the rigor required by the outcome and the project's policy. Scope relationships,\nattributed evidence-backed item judgment, and genuinely distinct higher judgment have separate\nowners. One item judgment derives its upstream readiness; agents do not synchronize parent\ncheckboxes, queue tags, or status prose. Capture alone is not acceptance, and readiness does not\npublish or advance a workflow. Use `openrig-operating-model` and `rig proof --help` for the\nsupported judgment, correction, and read path. Keep historical locks and evidence addressable.\nThe human supplies steering, taste, and decisions the project's authority reserves for them.\n\nFor studio applications, the running product is usually the best iteration surface. A separate mockup\nearns its cost only when it resolves a real design uncertainty that the running app cannot expose as\ncheaply. This removes a redundant artifact, not the visual review or proof contract.\n\n## Repair the narrowest authoritative layer\n\nFind the generator or source that every affected agent actually consumes. Fix a code defect in code;\nfix a missing trigger in the skill; fix a malformed contract in its schema. Then verify through the\nconsumer. Editing a rendered or installed copy creates a temporary fork, not a repair.\n\nThe payoff compounds: a correction to the shared application control plane changes the next agent's\nstarting point. That is how an ongoing agent-operated system improves without making one human its\npermanent router.\n",{"name":5,"metadata":24,"description":7},{"openrig":25},{"stage":26,"audience":27,"sibling_skills":28},"provisional","any agent building or operating an agent-backed application",[29,30,31,32],"agent-operated-workflows","forming-an-openrig-mental-model","mission-slice-sop","openrig-user","main","60438a272b68d091eddb01aad6e399af4996d536","rigs\u002Fworkshop-review-pair\u002Fagents\u002Fworkshop\u002Fskills\u002Fagent-operated-software",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":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add mvschwarz\u002Fopenrig-world --skill agent-operated-software",{"tool":48,"command":49},"bunx","bunx skills add mvschwarz\u002Fopenrig-world --skill agent-operated-software",{"tool":51,"command":52},"pnpm","pnpm dlx skills add mvschwarz\u002Fopenrig-world --skill agent-operated-software","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmvschwarz\u002Fopenrig-world\u002Fblob\u002Fmain\u002Frigs\u002Fworkshop-review-pair\u002Fagents\u002Fworkshop\u002Fskills\u002Fagent-operated-software\u002FSKILL.md",true,[],[57,64,71,78,85,92],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"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":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"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":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":80,"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","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":86,"name":87,"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","retiring-and-inheriting-a-seat","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",[],[]]