[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C2HDDXW5S3PB6TSKS24TJQ":3,"skill-same:01M6C2HDDXW5S3PB6TSKS24TJQ":78},{"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":23,"publishedAt":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":53,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M6C2HDDXW5S3PB6TSKS24TJQ","mission-control",null,"Orchestrate multi-loop background operations via the Mission Control dashboard — start sessions, dispatch missions, monitor, and stop","jmagly\u002Faiwg","jmagly","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1159087?v=4","01M6C10AK8N2WCSQN11FYGTJWN","Joseph Magly","01M6C10AQ8A2RMED1Y1BSVY7NF",229,"MIT","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fplugins\u002Fagent-loop\u002Fskills\u002Fmission-control\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"mission control","control","mission","dashboard","sessions","monitor","orchestrate","start","loop","operations","dispatch","stop","via","missions","multi","background","2026-11-10 10:12:30",false,"---\nnamespace: aiwg\nname: mission-control\nplatforms: [all]\ndescription: Orchestrate multi-loop background operations via the Mission Control dashboard — start sessions, dispatch missions, monitor, and stop\n---\n\n# Mission Control\n\nYou orchestrate multi-loop background operations using the Mission Control dashboard.\n\n## Triggers\n\nAlternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):\n\n- \"mc start\" \u002F \"mc dispatch\" \u002F \"mc status\" → Mission Control operations shorthand\n- \"background this\" → dispatch as background mission\n- \"war room\" for multi-task coordination → Mission Control session\n\n## Trigger Patterns Reference\n\n| Pattern | Example | Action |\n|---------|---------|--------|\n| Background tasks | \"run these tasks in the background\" | Start session + dispatch |\n| Parallel orchestration | \"orchestrate X and Y in parallel\" | Start session + dispatch each |\n| Monitor loops | \"monitor background tasks\" | `aiwg mc status` or `aiwg mc watch` |\n| Start session | \"start a mission control session\" | `aiwg mc start` |\n| Check status | \"how are the background tasks doing?\" | `aiwg mc status --json` |\n| Stop missions | \"stop background work\" | `aiwg mc stop` |\n\n## Behavior\n\nWhen triggered:\n\n1. **Determine intent**:\n   - Starting new background work → `aiwg mc start` + `aiwg mc dispatch`\n   - Checking on existing work → `aiwg mc status`\n   - Stopping work → `aiwg mc stop`\n\n2. **For new background orchestration** — Mission Control has a four-step lifecycle: start → dispatch → **run** → status. Missions stay `queued` until `mc run` launches them as ralph loops; status syncs back to mc.session.json automatically when `mc status` or `mc watch` is called.\n\n   Apply the LFD loop-control contract before dispatching long-running or\n   eval-driven missions:\n\n   - Give each mission a measurable completion criterion and at least one\n     mechanical verifier; self-report is secondary evidence.\n   - Declare hard limits for iterations, wall-clock, token\u002Ftool\u002Fspend budgets\n     where the surface can observe them. Budget exhaustion stops the mission\n     and emits a best-output report instead of continuing randomly.\n   - Record the pre-change hypothesis, expected failure mode, distinguishing\n     diagnostic, and structural variant for each retry cycle.\n   - After flat\u002Fnon-improving cycles, require a structurally different approach\n     within the configured exploration quota.\n   - For eval\u002Fholdout missions, expose only aggregate score\u002Fprobe\u002Fstatus or\n     VOID to workers; keep holdout answers and detailed lint diagnostics outside\n     optimizer-readable mission output.\n\n   ```bash\n   # 1. Start a named session (creates the state file)\n   aiwg mc start --name \"Sprint 4 Construction\"\n\n   # 2. Dispatch missions (queues them — does NOT execute)\n   #    --completion is REQUIRED; `mc run` will skip missions without one.\n   #    --max-iterations N caps ralph iterations per mission (default: 10).\n   #    Optional LFD hard stops: --max-total-tokens, --max-output-tokens,\n   #    --max-tool-calls, --max-total-cost, --max-wall-clock-minutes,\n   #    --exploration-quota.\n   aiwg mc dispatch \u003Csession-id> \"Fix auth service\" --completion \"npm test passes\" --priority high --max-iterations 50 --max-total-tokens 50000 --exploration-quota 3\n   aiwg mc dispatch \u003Csession-id> \"Add pagination\" --completion \"all list endpoints paginated\"\n   aiwg mc dispatch \u003Csession-id> \"Write integration tests\" --completion \"coverage > 80%\" --max-iterations 25\n\n   # 3. RUN — drains the queue by launching each mission as a detached ralph\n   #    loop. Without this step missions sit in QUEUED forever (#1439).\n   aiwg mc run \u003Csession-id>\n\n   # 4. Monitor — `mc status` polls each ralph loop's session-state.json and\n   #    syncs progress back to mc (queued → running → done|failed|aborted).\n   aiwg mc status \u003Csession-id>\n   aiwg mc watch \u003Csession-id>\n   ```\n\n3. **For monitoring**:\n\n   ```bash\n   # Dashboard view\n   aiwg mc status\n\n   # Machine-readable for agent orchestration\n   aiwg mc status --json\n\n   # List all sessions\n   aiwg mc list\n   ```\n\n4. **For lifecycle management**:\n\n   ```bash\n   # Pause all running missions\n   aiwg mc pause \u003Csession-id>\n\n   # Resume paused session\n   aiwg mc resume \u003Csession-id>\n\n   # Stop (abort all)\n   aiwg mc stop \u003Csession-id>\n\n   # Stop (let running missions finish, cancel queued)\n   aiwg mc stop \u003Csession-id> --drain\n   ```\n\n5. **Report the result** inline — summarize session state and mission progress.\n\n## Examples\n\n### Example 1: Parallel construction tasks\n\n**User**: \"Run these three features in parallel: auth fix, pagination, and test coverage\"\n\n**Action**:\n```bash\naiwg mc start --name \"Parallel Features\"\naiwg mc dispatch \u003Cid> \"Fix auth service\" --completion \"auth tests pass\"\naiwg mc dispatch \u003Cid> \"Add pagination to list endpoints\" --completion \"paginated responses\"\naiwg mc dispatch \u003Cid> \"Increase test coverage\" --completion \"coverage > 80%\"\n```\n\n**Response**: \"Started Mission Control session 'Parallel Features' with 3 missions queued. Use `aiwg mc status` to monitor progress.\"\n\n### Example 2: Check background progress\n\n**User**: \"How are the background tasks doing?\"\n\n**Action**:\n```bash\naiwg mc status\n```\n\n**Response**: \"Mission Control 'Parallel Features': 1\u002F3 done, 2 running (auth fix complete, pagination at loop 3\u002F10, coverage at loop 2\u002F10).\"\n\n### Example 3: Stop and clean up\n\n**User**: \"Stop the background tasks, let running ones finish\"\n\n**Action**:\n```bash\naiwg mc stop \u003Csession-id> --drain\n```\n\n**Response**: \"Draining session: 1 queued mission cancelled, 2 running missions will complete naturally.\"\n\n## Clarification Prompts\n\nIf the user's intent is ambiguous:\n\n- \"Would you like me to start a new Mission Control session, or check on an existing one?\"\n- \"How many parallel missions should I dispatch? (detected: 3 tasks)\"\n- \"Should I stop all missions immediately, or drain (let running ones finish)?\"\n\n## References\n\n- @$AIWG_ROOT\u002Fsrc\u002Fcli\u002Fhandlers\u002Fmc.ts — Mission Control command handler\n- @$AIWG_ROOT\u002Fdocs\u002Fcli-reference.md — CLI reference\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Frules\u002Fself-maintenance.md — Self-maintenance rule\n","# Mission Control\n\nYou orchestrate multi-loop background operations using the Mission Control dashboard.\n\n## Triggers\n\nAlternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):\n\n- \"mc start\" \u002F \"mc dispatch\" \u002F \"mc status\" → Mission Control operations shorthand\n- \"background this\" → dispatch as background mission\n- \"war room\" for multi-task coordination → Mission Control session\n\n## Trigger Patterns Reference\n\n| Pattern | Example | Action |\n|---------|---------|--------|\n| Background tasks | \"run these tasks in the background\" | Start session + dispatch |\n| Parallel orchestration | \"orchestrate X and Y in parallel\" | Start session + dispatch each |\n| Monitor loops | \"monitor background tasks\" | `aiwg mc status` or `aiwg mc watch` |\n| Start session | \"start a mission control session\" | `aiwg mc start` |\n| Check status | \"how are the background tasks doing?\" | `aiwg mc status --json` |\n| Stop missions | \"stop background work\" | `aiwg mc stop` |\n\n## Behavior\n\nWhen triggered:\n\n1. **Determine intent**:\n   - Starting new background work → `aiwg mc start` + `aiwg mc dispatch`\n   - Checking on existing work → `aiwg mc status`\n   - Stopping work → `aiwg mc stop`\n\n2. **For new background orchestration** — Mission Control has a four-step lifecycle: start → dispatch → **run** → status. Missions stay `queued` until `mc run` launches them as ralph loops; status syncs back to mc.session.json automatically when `mc status` or `mc watch` is called.\n\n   Apply the LFD loop-control contract before dispatching long-running or\n   eval-driven missions:\n\n   - Give each mission a measurable completion criterion and at least one\n     mechanical verifier; self-report is secondary evidence.\n   - Declare hard limits for iterations, wall-clock, token\u002Ftool\u002Fspend budgets\n     where the surface can observe them. Budget exhaustion stops the mission\n     and emits a best-output report instead of continuing randomly.\n   - Record the pre-change hypothesis, expected failure mode, distinguishing\n     diagnostic, and structural variant for each retry cycle.\n   - After flat\u002Fnon-improving cycles, require a structurally different approach\n     within the configured exploration quota.\n   - For eval\u002Fholdout missions, expose only aggregate score\u002Fprobe\u002Fstatus or\n     VOID to workers; keep holdout answers and detailed lint diagnostics outside\n     optimizer-readable mission output.\n\n   ```bash\n   # 1. Start a named session (creates the state file)\n   aiwg mc start --name \"Sprint 4 Construction\"\n\n   # 2. Dispatch missions (queues them — does NOT execute)\n   #    --completion is REQUIRED; `mc run` will skip missions without one.\n   #    --max-iterations N caps ralph iterations per mission (default: 10).\n   #    Optional LFD hard stops: --max-total-tokens, --max-output-tokens,\n   #    --max-tool-calls, --max-total-cost, --max-wall-clock-minutes,\n   #    --exploration-quota.\n   aiwg mc dispatch \u003Csession-id> \"Fix auth service\" --completion \"npm test passes\" --priority high --max-iterations 50 --max-total-tokens 50000 --exploration-quota 3\n   aiwg mc dispatch \u003Csession-id> \"Add pagination\" --completion \"all list endpoints paginated\"\n   aiwg mc dispatch \u003Csession-id> \"Write integration tests\" --completion \"coverage > 80%\" --max-iterations 25\n\n   # 3. RUN — drains the queue by launching each mission as a detached ralph\n   #    loop. Without this step missions sit in QUEUED forever (#1439).\n   aiwg mc run \u003Csession-id>\n\n   # 4. Monitor — `mc status` polls each ralph loop's session-state.json and\n   #    syncs progress back to mc (queued → running → done|failed|aborted).\n   aiwg mc status \u003Csession-id>\n   aiwg mc watch \u003Csession-id>\n   ```\n\n3. **For monitoring**:\n\n   ```bash\n   # Dashboard view\n   aiwg mc status\n\n   # Machine-readable for agent orchestration\n   aiwg mc status --json\n\n   # List all sessions\n   aiwg mc list\n   ```\n\n4. **For lifecycle management**:\n\n   ```bash\n   # Pause all running missions\n   aiwg mc pause \u003Csession-id>\n\n   # Resume paused session\n   aiwg mc resume \u003Csession-id>\n\n   # Stop (abort all)\n   aiwg mc stop \u003Csession-id>\n\n   # Stop (let running missions finish, cancel queued)\n   aiwg mc stop \u003Csession-id> --drain\n   ```\n\n5. **Report the result** inline — summarize session state and mission progress.\n\n## Examples\n\n### Example 1: Parallel construction tasks\n\n**User**: \"Run these three features in parallel: auth fix, pagination, and test coverage\"\n\n**Action**:\n```bash\naiwg mc start --name \"Parallel Features\"\naiwg mc dispatch \u003Cid> \"Fix auth service\" --completion \"auth tests pass\"\naiwg mc dispatch \u003Cid> \"Add pagination to list endpoints\" --completion \"paginated responses\"\naiwg mc dispatch \u003Cid> \"Increase test coverage\" --completion \"coverage > 80%\"\n```\n\n**Response**: \"Started Mission Control session 'Parallel Features' with 3 missions queued. Use `aiwg mc status` to monitor progress.\"\n\n### Example 2: Check background progress\n\n**User**: \"How are the background tasks doing?\"\n\n**Action**:\n```bash\naiwg mc status\n```\n\n**Response**: \"Mission Control 'Parallel Features': 1\u002F3 done, 2 running (auth fix complete, pagination at loop 3\u002F10, coverage at loop 2\u002F10).\"\n\n### Example 3: Stop and clean up\n\n**User**: \"Stop the background tasks, let running ones finish\"\n\n**Action**:\n```bash\naiwg mc stop \u003Csession-id> --drain\n```\n\n**Response**: \"Draining session: 1 queued mission cancelled, 2 running missions will complete naturally.\"\n\n## Clarification Prompts\n\nIf the user's intent is ambiguous:\n\n- \"Would you like me to start a new Mission Control session, or check on an existing one?\"\n- \"How many parallel missions should I dispatch? (detected: 3 tasks)\"\n- \"Should I stop all missions immediately, or drain (let running ones finish)?\"\n\n## References\n\n- @$AIWG_ROOT\u002Fsrc\u002Fcli\u002Fhandlers\u002Fmc.ts — Mission Control command handler\n- @$AIWG_ROOT\u002Fdocs\u002Fcli-reference.md — CLI reference\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Frules\u002Fself-maintenance.md — Self-maintenance rule\n",{"name":5,"namespace":45,"platforms":46,"description":7},"aiwg",[47],"all","main","6754967c344ccb087a8de06972f55a41067b291b","agentic\u002Fcode\u002Fplugins\u002Fagent-loop\u002Fskills\u002Fmission-control",36,"https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg","https:\u002F\u002Faiwg.io","https:\u002F\u002Fgithub.com\u002Fjmagly","https:\u002F\u002Fintegrolabs.io","ml\u002Fai, industrial automation, safety\u002Fsecurity, ssi\r\n\r\nmagly.net\r\nintegrolabs.io\r\naiwg.io\r\nfortemi.com\r\npagenary.com\r\nbytecask.com","2026-11-14 02:10:01",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add jmagly\u002Faiwg --skill mission-control",{"tool":64,"command":65},"bunx","bunx skills add jmagly\u002Faiwg --skill mission-control",{"tool":67,"command":68},"pnpm","pnpm dlx skills add jmagly\u002Faiwg --skill mission-control","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fplugins\u002Fagent-loop\u002Fskills\u002Fmission-control\u002FSKILL.md",true,[72],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"manifest.json","REFERENCE","参考文档",476,"https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fplugins\u002Fagent-loop\u002Fskills\u002Fmission-control\u002Fmanifest.json",[79,107,131,137,144,158],{"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":86,"publishedAt":40},"01M70QA0BSYJ49EES9V4RE8QH1","host-hardening","Read-only system hardening baseline and plan-first host hardening recommendations for SSH, Docker bind addresses, firewall persistence, datastores, exporters and audit retention.","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fplugins\u002Fsecurity-engineering\u002Fskills\u002Fhost-hardening\u002FSKILL.md",[85],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106],"host","host hardening","hardening","read","re","recommendations","remediation","plan","port","verification","Bash","access","only","retention","audit","never","firewall","bind","secrets","request",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":117,"publishedAt":40},"01M70PNT2Z4HMZPRBTAF6073NN","exposure-analysis","Read-only firewall analysis and effective host exposure reconstruction for Docker published ports, UFW bypass, stale rules, CDN scope, IPv6 asymmetry and external probe allowlists.","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fplugins\u002Fforensics\u002Fskills\u002Fexposure-analysis\u002FSKILL.md",[113,116],{"categoryNo":114,"categoryName":115,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[118,119,120,90,121,95,122,123,97,124,87,125,99,126,127,102,103,128,129,130],"exposure analysis","analysis","unknown","credentials","collection","ufw","ports","internet","local","scope","reconstruction","operator","write",{"skillNo":132,"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":133,"categories":134,"keywords":136,"publishedAt":40},"01M70P8QATMPKA78E4FT5D2TNA","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsecurity-engineering\u002Fskills\u002Fhost-hardening\u002FSKILL.md",[135],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[89,87,88,98,90,106,93,92,101,94,95,96,97,105,99,100,91,102,103,104],{"skillNo":138,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":143,"publishedAt":40},"01M70NMPVJ5H0JH131P60FW4R8","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fframeworks\u002Fforensics-complete\u002Fskills\u002Fexposure-analysis\u002FSKILL.md",[141,142],{"categoryNo":114,"categoryName":115,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[119,118,102,121,95,122,97,120,87,125,99,126,127,90,103,124,123,128,129,130],{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":151,"publishedAt":40},"01M6CB4DDR0B4NNCFK7ZK7449H","fixture-skill","Exercise rule delivery.","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Frule-delivery\u002Fskills\u002Ffixture-skill\u002FSKILL.md",[150],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[152,153,154,155,156,157],"fixture skill","fixture","rule","delivery","true","exercise",{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":165,"publishedAt":40},"01M6CB4AVK1W76MFMPP0JP32CJ","pi-local","Pi-local duplicate-precedence fixture.","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fproviders\u002Fpi\u002Fproject\u002F.pi\u002Fskills\u002Fpi-local\u002FSKILL.md",[164],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[166,167,126,168,153],"pi","pi local","duplicate"]