[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M758FFZR5W6S50CS8QKJRBSY":3,"skill-same:01M758FFZR5W6S50CS8QKJRBSY":54},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M758FFZR5W6S50CS8QKJRBSY","remediation-investigation",null,"Trace remediation sensor reports to their source, cross-reference live state, and distinguish transient from chronic cron failures.","lukemcqueen\u002Fsteadfaste-fleet","lukemcqueen","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F405240?v=4","01M757MHPAGRXTJAT46SKZP98R","Luke McQueen","01M757MHPZ573KP8DT9GB8SBQ7",4,"MIT","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Fremediation-investigation\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: remediation-investigation\ndescription: Trace remediation sensor reports to their source, cross-reference live state, and distinguish transient from chronic cron failures.\nversion: 1.0.0\n---\n\n# Remediation Investigation\n\n## When to Use\n\nLoad this skill when:\n- The `agent-remediation-sensor` reports a cron_error or service issue\n- You need to distinguish a transient timeout from a structural failure\n- The auto-remediation skill's known-fix table doesn't cover the reported error\n- You need to trace a sensor report back to the actual cron output or jobs.json state\n\n## Sensor Output Architecture\n\nThe `agent-remediation-sensor` (no_agent cron, every 5m) writes its findings as JSON\nto the **cron output directory**, NOT to a predictable path. Finding it requires scanning.\n\n### Finding the Latest Sensor Output\n\nThe sensor's job ID is not predictable. Scan for it:\n\n```bash\nfind ~\u002F.hermes\u002Fcron\u002Foutput\u002F -name \"*.md\" -mmin -10 | xargs grep -l \"remediation-sensor\\|cron_error\\|agent-remediation\" 2>\u002Fdev\u002Fnull | head -3\n```\n\nEach match is a full .md file containing a JSON array. Read the contents directly.\n\n### Sensor JSON Schema\n\n```json\n[\n  {\n    \"type\": \"cron_error\",\n    \"severity\": \"high\",\n    \"detail\": \"Errored cron: orch-skill-lifecycle\",\n    \"context\": {\n      \"job_id\": null,\n      \"name\": \"orch-skill-lifecycle\",\n      \"last_status\": \"error\"\n    },\n    \"timestamp\": \"2026-07-26T18:00:30.170571+00:00\"\n  }\n]\n```\n\n| Field | Type | Notes |\n|-------|------|-------|\n| `type` | string | `cron_error`, `disk_pressure`, `service_down`, etc. |\n| `severity` | string | `low`\u002F`medium`\u002F`high`\u002F`critical` |\n| `detail` | string | Human-readable description |\n| `context.name` | string | Cron job name (most useful field) |\n| `context.last_status` | string | `error` or `ok` |\n| `timestamp` | string | ISO timestamp of when sensor ran |\n\n## Cross-Referencing Sensor vs Live State\n\nThe sensor reads `last_status` from `~\u002F.hermes\u002Fcron\u002Fjobs.json`, which means:\n\n- **The sensor output can be up to 5 minutes stale** — the sensor runs every 5m\n- **`last_status=\"error\"` persists** until the job runs again successfully. An error from 12 hours ago still shows as \"error\" in the sensor report\n- **Always cross-reference `last_run_at` timestamp** to determine recency\n\n### Read jobs.json Directly\n\nThe `cronjob(action='list')` MCP tool does not exist. Use the raw jobs.json file:\n\n```python\nimport json, os\nwith open(os.path.expanduser('~\u002F.hermes\u002Fcron\u002Fjobs.json')) as f:\n    data = json.load(f)\nerrored = [j for j in data['jobs'] if j.get('last_status') == 'error']\n```\n\nKey fields in each job dict:\n\n| Field | Type | What it tells you |\n|-------|------|-------------------|\n| `name` | str | Cron job name |\n| `last_status` | str | `\"ok\"` or `\"error\"` |\n| `last_error` | str or null | The error message from the last run |\n| `last_run_at` | str (ISO) | When the job last ran |\n| `next_run_at` | str (ISO) | When it will next run |\n| `state` | str | `\"scheduled\"`, `\"paused\"`, etc. |\n| `enabled` | bool | Is the job active |\n\n## Diagnosing Transient vs Chronic\n\n### Transient (self-heals, no action needed)\n- Error message mentions `TimeoutError`, `timeout`, `connection reset`, `5xx status`\n- Internet connectivity is fine (`ping -c1 google.com` works)\n- The job has a next_run_at in the near future (self-retry)\n- The same error has not recurred across multiple sensor ticks\n\n### Chronic (needs structural fix)\n- Script not found, permission denied, import error, config error\n- The same error persists across 3+ consecutive sensor ticks\n- The error message points to a missing file, wrong path, or stale config\n- The job's schedule is missed (next_run_at is in the past and last_run_at is days old)\n\n### Fix Patterns\n\nFor transient timeouts: no action needed — the job will retry on its next schedule.\nFor chronic errors: apply the fix from `auto-remediation` skill's known-fix table,\nthen verify by re-running the failing script or checking the service directly.\n\n## Bus Health Verification\n\nThe Agent Bus listens on port **8903** (not 8905):\n\n```bash\ncurl -s http:\u002F\u002Flocalhost:8903\u002Fhealth\n# → {\"status\":\"ok\",\"backend\":\"pgmq\",\"queues\":N,...}\n```\n\nRequires `FLEET_BUS_TOKEN` from `~\u002Fsteadfaste-fleet\u002F.env` for direct API calls.\nThe bus-audit-watchdog (no_agent cron, every 1m) is the primary health indicator.\n","# Remediation Investigation\n\n## When to Use\n\nLoad this skill when:\n- The `agent-remediation-sensor` reports a cron_error or service issue\n- You need to distinguish a transient timeout from a structural failure\n- The auto-remediation skill's known-fix table doesn't cover the reported error\n- You need to trace a sensor report back to the actual cron output or jobs.json state\n\n## Sensor Output Architecture\n\nThe `agent-remediation-sensor` (no_agent cron, every 5m) writes its findings as JSON\nto the **cron output directory**, NOT to a predictable path. Finding it requires scanning.\n\n### Finding the Latest Sensor Output\n\nThe sensor's job ID is not predictable. Scan for it:\n\n```bash\nfind ~\u002F.hermes\u002Fcron\u002Foutput\u002F -name \"*.md\" -mmin -10 | xargs grep -l \"remediation-sensor\\|cron_error\\|agent-remediation\" 2>\u002Fdev\u002Fnull | head -3\n```\n\nEach match is a full .md file containing a JSON array. Read the contents directly.\n\n### Sensor JSON Schema\n\n```json\n[\n  {\n    \"type\": \"cron_error\",\n    \"severity\": \"high\",\n    \"detail\": \"Errored cron: orch-skill-lifecycle\",\n    \"context\": {\n      \"job_id\": null,\n      \"name\": \"orch-skill-lifecycle\",\n      \"last_status\": \"error\"\n    },\n    \"timestamp\": \"2026-07-26T18:00:30.170571+00:00\"\n  }\n]\n```\n\n| Field | Type | Notes |\n|-------|------|-------|\n| `type` | string | `cron_error`, `disk_pressure`, `service_down`, etc. |\n| `severity` | string | `low`\u002F`medium`\u002F`high`\u002F`critical` |\n| `detail` | string | Human-readable description |\n| `context.name` | string | Cron job name (most useful field) |\n| `context.last_status` | string | `error` or `ok` |\n| `timestamp` | string | ISO timestamp of when sensor ran |\n\n## Cross-Referencing Sensor vs Live State\n\nThe sensor reads `last_status` from `~\u002F.hermes\u002Fcron\u002Fjobs.json`, which means:\n\n- **The sensor output can be up to 5 minutes stale** — the sensor runs every 5m\n- **`last_status=\"error\"` persists** until the job runs again successfully. An error from 12 hours ago still shows as \"error\" in the sensor report\n- **Always cross-reference `last_run_at` timestamp** to determine recency\n\n### Read jobs.json Directly\n\nThe `cronjob(action='list')` MCP tool does not exist. Use the raw jobs.json file:\n\n```python\nimport json, os\nwith open(os.path.expanduser('~\u002F.hermes\u002Fcron\u002Fjobs.json')) as f:\n    data = json.load(f)\nerrored = [j for j in data['jobs'] if j.get('last_status') == 'error']\n```\n\nKey fields in each job dict:\n\n| Field | Type | What it tells you |\n|-------|------|-------------------|\n| `name` | str | Cron job name |\n| `last_status` | str | `\"ok\"` or `\"error\"` |\n| `last_error` | str or null | The error message from the last run |\n| `last_run_at` | str (ISO) | When the job last ran |\n| `next_run_at` | str (ISO) | When it will next run |\n| `state` | str | `\"scheduled\"`, `\"paused\"`, etc. |\n| `enabled` | bool | Is the job active |\n\n## Diagnosing Transient vs Chronic\n\n### Transient (self-heals, no action needed)\n- Error message mentions `TimeoutError`, `timeout`, `connection reset`, `5xx status`\n- Internet connectivity is fine (`ping -c1 google.com` works)\n- The job has a next_run_at in the near future (self-retry)\n- The same error has not recurred across multiple sensor ticks\n\n### Chronic (needs structural fix)\n- Script not found, permission denied, import error, config error\n- The same error persists across 3+ consecutive sensor ticks\n- The error message points to a missing file, wrong path, or stale config\n- The job's schedule is missed (next_run_at is in the past and last_run_at is days old)\n\n### Fix Patterns\n\nFor transient timeouts: no action needed — the job will retry on its next schedule.\nFor chronic errors: apply the fix from `auto-remediation` skill's known-fix table,\nthen verify by re-running the failing script or checking the service directly.\n\n## Bus Health Verification\n\nThe Agent Bus listens on port **8903** (not 8905):\n\n```bash\ncurl -s http:\u002F\u002Flocalhost:8903\u002Fhealth\n# → {\"status\":\"ok\",\"backend\":\"pgmq\",\"queues\":N,...}\n```\n\nRequires `FLEET_BUS_TOKEN` from `~\u002Fsteadfaste-fleet\u002F.env` for direct API calls.\nThe bus-audit-watchdog (no_agent cron, every 1m) is the primary health indicator.\n",{"name":5,"version":24,"description":7},"1.0.0","main","9dc0e92c5fa81d4db5292b205716e8ea0c00d10e","skills\u002Fdevops\u002Fremediation-investigation",1,"https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet","steadfaste.com","https:\u002F\u002Fgithub.com\u002Flukemcqueen","AI Architect | Building Hermes Cortex: governed multi-agent AI for autonomous software engineering | Enterprise Tech Consultant","2026-11-14 22:33:34",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add lukemcqueen\u002Fsteadfaste-fleet --skill remediation-investigation",{"tool":40,"command":41},"bunx","bunx skills add lukemcqueen\u002Fsteadfaste-fleet --skill remediation-investigation",{"tool":43,"command":44},"pnpm","pnpm dlx skills add lukemcqueen\u002Fsteadfaste-fleet --skill remediation-investigation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Fremediation-investigation\u002FSKILL.md",true,[48],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Forch-skill-lifecycle-timeout-example.md","REFERENCE","参考文档",2281,"https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Fremediation-investigation\u002Freferences\u002Forch-skill-lifecycle-timeout-example.md",[55,63,70,77,84,91],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":62},"01M7DXY4G8NSVB59K8B6S2AQNP","macbook-linux-maintenance","Legacy MacBook Linux fixes: GPU wedge, reboot hang, thermal.","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Fmacbook-linux-maintenance\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":62},"01M7DXXYJCXFJ3TGB84ZQ8KFE6","governance-regression-triage","Triage a host's governance issues: what changed.","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Fgovernance-regression-triage\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":62},"01M7DXXSAP1G8FDRJAMXQGBBMK","enforcement-immutability","Use when enforcement files lose their immutable flag.","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Fenforcement-immutability\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":62},"01M78SSDQVRYX64Y16X32TC0NS","steadfaste-fleet-repo-deploy","Use when committing to the steadfaste-fleet repo.","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Fsteadfaste-fleet-repo-deploy\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"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":62},"01M78SS928F3R2RJAYVW4E30CE","steadfaste-fleet-maintenance","Maintain an installed Steadfaste Fleet instance — update both the upstream Hermes Agent and the fleet repo layer, merge diverged histories, sync skills safely, and troubleshoot common issues. Covers the dual-update workflow (hermes update + fleet-update.sh), encrypted brain data backup, mycortex import, and recovery techniques.","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Fsteadfaste-fleet-maintenance\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":62},"01M78SP1CHW0T0BWE5ZT6JBPX8","fleet-preflight","DEPRECATED alias — merged into survey-before-action (2026-08-20). Load survey-before-action instead; its \"Repo-Specific Pre-Flight\" section covers git search, Hermes boundary, and deployment verification.","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Ffleet-preflight\u002FSKILL.md",[],[]]