[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6M8YXH3867VB0AAZSR6HCEN":3,"skill-same:01M6M8YXH3867VB0AAZSR6HCEN":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":29,"linkOnly":30,"markdownContent":31,"markdownBody":32,"frontMatter":33,"refName":35,"commitSha":36,"skillDirectory":37,"forksCount":38,"repositoryHtmlUrl":39,"repositoryHomepageUrl":40,"ownerHtmlUrl":41,"ownerBlogUrl":42,"ownerDescription":43,"updatedAt":44,"install":45,"resources":58},"01M6M8YXH3867VB0AAZSR6HCEN","loop-heartbeat",null,"Scheduled discovery automation that runs scans on a heartbeat interval, classifies findings, and routes them to goals or triage inbox.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FColin4k1024\u002Ftsp\u002Fskills\u002Floop-heartbeat\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28],"loop","heartbeat","loop heartbeat","triage","automation","inbox","discovery","triage inbox","goals","scheduled","2026-11-10 10:12:30",false,"---\nname: loop-heartbeat\ndescription: \"Scheduled discovery automation that runs scans on a heartbeat interval, classifies findings, and routes them to goals or triage inbox.\"\norigin: ECC\n---\n\n# Loop Heartbeat\n\nScheduled discovery automation that runs scans, finds issues, and routes findings\nto goals or triage. The heartbeat is what makes a loop a loop — not a one-shot run.\n\nBased on Addy Osmani's Loop Engineering: \"Automations are the thing that makes\na loop an actual loop. Run prompts on a schedule. Findings go to a triage inbox;\nempty runs archive themselves.\"\n\n## When to Activate\n\n- User invokes `\u002Fheartbeat start` to begin scheduled scans\n- User invokes `\u002Fheartbeat run` for a one-shot scan\n- A goal converges and follow-up scanning is needed\n- Project onboarding includes quality monitoring setup\n\n## Core Concept\n\nThe heartbeat is the \"discovery layer\" of a loop. It answers: \"What's broken right\nnow?\" on a recurring basis without human prompting.\n\n```\nEvery 30 minutes:\n  ┌─ Run test suite ─── PASS → skip\n  ├─ Run linter ─────── FAIL → create goal (auto-fix)\n  ├─ Audit deps ─────── FAIL → triage inbox (human decision)\n  └─ Type check ─────── PASS → skip\n```\n\n## Configuration\n\nCreate `.claude\u002Fheartbeat.yaml` in the project root:\n\n```yaml\nheartbeat:\n  interval: \"30m\"\n  scans:\n    - name: \"test-health\"\n      command: \"npm test 2>&1 | tail -10\"\n      onFailure: \"auto-goal\"\n      description: \"Test suite health\"\n    - name: \"lint-drift\"\n      command: \"npm run lint -- --quiet 2>&1 | wc -l\"\n      threshold: 0\n      onFailure: \"triage\"\n      description: \"Lint error count\"\n    - name: \"type-check\"\n      command: \"npx tsc --noEmit 2>&1; echo EXIT:$?\"\n      onFailure: \"auto-goal\"\n      description: \"TypeScript type errors\"\n  budget:\n    maxDollarsPerHour: 2.0\n    pauseOnExhaust: true\n```\n\n## Scan Result Classification\n\n| onFailure | Behavior | Use When |\n|-----------|----------|----------|\n| `auto-goal` | Creates `\u002Fgoal` automatically | Machine can fix it (tests, lint, types) |\n| `triage` | Adds to `\u002Ftriage` inbox | Human judgment needed (deps, security) |\n| `notify` | Desktop notification only | Informational, no action required |\n| `ignore` | Log silently | Monitoring only, aggregate later |\n\n## Budget Controls\n\n- `maxDollarsPerHour`: Pause heartbeat if scanning costs exceed this\n- `pauseOnExhaust`: If true, pause (resumable); if false, stop entirely\n- Goal creation inherits the default goal budget from `\u002Fgoal` settings\n\n## Empty Run Handling\n\nWhen all scans pass:\n- No goals or triage items are created\n- Run is logged to `~\u002F.claude\u002Fheartbeat-last-run.json`\n- Next run proceeds on schedule\n- This is the \"archive themselves silently\" behavior\n\n## Integration Points\n\n- **`\u002Fgoal`**: `auto-goal` failures create goals via completion-oracle.js\n- **`\u002Ftriage`**: `triage` failures append to `~\u002F.claude\u002Ftriage\u002Finbox.jsonl`\n- **CronCreate**: Scheduling uses the Claude Code CronCreate primitive\n- **ScheduleWakeup**: Alternative for dynamic-interval loops\n- **Hooks**: Runs as a scheduled task, not a synchronous hook\n\n## Hard Bans\n\n- Heartbeat MUST NOT modify code (it's discovery-only)\n- Heartbeat MUST NOT create goals without a stopping condition\n- Budget limits MUST be enforced (no unbounded scan spending)\n- Failed scans MUST be classified (no silent failures)\n- Empty runs MUST NOT create noise (pass = skip)\n\n## Example Session\n\n```\nUser: \u002Fheartbeat start\n\nSystem:\n  Loaded .claude\u002Fheartbeat.yaml (3 scans configured)\n  Registered CronCreate: every 30m\n  Next run: 30m from now\n  Budget: $2.00\u002Fhour\n\n[30 minutes later, heartbeat fires]\n\nScan results:\n  ✓ test-health: all tests pass\n  ✗ lint-drift: 4 lint errors found → created goal-a1b2c3d4\n  ✓ type-check: no type errors\n\nSummary: 2\u002F3 scans passed, 1 goal created\n```\n","# Loop Heartbeat\n\nScheduled discovery automation that runs scans, finds issues, and routes findings\nto goals or triage. The heartbeat is what makes a loop a loop — not a one-shot run.\n\nBased on Addy Osmani's Loop Engineering: \"Automations are the thing that makes\na loop an actual loop. Run prompts on a schedule. Findings go to a triage inbox;\nempty runs archive themselves.\"\n\n## When to Activate\n\n- User invokes `\u002Fheartbeat start` to begin scheduled scans\n- User invokes `\u002Fheartbeat run` for a one-shot scan\n- A goal converges and follow-up scanning is needed\n- Project onboarding includes quality monitoring setup\n\n## Core Concept\n\nThe heartbeat is the \"discovery layer\" of a loop. It answers: \"What's broken right\nnow?\" on a recurring basis without human prompting.\n\n```\nEvery 30 minutes:\n  ┌─ Run test suite ─── PASS → skip\n  ├─ Run linter ─────── FAIL → create goal (auto-fix)\n  ├─ Audit deps ─────── FAIL → triage inbox (human decision)\n  └─ Type check ─────── PASS → skip\n```\n\n## Configuration\n\nCreate `.claude\u002Fheartbeat.yaml` in the project root:\n\n```yaml\nheartbeat:\n  interval: \"30m\"\n  scans:\n    - name: \"test-health\"\n      command: \"npm test 2>&1 | tail -10\"\n      onFailure: \"auto-goal\"\n      description: \"Test suite health\"\n    - name: \"lint-drift\"\n      command: \"npm run lint -- --quiet 2>&1 | wc -l\"\n      threshold: 0\n      onFailure: \"triage\"\n      description: \"Lint error count\"\n    - name: \"type-check\"\n      command: \"npx tsc --noEmit 2>&1; echo EXIT:$?\"\n      onFailure: \"auto-goal\"\n      description: \"TypeScript type errors\"\n  budget:\n    maxDollarsPerHour: 2.0\n    pauseOnExhaust: true\n```\n\n## Scan Result Classification\n\n| onFailure | Behavior | Use When |\n|-----------|----------|----------|\n| `auto-goal` | Creates `\u002Fgoal` automatically | Machine can fix it (tests, lint, types) |\n| `triage` | Adds to `\u002Ftriage` inbox | Human judgment needed (deps, security) |\n| `notify` | Desktop notification only | Informational, no action required |\n| `ignore` | Log silently | Monitoring only, aggregate later |\n\n## Budget Controls\n\n- `maxDollarsPerHour`: Pause heartbeat if scanning costs exceed this\n- `pauseOnExhaust`: If true, pause (resumable); if false, stop entirely\n- Goal creation inherits the default goal budget from `\u002Fgoal` settings\n\n## Empty Run Handling\n\nWhen all scans pass:\n- No goals or triage items are created\n- Run is logged to `~\u002F.claude\u002Fheartbeat-last-run.json`\n- Next run proceeds on schedule\n- This is the \"archive themselves silently\" behavior\n\n## Integration Points\n\n- **`\u002Fgoal`**: `auto-goal` failures create goals via completion-oracle.js\n- **`\u002Ftriage`**: `triage` failures append to `~\u002F.claude\u002Ftriage\u002Finbox.jsonl`\n- **CronCreate**: Scheduling uses the Claude Code CronCreate primitive\n- **ScheduleWakeup**: Alternative for dynamic-interval loops\n- **Hooks**: Runs as a scheduled task, not a synchronous hook\n\n## Hard Bans\n\n- Heartbeat MUST NOT modify code (it's discovery-only)\n- Heartbeat MUST NOT create goals without a stopping condition\n- Budget limits MUST be enforced (no unbounded scan spending)\n- Failed scans MUST be classified (no silent failures)\n- Empty runs MUST NOT create noise (pass = skip)\n\n## Example Session\n\n```\nUser: \u002Fheartbeat start\n\nSystem:\n  Loaded .claude\u002Fheartbeat.yaml (3 scans configured)\n  Registered CronCreate: every 30m\n  Next run: 30m from now\n  Budget: $2.00\u002Fhour\n\n[30 minutes later, heartbeat fires]\n\nScan results:\n  ✓ test-health: all tests pass\n  ✗ lint-drift: 4 lint errors found → created goal-a1b2c3d4\n  ✓ type-check: no type errors\n\nSummary: 2\u002F3 scans passed, 1 goal created\n```\n",{"name":5,"origin":34,"description":7},"ECC","main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002FColin4k1024\u002Ftsp\u002Fskills\u002Floop-heartbeat",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill loop-heartbeat",{"tool":51,"command":52},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill loop-heartbeat",{"tool":54,"command":55},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill loop-heartbeat","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FColin4k1024\u002Ftsp\u002Fskills\u002Floop-heartbeat\u002FSKILL.md",true,[],[60,70,78,86,94,102],{"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":64,"licenseFileUrl":65,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":69},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"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":64,"licenseFileUrl":74,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":69},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\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":64,"licenseFileUrl":82,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":69},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":90,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":69},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":98,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":69},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":106,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":69},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]