[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6JV2GTJVYHTQS942WAZH3MH":3,"skill-same:01M6JV2GTJVYHTQS942WAZH3MH":58},{"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":28,"linkOnly":29,"markdownContent":30,"markdownBody":31,"frontMatter":32,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":39,"ownerHtmlUrl":40,"ownerBlogUrl":41,"ownerDescription":42,"updatedAt":43,"install":44,"resources":57},"01M6JV2GTJVYHTQS942WAZH3MH","goal-convergence",null,"Goal-oriented autonomous loop with external completion oracle. Keeps iterating until verifiable stopping conditions are met, checked by a separate model.","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\u002Fgoal-convergence\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27],"goal","convergence","goal convergence","oracle","loop","model","autonomous","with","autonomous loop","2026-11-10 10:12:30",false,"---\nname: goal-convergence\ndescription: \"Goal-oriented autonomous loop with external completion oracle. Keeps iterating until verifiable stopping conditions are met, checked by a separate model.\"\norigin: ECC\n---\n\n# Goal Convergence\n\nGoal-oriented autonomous loop with external completion oracle.\nBased on Addy Osmani's Loop Engineering principle: \"Keep going until a verifiable\nstopping condition holds, with a separate small model checking completion.\"\n\n## When to Activate\n\n- User invokes `\u002Fgoal` command\n- Heartbeat auto-creates a goal from scan failures\n- Triage item is promoted to a goal via `\u002Ftriage act \u003Cid> goal`\n- Session resumes with an active goal state file\n\n## Core Concept: Maker-Oracle Separation\n\nThe model that wrote the code is too nice grading its own homework.\nA second model (the oracle) with different instructions and READ-ONLY tools\ncatches what the first talked itself into.\n\n```\nMaker (primary model, full tools)\n  │\n  ▼ produces iteration output\n  │\nOracle (different model, read-only)\n  │\n  ├─ ALL conditions pass → CONVERGE (goal done)\n  ├─ Some fail + budget remains → nextHint → LOOP (maker iterates)\n  └─ Budget exhausted → ESCALATE (triage inbox)\n```\n\n## Goal Lifecycle\n\n```\nCREATE → ACTIVE → [iterate] → CONVERGED\n                       │\n                       ├──── PAUSED (manual \u002Fgoal pause)\n                       └──── ESCALATED (budget exhausted or repeated failure)\n```\n\nStates:\n- `active`: Maker-oracle loop is running\n- `paused`: Manually paused, resumes with `\u002Fgoal resume`\n- `converged`: All stopping conditions met, goal complete\n- `escalated`: Cannot converge within budget, needs human triage\n- `failed`: Explicitly abandoned\n\n## Stopping Conditions\n\nEach goal has one or more stopping conditions. ALL must pass for convergence.\n\n| Type | Command Pattern | Example |\n|------|----------------|---------|\n| `test_pass` | Test runner exits 0 | `npm test` |\n| `lint_clean` | Linter exits 0 | `npm run lint -- --quiet` |\n| `coverage_threshold` | Coverage >= N% | `npm test -- --coverage` |\n| `build_pass` | Build succeeds | `npm run build` |\n| `custom_command` | Any command exits 0 | `grep -r \"TODO\" src\u002F \\| wc -l` |\n\n## Oracle Protocol\n\nThe oracle receives:\n1. The goal objective (natural language)\n2. All stopping condition commands and their latest output\n3. The maker's iteration summary\n4. Previous iteration history (last 3)\n\nThe oracle returns:\n```json\n{\n  \"converged\": false,\n  \"conditionResults\": [\n    {\"type\": \"test_pass\", \"passed\": false, \"output\": \"2 tests failing\"},\n    {\"type\": \"lint_clean\", \"passed\": true, \"output\": \"\"}\n  ],\n  \"reasons\": [\"2 tests still failing in auth module\"],\n  \"nextHint\": \"Focus on src\u002Fauth\u002Frefresh.test.ts — the token expiry mock is stale\",\n  \"confidence\": 0.85\n}\n```\n\n## Budget Management\n\nThree budget dimensions, any exhaustion triggers escalation:\n\n| Dimension | Default | Rationale |\n|-----------|---------|-----------|\n| Iterations | 15 | Prevents infinite loops |\n| Wall time | 2h | Bounds real-world duration |\n| Cost (USD) | $10 | Prevents runaway API spend |\n\nOn escalation, the goal:\n1. Persists full state to `~\u002F.claude\u002Fgoals\u002F{goalId}.json`\n2. Creates a triage inbox item with context\n3. Marks state as `escalated`\n4. Reports final status to user\n\n## Inter-Session Persistence\n\nGoals survive session restarts:\n1. `SessionEnd` hook serializes active goals\n2. `SessionStart` hook detects active goals and notifies user\n3. `\u002Fgoal resume` re-enters the loop with oracle's last `nextHint`\n\nState file: `~\u002F.claude\u002Fgoals\u002F{goalId}.json` (follows `schemas\u002Fgoal.schema.json`)\n\n## Integration Points\n\n- **`\u002Fheartbeat`**: Auto-creates goals from scan failures\n- **`\u002Ftriage`**: Escalated goals land in triage; triage items can become goals\n- **`\u002Fcheckpoint`**: Each iteration implicitly checkpoints\n- **`\u002Fverify`**: Oracle internally uses verification patterns\n- **`wave-execution`**: Multiple goals can run in parallel waves\n- **`rework-loop`**: Failed iterations trigger blame-attributed rework\n\n## Hard Bans\n\n- Oracle MUST be a different model than maker (eliminates self-grading bias)\n- Oracle MUST NOT have write tools (prevents it from \"helping\" fix issues)\n- Goals MUST have at least one stopping condition (no open-ended loops)\n- Budget MUST have at least one limit set (no unbounded execution)\n- State MUST persist to disk (no goals lost on crash)\n\n## Example\n\n```\nUser: \u002Fgoal \"make all tests pass\"\n\nSystem infers:\n  objective: \"make all tests pass\"\n  stoppingConditions: [{type: \"test_pass\", command: \"npm test\"}]\n  budget: {maxIterations: 15, maxDuration: \"2h\", maxDollars: 10}\n  oracle: {model: \"haiku\"}\n\nIteration 1:\n  Maker: reads test output, fixes obvious import error in auth.ts\n  Oracle: runs `npm test` → 1 test still failing → {converged: false, nextHint: \"...\"}\n\nIteration 2:\n  Maker: fixes token refresh logic based on oracle hint\n  Oracle: runs `npm test` → all pass → {converged: true}\n\nResult: CONVERGED in 2 iterations, $0.45 spent\n```\n","# Goal Convergence\n\nGoal-oriented autonomous loop with external completion oracle.\nBased on Addy Osmani's Loop Engineering principle: \"Keep going until a verifiable\nstopping condition holds, with a separate small model checking completion.\"\n\n## When to Activate\n\n- User invokes `\u002Fgoal` command\n- Heartbeat auto-creates a goal from scan failures\n- Triage item is promoted to a goal via `\u002Ftriage act \u003Cid> goal`\n- Session resumes with an active goal state file\n\n## Core Concept: Maker-Oracle Separation\n\nThe model that wrote the code is too nice grading its own homework.\nA second model (the oracle) with different instructions and READ-ONLY tools\ncatches what the first talked itself into.\n\n```\nMaker (primary model, full tools)\n  │\n  ▼ produces iteration output\n  │\nOracle (different model, read-only)\n  │\n  ├─ ALL conditions pass → CONVERGE (goal done)\n  ├─ Some fail + budget remains → nextHint → LOOP (maker iterates)\n  └─ Budget exhausted → ESCALATE (triage inbox)\n```\n\n## Goal Lifecycle\n\n```\nCREATE → ACTIVE → [iterate] → CONVERGED\n                       │\n                       ├──── PAUSED (manual \u002Fgoal pause)\n                       └──── ESCALATED (budget exhausted or repeated failure)\n```\n\nStates:\n- `active`: Maker-oracle loop is running\n- `paused`: Manually paused, resumes with `\u002Fgoal resume`\n- `converged`: All stopping conditions met, goal complete\n- `escalated`: Cannot converge within budget, needs human triage\n- `failed`: Explicitly abandoned\n\n## Stopping Conditions\n\nEach goal has one or more stopping conditions. ALL must pass for convergence.\n\n| Type | Command Pattern | Example |\n|------|----------------|---------|\n| `test_pass` | Test runner exits 0 | `npm test` |\n| `lint_clean` | Linter exits 0 | `npm run lint -- --quiet` |\n| `coverage_threshold` | Coverage >= N% | `npm test -- --coverage` |\n| `build_pass` | Build succeeds | `npm run build` |\n| `custom_command` | Any command exits 0 | `grep -r \"TODO\" src\u002F \\| wc -l` |\n\n## Oracle Protocol\n\nThe oracle receives:\n1. The goal objective (natural language)\n2. All stopping condition commands and their latest output\n3. The maker's iteration summary\n4. Previous iteration history (last 3)\n\nThe oracle returns:\n```json\n{\n  \"converged\": false,\n  \"conditionResults\": [\n    {\"type\": \"test_pass\", \"passed\": false, \"output\": \"2 tests failing\"},\n    {\"type\": \"lint_clean\", \"passed\": true, \"output\": \"\"}\n  ],\n  \"reasons\": [\"2 tests still failing in auth module\"],\n  \"nextHint\": \"Focus on src\u002Fauth\u002Frefresh.test.ts — the token expiry mock is stale\",\n  \"confidence\": 0.85\n}\n```\n\n## Budget Management\n\nThree budget dimensions, any exhaustion triggers escalation:\n\n| Dimension | Default | Rationale |\n|-----------|---------|-----------|\n| Iterations | 15 | Prevents infinite loops |\n| Wall time | 2h | Bounds real-world duration |\n| Cost (USD) | $10 | Prevents runaway API spend |\n\nOn escalation, the goal:\n1. Persists full state to `~\u002F.claude\u002Fgoals\u002F{goalId}.json`\n2. Creates a triage inbox item with context\n3. Marks state as `escalated`\n4. Reports final status to user\n\n## Inter-Session Persistence\n\nGoals survive session restarts:\n1. `SessionEnd` hook serializes active goals\n2. `SessionStart` hook detects active goals and notifies user\n3. `\u002Fgoal resume` re-enters the loop with oracle's last `nextHint`\n\nState file: `~\u002F.claude\u002Fgoals\u002F{goalId}.json` (follows `schemas\u002Fgoal.schema.json`)\n\n## Integration Points\n\n- **`\u002Fheartbeat`**: Auto-creates goals from scan failures\n- **`\u002Ftriage`**: Escalated goals land in triage; triage items can become goals\n- **`\u002Fcheckpoint`**: Each iteration implicitly checkpoints\n- **`\u002Fverify`**: Oracle internally uses verification patterns\n- **`wave-execution`**: Multiple goals can run in parallel waves\n- **`rework-loop`**: Failed iterations trigger blame-attributed rework\n\n## Hard Bans\n\n- Oracle MUST be a different model than maker (eliminates self-grading bias)\n- Oracle MUST NOT have write tools (prevents it from \"helping\" fix issues)\n- Goals MUST have at least one stopping condition (no open-ended loops)\n- Budget MUST have at least one limit set (no unbounded execution)\n- State MUST persist to disk (no goals lost on crash)\n\n## Example\n\n```\nUser: \u002Fgoal \"make all tests pass\"\n\nSystem infers:\n  objective: \"make all tests pass\"\n  stoppingConditions: [{type: \"test_pass\", command: \"npm test\"}]\n  budget: {maxIterations: 15, maxDuration: \"2h\", maxDollars: 10}\n  oracle: {model: \"haiku\"}\n\nIteration 1:\n  Maker: reads test output, fixes obvious import error in auth.ts\n  Oracle: runs `npm test` → 1 test still failing → {converged: false, nextHint: \"...\"}\n\nIteration 2:\n  Maker: fixes token refresh logic based on oracle hint\n  Oracle: runs `npm test` → all pass → {converged: true}\n\nResult: CONVERGED in 2 iterations, $0.45 spent\n```\n",{"name":5,"origin":33,"description":7},"ECC","main","b0f0a87593c578a7898eccaf1b363f7f87c1f99b","plugins\u002FColin4k1024\u002Ftsp\u002Fskills\u002Fgoal-convergence",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":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill goal-convergence",{"tool":50,"command":51},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill goal-convergence",{"tool":53,"command":54},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill goal-convergence","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FColin4k1024\u002Ftsp\u002Fskills\u002Fgoal-convergence\u002FSKILL.md",true,[],[59,69,77,85,93,101],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":64,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":68},"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":73,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":68},"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":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":81,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":68},"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":89,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":68},"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":97,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":68},"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":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":105,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":68},"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",[],[]]