[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MFXP8NSVECJG6NHW0CF176":3,"skill-same:01M6MFXP8NSVECJG6NHW0CF176":64},{"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":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":45,"ownerHtmlUrl":46,"ownerBlogUrl":47,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M6MFXP8NSVECJG6NHW0CF176","usage-kernel",null,"Use the six Codex Usage Tracker tools for exact local usage facts, bounded exploration, allowance observations, and evidence timelines.","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\u002Fdouglasmonsky\u002Fcodex-usage-tracker\u002Fskills\u002Fusage-kernel\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34],"kernel","usage","usage kernel","codex","Tools","codex usage","use","evidence","tracker","exploration","local","observations","allowance","facts","for","bounded","2026-11-10 10:12:30",false,"---\nname: usage-kernel\ndescription: Use the six Codex Usage Tracker tools for exact local usage facts, bounded exploration, allowance observations, and evidence timelines.\n---\n\n# Codex Usage Tracker\n\nUse the tracker as a factual local data plane. The tools return exact or\nexplicitly graded facts; the model owns inference, explanation, and\nrecommendations.\n\nUse the three-step loop **scope → batch → evidence**:\n\n1. **Scope.** Start with the needed `usage_query` whenever the question maps\n   to a curated template or a known typed request. The result carries its\n   generation, grade, history coverage, and cache state. Call `usage_status`\n   only when the query reports an absent or insufficiently fresh index, or\n   when the user explicitly asks about operational state. A committed\n   generation remains queryable while refresh is active or recommended. When\n   the needed fields are unfamiliar, set `include_guidance=true` on the same\n   `usage_query` call that carries the first batch; use an empty batch only for\n   standalone capability discovery.\n2. **Batch.** Prefer one batched `usage_query` call. Its arguments always wrap\n   one or more query requests in the `requests` array. Execute a curated\n   server-side template with\n   `{\"requests\":[{\"template\":\"\u003Cname>\"}]}`; for the common thread leaderboard\n   use `{\"requests\":[{\"template\":\"top_threads\"}]}`. Templates query the\n   hydrated snapshot and report its coverage; refresh complete history only\n   when the user asks. For same five ranked threads, use result 1 for\n   labels, selectors, totals, shares, and token classes; use result 2 only for\n   cost\u002Fcredits. Do not query again unless user asks for evidence. Use\n   `{\"requests\":[{\"template\":\"weekly_drivers\"}]}` for the latest indexed\n   seven-day thread leaderboard,\n   `{\"requests\":[{\"template\":\"week_over_week\"}]}` for that window versus the\n   immediately preceding seven days, and\n   `{\"requests\":[{\"template\":\"latest_incremental_change\"}]}` for the active\n   generation's inserted calls and leading affected thread. These templates\n   derive their anchors from the committed snapshot; do not discover dates or\n   generation numbers first. Use\n   `{\"requests\":[{\"template\":\"model_effort\"}]}` for model\u002Feffort mix and\n   `{\"requests\":[{\"template\":\"tools\"}]}` for structural tool facts. Do not repeat a\n   successful curated template or request guidance after it returns rows.\n   Supply `parameters` only when the selected template requires them.\n   Otherwise send only the typed dataset, operation, dimensions, measures,\n   filters, and limits needed for the question. Do not copy or reconstruct a\n   returned template body.\n   Preserve the returned generation, grade, coverage, counts, and explicit\n   row\u002Fbyte limits. Compose filters as\n   `{field, operator, value}` using only the dataset fields and operators in\n   `filter_grammar`; `in` takes an array of 1–25 values. Phase queries require\n   one returned scope-filter template for a thread, turn, or time window.\n3. **Evidence.** Rank candidates from the facts first. Call `usage_evidence`\n   only after ranking, and only with an exact returned logical selector. Use\n   `live=true` for the same timeline in live mode.\n\nLabel every claim:\n\n- **fact** — returned exact\u002Fdeterministic data; for `partial`, state the\n  hydration preset\u002Fcutoff and never generalize to all history;\n- **estimate** — returned estimated data with coverage and provenance;\n- **hypothesis** — model inference that still needs evidence;\n- **unsupported** — unavailable from the returned scope and not asserted.\n\nThe optional `context` dataset is aggregate-only private local evidence. Its\n`observed_bytes` and `events` measures are exact for the structurally observed\npayload strings that were indexed. `estimated_tokens` is available only when\nan explicit tokenizer populated it; always preserve its estimator identity and\ncoverage. Never describe category bytes or estimates as exact billed input\ntokens, and keep `unattributed_input_tokens` unsupported when the response\nreports it as `null`. If context composition is disabled, continue with the\nbase accounting datasets instead of starting hidden work.\n\nCall `usage_refresh` only when freshness matters. Reuse the returned job; never\nstart a duplicate. Use `usage_job_status` with a bounded `wait_seconds` value\nso the host waits; do not short-interval poll from the model. Use\n`usage_allowance` for observed allowance facts and preserve its provenance and\nlimitations. Do not infer waste or productivity from token totals alone.\n\nNever inspect raw logs as a fallback, invent missing selectors, claim narrative\nfindings the tools did not return, or expose prompts, reasoning, tool\narguments\u002Foutput, secrets, or local paths.\n","# Codex Usage Tracker\n\nUse the tracker as a factual local data plane. The tools return exact or\nexplicitly graded facts; the model owns inference, explanation, and\nrecommendations.\n\nUse the three-step loop **scope → batch → evidence**:\n\n1. **Scope.** Start with the needed `usage_query` whenever the question maps\n   to a curated template or a known typed request. The result carries its\n   generation, grade, history coverage, and cache state. Call `usage_status`\n   only when the query reports an absent or insufficiently fresh index, or\n   when the user explicitly asks about operational state. A committed\n   generation remains queryable while refresh is active or recommended. When\n   the needed fields are unfamiliar, set `include_guidance=true` on the same\n   `usage_query` call that carries the first batch; use an empty batch only for\n   standalone capability discovery.\n2. **Batch.** Prefer one batched `usage_query` call. Its arguments always wrap\n   one or more query requests in the `requests` array. Execute a curated\n   server-side template with\n   `{\"requests\":[{\"template\":\"\u003Cname>\"}]}`; for the common thread leaderboard\n   use `{\"requests\":[{\"template\":\"top_threads\"}]}`. Templates query the\n   hydrated snapshot and report its coverage; refresh complete history only\n   when the user asks. For same five ranked threads, use result 1 for\n   labels, selectors, totals, shares, and token classes; use result 2 only for\n   cost\u002Fcredits. Do not query again unless user asks for evidence. Use\n   `{\"requests\":[{\"template\":\"weekly_drivers\"}]}` for the latest indexed\n   seven-day thread leaderboard,\n   `{\"requests\":[{\"template\":\"week_over_week\"}]}` for that window versus the\n   immediately preceding seven days, and\n   `{\"requests\":[{\"template\":\"latest_incremental_change\"}]}` for the active\n   generation's inserted calls and leading affected thread. These templates\n   derive their anchors from the committed snapshot; do not discover dates or\n   generation numbers first. Use\n   `{\"requests\":[{\"template\":\"model_effort\"}]}` for model\u002Feffort mix and\n   `{\"requests\":[{\"template\":\"tools\"}]}` for structural tool facts. Do not repeat a\n   successful curated template or request guidance after it returns rows.\n   Supply `parameters` only when the selected template requires them.\n   Otherwise send only the typed dataset, operation, dimensions, measures,\n   filters, and limits needed for the question. Do not copy or reconstruct a\n   returned template body.\n   Preserve the returned generation, grade, coverage, counts, and explicit\n   row\u002Fbyte limits. Compose filters as\n   `{field, operator, value}` using only the dataset fields and operators in\n   `filter_grammar`; `in` takes an array of 1–25 values. Phase queries require\n   one returned scope-filter template for a thread, turn, or time window.\n3. **Evidence.** Rank candidates from the facts first. Call `usage_evidence`\n   only after ranking, and only with an exact returned logical selector. Use\n   `live=true` for the same timeline in live mode.\n\nLabel every claim:\n\n- **fact** — returned exact\u002Fdeterministic data; for `partial`, state the\n  hydration preset\u002Fcutoff and never generalize to all history;\n- **estimate** — returned estimated data with coverage and provenance;\n- **hypothesis** — model inference that still needs evidence;\n- **unsupported** — unavailable from the returned scope and not asserted.\n\nThe optional `context` dataset is aggregate-only private local evidence. Its\n`observed_bytes` and `events` measures are exact for the structurally observed\npayload strings that were indexed. `estimated_tokens` is available only when\nan explicit tokenizer populated it; always preserve its estimator identity and\ncoverage. Never describe category bytes or estimates as exact billed input\ntokens, and keep `unattributed_input_tokens` unsupported when the response\nreports it as `null`. If context composition is disabled, continue with the\nbase accounting datasets instead of starting hidden work.\n\nCall `usage_refresh` only when freshness matters. Reuse the returned job; never\nstart a duplicate. Use `usage_job_status` with a bounded `wait_seconds` value\nso the host waits; do not short-interval poll from the model. Use\n`usage_allowance` for observed allowance facts and preserve its provenance and\nlimitations. Do not infer waste or productivity from token totals alone.\n\nNever inspect raw logs as a fallback, invent missing selectors, claim narrative\nfindings the tools did not return, or expose prompts, reasoning, tool\narguments\u002Foutput, secrets, or local paths.\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fdouglasmonsky\u002Fcodex-usage-tracker\u002Fskills\u002Fusage-kernel",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":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill usage-kernel",{"tool":56,"command":57},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill usage-kernel",{"tool":59,"command":60},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill usage-kernel","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fdouglasmonsky\u002Fcodex-usage-tracker\u002Fskills\u002Fusage-kernel\u002FSKILL.md",true,[],[65,75,83,91,99,107],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":70,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":74},"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":79,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":74},"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":87,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":74},"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":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":95,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":74},"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":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":103,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":74},"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":111,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":74},"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",[],[]]