[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MJCYMMFTF4PK2HBRDXXAC3":3,"skill-same:01M6MJCYMMFTF4PK2HBRDXXAC3":67},{"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":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":48,"ownerHtmlUrl":49,"ownerBlogUrl":50,"ownerDescription":51,"updatedAt":52,"install":53,"resources":66},"01M6MJCYMMFTF4PK2HBRDXXAC3","costguard",null,"Find and quantify CI\u002Fcron and cloud-spend waste. Audit repos, run read-only provider billing checks, preview or apply CI auto-fixes, and render a monthly cost digest.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fmbanderas\u002Fcostguard\u002Fskills\u002Fcostguard\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"provider","apply","fixes","read-only","billing","render","monthly","digest","preview","repos","cost","only","auto","read","find","cron","ci","audit","run","2026-11-10 10:12:30",false,"---\nname: costguard\ndescription: Find and quantify CI\u002Fcron and cloud-spend waste. Audit repos, run read-only provider billing checks, preview or apply CI auto-fixes, and render a monthly cost digest.\nlicense: MIT\n---\n\nDrive **Costguard** — a read-only cost auditor for CI minutes, cron schedules,\nand cloud provider billing (GitHub Actions, Vercel, Supabase, Railway, Netlify, Neon, Cloudflare, and more).\nIt finds waste, estimates the monthly dollar cost, and can surgically auto-fix\nCI workflow files. It never writes to provider accounts, never pushes git, and\nnever prints tokens.\n\nMap the user's request to one Costguard CLI call and run it from the repo root.\n\n## Command launcher\n\nCostguard reads a `workspaces.json` registry from the **current working\ndirectory**, so run it from a project that has one (or run `registry init`\nfirst). Pick the launcher that matches your context; below, `costguard\n\u003Csubcommand>` means whichever you use.\n\n### If installed via plugin\n\nWhen this skill is loaded from the Costguard plugin, run the bundled build — it\nships a prebuilt `dist\u002Fcli\u002Findex.js`, so no build step is needed. Locate the\nplugin root (the dir containing `dist\u002Fcli\u002Findex.js`):\n\n- **Claude Code** — it is `${CLAUDE_PLUGIN_ROOT}`:\n\n  ```bash\n  node \"${CLAUDE_PLUGIN_ROOT}\u002Fdist\u002Fcli\u002Findex.js\" \u003Csubcommand> ...\n  ```\n\n- **Codex** — walk up from this `SKILL.md` to the dir holding\n  `.codex-plugin\u002Fplugin.json`:\n\n  ```bash\n  node \"\u003Cplugin-root>\u002Fdist\u002Fcli\u002Findex.js\" \u003Csubcommand> ...\n  ```\n\n### If using npx (no plugin)\n\nNo checkout and no build — run the published CLI directly:\n\n```bash\nnpx -y -p @costguard\u002Fcostguard-mcp costguard \u003Csubcommand> ...\n```\n\nOr, if `costguard` is on `PATH` (`npm i -g @costguard\u002Fcostguard-mcp`), use it\ndirectly: `costguard \u003Csubcommand> ...`. Heads-up: `npx -y @costguard\u002Fcostguard-mcp`\n(no `-p`, no subcommand) starts the MCP **server**, whereas `npx -y -p\n@costguard\u002Fcostguard-mcp costguard \u003Csubcommand>` runs the **CLI**.\n\n## 1. Audit for waste (the main action)\n\n```bash\ncostguard audit \u003Cworkspace...>            # named workspaces\ncostguard audit --all                     # every registered workspace\ncostguard audit \u003Cws> --providers all      # + read-only cloud billing checks\ncostguard audit \u003Cws> --ci-only            # static CI checks only\ncostguard audit \u003Cws> --crons-only         # cron checks only\ncostguard audit \u003Cws> --site               # + read-only live-site checks (site URL from registry)\ncostguard audit \u003Cws> --substitutions      # + cross-tool cheaper-alternative suggestions\ncostguard audit \u003Cws> --json               # JSON instead of Markdown\n```\n\nPrints a report: each finding has a severity, an estimated monthly USD cost, a\ndetail, and a fix suggestion. Report stdout verbatim.\n\n## 2. Scan \u002F registry \u002F report\n\n```bash\ncostguard scan                # discover CI + cron files under the registry root\ncostguard registry list       # show registered workspaces\ncostguard registry init       # create a workspaces.json in the cwd\ncostguard report              # re-render the last saved audit run\n```\n\n## 3. Auto-fix CI files (dry-run first)\n\n```bash\ncostguard fix \u003Cws>            # dry-run: print a unified-diff preview, write nothing\ncostguard fix \u003Cws> --apply    # write the surgical edits to disk (idempotent)\ncostguard fix \u003Cws> --pr       # also emit local PR artifacts (no push)\n```\n\nDefault is dry-run. Only deterministic ADD-rule fixers run (timeout,\nconcurrency, paths-ignore). Costguard never pushes; `--open-pr` is gated and\nrefuses without an explicit token.\n\n## 4. Monthly cost digest\n\n```bash\ncostguard digest             # render the digest from the last run (dry-run)\ncostguard digest --post      # delivery adapter (inert unless configured)\n```\n\n## 5. Auto-discover providers\n\nDetect which providers a repo uses — from config files, `package.json` deps, and\nenv-var **names** (never values, never secrets). Covers all 13 wired providers\nplus inngest.\n\n```bash\ncostguard discover [dir]     # list detected providers + evidence (default dir: .)\ncostguard discover . --json  # JSON: { dir, providers, detections }\ncostguard discover . --write # union-merge detected providers into .\u002Fworkspaces.json (non-destructive)\n```\n\n## 6. Live-site cost checks\n\nRead-only, GET-only checks on a live URL (no browser, no form submit, no auth\nreplay). Flags transfer weight, oversized images, missing compression, weak cache\nheaders, and render-blocking scripts. The `$\u002Fmo` headline is the single\n`site\u002Ftransfer-weight` line — sourced when the host bills transfer (Vercel\u002FNetlify),\nor an explicit `$0` performance note (Cloudflare Pages static \u002F unknown host).\nPer-asset findings (`oversized-image`, `missing-compression`) put their dollar share\nin `detail` and carry `estMonthlyUsd: 0` (no double-count); a `$0` performance-only\npage never raises a `high` finding, so it never fails CI on cost alone.\n\n```bash\ncostguard site \u003Curl>         # Markdown report\ncostguard site \u003Curl> --json  # JSON findings\n```\n\n`audit --site` runs the same checks for any workspace whose `workspaces.json`\nentry has a `site` URL. `audit --substitutions` adds cross-tool\n`\u003Cprovider>\u002Fcheaper-alternative` suggestions (e.g. a static Vercel\u002FNetlify Pro\nsite → Cloudflare Pages), each with a sourced saving, migration effort, and\nlock-in caveat.\n\n## Provider billing checks\n\n`--providers \u003Cids|all>` adds read-only billing checks for the providers listed\non each workspace in `workspaces.json`. Tokens are read from the environment \u002F\n`.env` only. A provider whose token env var is absent is **skipped**, not\nfailed. Supported: `github`, `supabase`, `railway`, `netlify`, `neon`, `vercel`,\n`sentry`, `upstash`, `atlas`, `cloudflare`, `fly`, `render`, `datadog` (+ inngest\ndetection).\n\n## 7. MCP tools (for AI coding agents)\n\nCostguard also ships a bundled **MCP server** that exposes the same engine over a\nhost-agnostic tool surface (Claude Code, Codex, any MCP host). It wraps the same\nread-only engine functions — no new behavior, same posture. In Claude Code it is\ndeclared by `.claude-plugin\u002F.mcp.json` and launched from the bundled build:\n\n```json\n{ \"mcpServers\": { \"costguard\": { \"command\": \"node\",\n  \"args\": [\"${CLAUDE_PLUGIN_ROOT}\u002Fdist\u002Fmcp\u002Fserver.js\"] } } }\n```\n\nIn the plugin, the server runs from the committed `dist\u002Fmcp\u002Fserver.js` — no\ninstall step.\n\n### Codex MCP config\n\nFor **Codex**, add one of these to `~\u002F.codex\u002Fconfig.toml`. Use npx for a\nno-checkout install (pulls the published package), or the bundled build if you\nrun Codex from the plugin:\n\n```toml\n# npx — no checkout\n[mcp_servers.costguard]\ncommand = \"npx\"\nargs = [\"-y\", \"@costguard\u002Fcostguard-mcp\"]\n```\n\n```toml\n# bundled plugin build\n[mcp_servers.costguard]\ncommand = \"node\"\nargs = [\"\u003Cplugin-root>\u002Fdist\u002Fmcp\u002Fserver.js\"]\n```\n\nTools:\n\n| Tool | Posture |\n|---|---|\n| `audit_workspace` | read-only; returns a Findings envelope (`includeSite` adds site checks) |\n| `discover_providers` | read-only; env-var NAMES only, never values |\n| `audit_site` | read-only, GET-only |\n| `plan_fix` | dry-run; returns unified diffs only, writes nothing |\n| `apply_fix` | writes local CI files; REFUSES unless `confirmApply:true`; never pushes git |\n| `plan_live_checks` | plans a live billing read (see below); emits a snippet only with consent |\n| `ingest_live_reading` | parses a returned billing figure into a Finding |\n\n## 8. Live billing checks (`--live`) — opt-in, consent-gated\n\n`--live` **extends** the read-only posture above: it adds **browser-driven reads\nover your already-logged-in session**, performed by the **playwriter** MCP server\nunder the agent's orchestration. This is a genuine posture change and is treated\nas one — **off by default, opt-in, and consent-gated.** costguard's own tools\nstill never drive a browser and never see credentials: `plan_live_checks` only\nemits a **read-only** snippet (navigation + reading rendered billing figures — no\nclicks, typing, form submits, credential replay, cookies, localStorage,\nsessionStorage, or screenshots), and `ingest_live_reading` only parses the\nreturned figure. The browser action is performed by playwriter, authorized by you.\n\n**API-first \u002F browser-fallback:** `plan_live_checks` is API-first when a provider\nmodule exists and its API token resolves from the environment (a deterministic\nenv-NAME check, no network probe) — in that case prefer `audit_workspace`. Only\nwhen there is no usable API token does it fall back to a browser playbook.\n\n**Three consent gates (all required):** (1) the host's MCP tool-call consent;\n(2) costguard's own per-run confirmation — `plan_live_checks` returns a\n`consentNotice` the agent MUST surface, and emits the actionable snippet only when\ncalled with `confirmLive:true`; (3) playwriter's own consent before it executes.\n\n**Graceful degrade:** if playwriter is not connected, the agent cannot run the\nsnippet; `ingest_live_reading` returns a `kind:\"diagnostic\"` Finding (excluded\nfrom cost totals) and the audit never blocks.\n\n## Notes\n\n- All provider calls are read-only (GET \u002F read-only GraphQL). No POST\u002FPUT\u002FPATCH\u002F\n  DELETE to provider accounts.\n- Estimated dollar costs are best-effort and depend on plan\u002Ftier; treat them as\n  directional, not invoices.\n- Requires `node` on `PATH`. The bare `costguard` command is optional when the\n  skill runs from the plugin — use the plugin-root `node` launcher above.\n","Drive **Costguard** — a read-only cost auditor for CI minutes, cron schedules,\nand cloud provider billing (GitHub Actions, Vercel, Supabase, Railway, Netlify, Neon, Cloudflare, and more).\nIt finds waste, estimates the monthly dollar cost, and can surgically auto-fix\nCI workflow files. It never writes to provider accounts, never pushes git, and\nnever prints tokens.\n\nMap the user's request to one Costguard CLI call and run it from the repo root.\n\n## Command launcher\n\nCostguard reads a `workspaces.json` registry from the **current working\ndirectory**, so run it from a project that has one (or run `registry init`\nfirst). Pick the launcher that matches your context; below, `costguard\n\u003Csubcommand>` means whichever you use.\n\n### If installed via plugin\n\nWhen this skill is loaded from the Costguard plugin, run the bundled build — it\nships a prebuilt `dist\u002Fcli\u002Findex.js`, so no build step is needed. Locate the\nplugin root (the dir containing `dist\u002Fcli\u002Findex.js`):\n\n- **Claude Code** — it is `${CLAUDE_PLUGIN_ROOT}`:\n\n  ```bash\n  node \"${CLAUDE_PLUGIN_ROOT}\u002Fdist\u002Fcli\u002Findex.js\" \u003Csubcommand> ...\n  ```\n\n- **Codex** — walk up from this `SKILL.md` to the dir holding\n  `.codex-plugin\u002Fplugin.json`:\n\n  ```bash\n  node \"\u003Cplugin-root>\u002Fdist\u002Fcli\u002Findex.js\" \u003Csubcommand> ...\n  ```\n\n### If using npx (no plugin)\n\nNo checkout and no build — run the published CLI directly:\n\n```bash\nnpx -y -p @costguard\u002Fcostguard-mcp costguard \u003Csubcommand> ...\n```\n\nOr, if `costguard` is on `PATH` (`npm i -g @costguard\u002Fcostguard-mcp`), use it\ndirectly: `costguard \u003Csubcommand> ...`. Heads-up: `npx -y @costguard\u002Fcostguard-mcp`\n(no `-p`, no subcommand) starts the MCP **server**, whereas `npx -y -p\n@costguard\u002Fcostguard-mcp costguard \u003Csubcommand>` runs the **CLI**.\n\n## 1. Audit for waste (the main action)\n\n```bash\ncostguard audit \u003Cworkspace...>            # named workspaces\ncostguard audit --all                     # every registered workspace\ncostguard audit \u003Cws> --providers all      # + read-only cloud billing checks\ncostguard audit \u003Cws> --ci-only            # static CI checks only\ncostguard audit \u003Cws> --crons-only         # cron checks only\ncostguard audit \u003Cws> --site               # + read-only live-site checks (site URL from registry)\ncostguard audit \u003Cws> --substitutions      # + cross-tool cheaper-alternative suggestions\ncostguard audit \u003Cws> --json               # JSON instead of Markdown\n```\n\nPrints a report: each finding has a severity, an estimated monthly USD cost, a\ndetail, and a fix suggestion. Report stdout verbatim.\n\n## 2. Scan \u002F registry \u002F report\n\n```bash\ncostguard scan                # discover CI + cron files under the registry root\ncostguard registry list       # show registered workspaces\ncostguard registry init       # create a workspaces.json in the cwd\ncostguard report              # re-render the last saved audit run\n```\n\n## 3. Auto-fix CI files (dry-run first)\n\n```bash\ncostguard fix \u003Cws>            # dry-run: print a unified-diff preview, write nothing\ncostguard fix \u003Cws> --apply    # write the surgical edits to disk (idempotent)\ncostguard fix \u003Cws> --pr       # also emit local PR artifacts (no push)\n```\n\nDefault is dry-run. Only deterministic ADD-rule fixers run (timeout,\nconcurrency, paths-ignore). Costguard never pushes; `--open-pr` is gated and\nrefuses without an explicit token.\n\n## 4. Monthly cost digest\n\n```bash\ncostguard digest             # render the digest from the last run (dry-run)\ncostguard digest --post      # delivery adapter (inert unless configured)\n```\n\n## 5. Auto-discover providers\n\nDetect which providers a repo uses — from config files, `package.json` deps, and\nenv-var **names** (never values, never secrets). Covers all 13 wired providers\nplus inngest.\n\n```bash\ncostguard discover [dir]     # list detected providers + evidence (default dir: .)\ncostguard discover . --json  # JSON: { dir, providers, detections }\ncostguard discover . --write # union-merge detected providers into .\u002Fworkspaces.json (non-destructive)\n```\n\n## 6. Live-site cost checks\n\nRead-only, GET-only checks on a live URL (no browser, no form submit, no auth\nreplay). Flags transfer weight, oversized images, missing compression, weak cache\nheaders, and render-blocking scripts. The `$\u002Fmo` headline is the single\n`site\u002Ftransfer-weight` line — sourced when the host bills transfer (Vercel\u002FNetlify),\nor an explicit `$0` performance note (Cloudflare Pages static \u002F unknown host).\nPer-asset findings (`oversized-image`, `missing-compression`) put their dollar share\nin `detail` and carry `estMonthlyUsd: 0` (no double-count); a `$0` performance-only\npage never raises a `high` finding, so it never fails CI on cost alone.\n\n```bash\ncostguard site \u003Curl>         # Markdown report\ncostguard site \u003Curl> --json  # JSON findings\n```\n\n`audit --site` runs the same checks for any workspace whose `workspaces.json`\nentry has a `site` URL. `audit --substitutions` adds cross-tool\n`\u003Cprovider>\u002Fcheaper-alternative` suggestions (e.g. a static Vercel\u002FNetlify Pro\nsite → Cloudflare Pages), each with a sourced saving, migration effort, and\nlock-in caveat.\n\n## Provider billing checks\n\n`--providers \u003Cids|all>` adds read-only billing checks for the providers listed\non each workspace in `workspaces.json`. Tokens are read from the environment \u002F\n`.env` only. A provider whose token env var is absent is **skipped**, not\nfailed. Supported: `github`, `supabase`, `railway`, `netlify`, `neon`, `vercel`,\n`sentry`, `upstash`, `atlas`, `cloudflare`, `fly`, `render`, `datadog` (+ inngest\ndetection).\n\n## 7. MCP tools (for AI coding agents)\n\nCostguard also ships a bundled **MCP server** that exposes the same engine over a\nhost-agnostic tool surface (Claude Code, Codex, any MCP host). It wraps the same\nread-only engine functions — no new behavior, same posture. In Claude Code it is\ndeclared by `.claude-plugin\u002F.mcp.json` and launched from the bundled build:\n\n```json\n{ \"mcpServers\": { \"costguard\": { \"command\": \"node\",\n  \"args\": [\"${CLAUDE_PLUGIN_ROOT}\u002Fdist\u002Fmcp\u002Fserver.js\"] } } }\n```\n\nIn the plugin, the server runs from the committed `dist\u002Fmcp\u002Fserver.js` — no\ninstall step.\n\n### Codex MCP config\n\nFor **Codex**, add one of these to `~\u002F.codex\u002Fconfig.toml`. Use npx for a\nno-checkout install (pulls the published package), or the bundled build if you\nrun Codex from the plugin:\n\n```toml\n# npx — no checkout\n[mcp_servers.costguard]\ncommand = \"npx\"\nargs = [\"-y\", \"@costguard\u002Fcostguard-mcp\"]\n```\n\n```toml\n# bundled plugin build\n[mcp_servers.costguard]\ncommand = \"node\"\nargs = [\"\u003Cplugin-root>\u002Fdist\u002Fmcp\u002Fserver.js\"]\n```\n\nTools:\n\n| Tool | Posture |\n|---|---|\n| `audit_workspace` | read-only; returns a Findings envelope (`includeSite` adds site checks) |\n| `discover_providers` | read-only; env-var NAMES only, never values |\n| `audit_site` | read-only, GET-only |\n| `plan_fix` | dry-run; returns unified diffs only, writes nothing |\n| `apply_fix` | writes local CI files; REFUSES unless `confirmApply:true`; never pushes git |\n| `plan_live_checks` | plans a live billing read (see below); emits a snippet only with consent |\n| `ingest_live_reading` | parses a returned billing figure into a Finding |\n\n## 8. Live billing checks (`--live`) — opt-in, consent-gated\n\n`--live` **extends** the read-only posture above: it adds **browser-driven reads\nover your already-logged-in session**, performed by the **playwriter** MCP server\nunder the agent's orchestration. This is a genuine posture change and is treated\nas one — **off by default, opt-in, and consent-gated.** costguard's own tools\nstill never drive a browser and never see credentials: `plan_live_checks` only\nemits a **read-only** snippet (navigation + reading rendered billing figures — no\nclicks, typing, form submits, credential replay, cookies, localStorage,\nsessionStorage, or screenshots), and `ingest_live_reading` only parses the\nreturned figure. The browser action is performed by playwriter, authorized by you.\n\n**API-first \u002F browser-fallback:** `plan_live_checks` is API-first when a provider\nmodule exists and its API token resolves from the environment (a deterministic\nenv-NAME check, no network probe) — in that case prefer `audit_workspace`. Only\nwhen there is no usable API token does it fall back to a browser playbook.\n\n**Three consent gates (all required):** (1) the host's MCP tool-call consent;\n(2) costguard's own per-run confirmation — `plan_live_checks` returns a\n`consentNotice` the agent MUST surface, and emits the actionable snippet only when\ncalled with `confirmLive:true`; (3) playwriter's own consent before it executes.\n\n**Graceful degrade:** if playwriter is not connected, the agent cannot run the\nsnippet; `ingest_live_reading` returns a `kind:\"diagnostic\"` Finding (excluded\nfrom cost totals) and the audit never blocks.\n\n## Notes\n\n- All provider calls are read-only (GET \u002F read-only GraphQL). No POST\u002FPUT\u002FPATCH\u002F\n  DELETE to provider accounts.\n- Estimated dollar costs are best-effort and depend on plan\u002Ftier; treat them as\n  directional, not invoices.\n- Requires `node` on `PATH`. The bare `costguard` command is optional when the\n  skill runs from the plugin — use the plugin-root `node` launcher above.\n",{"name":5,"license":15,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fmbanderas\u002Fcostguard\u002Fskills\u002Fcostguard",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":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill costguard",{"tool":59,"command":60},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill costguard",{"tool":62,"command":63},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill costguard","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fmbanderas\u002Fcostguard\u002Fskills\u002Fcostguard\u002FSKILL.md",true,[],[68,77,85,93,101,109],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":72,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":76},"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.","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":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":81,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":76},"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":89,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":76},"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":97,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":76},"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":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":105,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":76},"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":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":113,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":76},"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",[],[]]