[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77S9HDR4VKXM2RPABMPFMJA":3,"skill-same:01M77S9HDR4VKXM2RPABMPFMJA":43},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":13,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":28,"install":29,"resources":42},"01M77S9HDR4VKXM2RPABMPFMJA","hol-guard",null,"Use when setting up HOL Guard, protecting local AI harnesses, reviewing Guard approvals or receipts, scanning Codex plugins, skills, MCP servers, marketplace packages, or running plugin-scanner verification before release.","ConcertoNotes\u002Fcodex-plugins","ConcertoNotes","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F249301288?v=4","01M77NJ0BK2KN5YW0D8RHD99TB","01M77NJ0CCEDPATAY3JTXEWNK5",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FConcertoNotes\u002Fcodex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fcommunity\u002Fhol-guard-plugin\u002Fskills\u002Fhol-guard\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: hol-guard\ndescription: Use when setting up HOL Guard, protecting local AI harnesses, reviewing Guard approvals or receipts, scanning Codex plugins, skills, MCP servers, marketplace packages, or running plugin-scanner verification before release.\nlicense: Apache-2.0\n---\n\n# HOL Guard\n\nHOL Guard protects local AI harnesses before tools run. Use this skill when the user wants AI antivirus behavior, local approval review, Codex protection, Claude Code protection, MCP safety checks, skill\u002Fpackage verification, or release gates from `hol-guard` and `plugin-scanner`.\n\n## Hard Rules\n\n- Never read `.env` files.\n- Never bypass Guard approvals.\n- Do not mark a workspace protected until a Guard command proves status.\n- Prefer reversible Guard commands over direct harness config edits.\n- Do not mutate user-level harness config unless the `hol-guard` command owns that mutation.\n- Treat scanner failures as real until inspected.\n- Preserve existing user changes and inspect `git status --short` before edits in a repo.\n\n## Install Check\n\nFirst check whether the CLI exists:\n\n```bash\ncommand -v hol-guard\ncommand -v plugin-scanner\n```\n\nIf missing and the user asked for setup, prefer:\n\n```bash\npipx install hol-guard\n```\n\nFallback only when `pipx` is unavailable:\n\n```bash\npython3 -m pip install --user hol-guard\n```\n\nAfter install:\n\n```bash\nhol-guard status\nhol-guard detect --json\n```\n\n## Protect A Local Harness\n\nUse this flow for Codex, Claude Code, Copilot CLI, Cursor, Gemini, Hermes, OpenClaw, OpenCode, or Antigravity.\n\n```bash\nhol-guard bootstrap\nhol-guard install \u003Charness>\nhol-guard run \u003Charness> --dry-run\nhol-guard run \u003Charness>\nhol-guard status\n```\n\nHarness names:\n\n- `codex`\n- `claude-code`\n- `copilot`\n- `cursor`\n- `gemini`\n- `hermes`\n- `openclaw`\n- `opencode`\n- `antigravity`\n\nHarness aliases:\n\n- `claude` maps to `claude-code`\n- `gemini-cli` maps to `gemini`\n- `open-code` maps to `opencode`\n- `open-claw` maps to `openclaw`\n- `copilot-cli` maps to `copilot`\n\nUse harness-specific bootstrap when available:\n\n```bash\nhol-guard hermes bootstrap\n```\n\n### Claude Code\n\nUse this when the workspace has `.claude\u002Fsettings.local.json`, `.claude\u002Fagents`, Claude hooks, `.mcp.json`, or Claude-managed tool approval surfaces.\n\n```bash\nhol-guard install claude-code\nhol-guard run claude-code --dry-run\nhol-guard run claude-code\nhol-guard doctor claude-code --json\n```\n\nClaude Code is a first-class Guard target. Prefer Guard-owned Claude hooks over direct manual edits to Claude config.\n\n### Codex\n\nUse this when the workspace has Codex config, `.codex\u002Fhooks.json`, Codex MCP servers, or Codex App\u002FCLI tool flows.\n\n```bash\nhol-guard install codex\nhol-guard run codex --dry-run\nhol-guard run codex\nhol-guard doctor codex --json\n```\n\nCodex supports Guard-owned `PreToolUse` Bash hooks and same-chat MCP elicitation where available.\n\n### Other Harnesses\n\nUse the same Guard flow for:\n\n- Copilot CLI: `hol-guard install copilot`\n- Cursor: `hol-guard install cursor`\n- Gemini CLI: `hol-guard install gemini`\n- Hermes: `hol-guard hermes bootstrap`\n- OpenClaw: `hol-guard install openclaw`\n- OpenCode: `hol-guard install opencode`\n- Antigravity: `hol-guard install antigravity`\n\n## Approval Work\n\nIf Guard blocks or queues work:\n\n```bash\nhol-guard approvals\nhol-guard approvals open\nhol-guard receipts\nhol-guard diff \u003Charness>\n```\n\nFor terminal-only resolution:\n\n```bash\nhol-guard approvals approve \u003Crequest-id>\nhol-guard approvals deny \u003Crequest-id>\n```\n\nOnly approve after reading the risk reason and understanding the requested scope.\n\n## Evidence Work\n\nUse evidence commands when user needs proof, audit trail, or handoff artifacts:\n\n```bash\nhol-guard receipts\nhol-guard inventory\nhol-guard abom --format json\nhol-guard events\nhol-guard explain \u003Cartifact-id>\n```\n\nFor cloud sync, keep it optional and user-directed:\n\n```bash\nhol-guard connect\nhol-guard connect status\nhol-guard connect repair\nhol-guard sync\n```\n\n## Scan A Plugin Or Skill Package\n\nUse scanner mode for Codex plugins, Claude Code project surfaces, `.agents` marketplaces, skills, MCP server configs, and release gates.\n\n```bash\nplugin-scanner lint .\nplugin-scanner verify .\n```\n\nIf scanning a specific package:\n\n```bash\nplugin-scanner lint \u003Cpath>\nplugin-scanner verify \u003Cpath>\n```\n\nIf the target is a Codex marketplace root with `.agents\u002Fplugins\u002Fmarketplace.json`, scan the repo root so local plugin entries can be discovered.\n\nScanner target guidance:\n\n- Codex plugin: scan the repo root or plugin folder containing `.codex-plugin\u002Fplugin.json`.\n- Codex marketplace: scan the repo root containing `.agents\u002Fplugins\u002Fmarketplace.json`.\n- Claude Code project: scan the workspace root containing `.claude\u002F`, `.mcp.json`, hooks, or agent folders.\n- MCP server package: scan the package root containing server config and package metadata.\n- Skill package: scan the folder containing `SKILL.md`.\n- Mixed agent workspace: scan the repo root so local plugin, skill, MCP, and harness config surfaces are discovered together.\n\n## Common Debug Commands\n\n```bash\nhol-guard doctor\nhol-guard doctor \u003Charness> --json\nhol-guard detect --json\nhol-guard settings show\nhol-guard explain install-connect\nplugin-scanner verify . --json\n```\n\n## Response Pattern\n\nWhen using Guard, report:\n\n- What command ran.\n- What Guard found.\n- What remains blocked or risky.\n- What proof exists.\n- Exact next command if user must act.\n\nDo not claim protection, approval, or release readiness without command output proving it.\n\n## Local Helper\n\nThis plugin includes:\n\n```bash\nbash scripts\u002Fhol-guard-plugin status\nbash scripts\u002Fhol-guard-plugin harnesses\nbash scripts\u002Fhol-guard-plugin protect claude-code\nbash scripts\u002Fhol-guard-plugin protect \u003Charness>\nbash scripts\u002Fhol-guard-plugin scan-system claude \u003Cpath>\nbash scripts\u002Fhol-guard-plugin scan-system codex \u003Cpath>\nbash scripts\u002Fhol-guard-plugin scan \u003Cpath>\nbash scripts\u002Fhol-guard-plugin evidence\n```\n\nUse the helper only when running from this plugin repository. Otherwise call `hol-guard` and `plugin-scanner` directly.\n","# HOL Guard\n\nHOL Guard protects local AI harnesses before tools run. Use this skill when the user wants AI antivirus behavior, local approval review, Codex protection, Claude Code protection, MCP safety checks, skill\u002Fpackage verification, or release gates from `hol-guard` and `plugin-scanner`.\n\n## Hard Rules\n\n- Never read `.env` files.\n- Never bypass Guard approvals.\n- Do not mark a workspace protected until a Guard command proves status.\n- Prefer reversible Guard commands over direct harness config edits.\n- Do not mutate user-level harness config unless the `hol-guard` command owns that mutation.\n- Treat scanner failures as real until inspected.\n- Preserve existing user changes and inspect `git status --short` before edits in a repo.\n\n## Install Check\n\nFirst check whether the CLI exists:\n\n```bash\ncommand -v hol-guard\ncommand -v plugin-scanner\n```\n\nIf missing and the user asked for setup, prefer:\n\n```bash\npipx install hol-guard\n```\n\nFallback only when `pipx` is unavailable:\n\n```bash\npython3 -m pip install --user hol-guard\n```\n\nAfter install:\n\n```bash\nhol-guard status\nhol-guard detect --json\n```\n\n## Protect A Local Harness\n\nUse this flow for Codex, Claude Code, Copilot CLI, Cursor, Gemini, Hermes, OpenClaw, OpenCode, or Antigravity.\n\n```bash\nhol-guard bootstrap\nhol-guard install \u003Charness>\nhol-guard run \u003Charness> --dry-run\nhol-guard run \u003Charness>\nhol-guard status\n```\n\nHarness names:\n\n- `codex`\n- `claude-code`\n- `copilot`\n- `cursor`\n- `gemini`\n- `hermes`\n- `openclaw`\n- `opencode`\n- `antigravity`\n\nHarness aliases:\n\n- `claude` maps to `claude-code`\n- `gemini-cli` maps to `gemini`\n- `open-code` maps to `opencode`\n- `open-claw` maps to `openclaw`\n- `copilot-cli` maps to `copilot`\n\nUse harness-specific bootstrap when available:\n\n```bash\nhol-guard hermes bootstrap\n```\n\n### Claude Code\n\nUse this when the workspace has `.claude\u002Fsettings.local.json`, `.claude\u002Fagents`, Claude hooks, `.mcp.json`, or Claude-managed tool approval surfaces.\n\n```bash\nhol-guard install claude-code\nhol-guard run claude-code --dry-run\nhol-guard run claude-code\nhol-guard doctor claude-code --json\n```\n\nClaude Code is a first-class Guard target. Prefer Guard-owned Claude hooks over direct manual edits to Claude config.\n\n### Codex\n\nUse this when the workspace has Codex config, `.codex\u002Fhooks.json`, Codex MCP servers, or Codex App\u002FCLI tool flows.\n\n```bash\nhol-guard install codex\nhol-guard run codex --dry-run\nhol-guard run codex\nhol-guard doctor codex --json\n```\n\nCodex supports Guard-owned `PreToolUse` Bash hooks and same-chat MCP elicitation where available.\n\n### Other Harnesses\n\nUse the same Guard flow for:\n\n- Copilot CLI: `hol-guard install copilot`\n- Cursor: `hol-guard install cursor`\n- Gemini CLI: `hol-guard install gemini`\n- Hermes: `hol-guard hermes bootstrap`\n- OpenClaw: `hol-guard install openclaw`\n- OpenCode: `hol-guard install opencode`\n- Antigravity: `hol-guard install antigravity`\n\n## Approval Work\n\nIf Guard blocks or queues work:\n\n```bash\nhol-guard approvals\nhol-guard approvals open\nhol-guard receipts\nhol-guard diff \u003Charness>\n```\n\nFor terminal-only resolution:\n\n```bash\nhol-guard approvals approve \u003Crequest-id>\nhol-guard approvals deny \u003Crequest-id>\n```\n\nOnly approve after reading the risk reason and understanding the requested scope.\n\n## Evidence Work\n\nUse evidence commands when user needs proof, audit trail, or handoff artifacts:\n\n```bash\nhol-guard receipts\nhol-guard inventory\nhol-guard abom --format json\nhol-guard events\nhol-guard explain \u003Cartifact-id>\n```\n\nFor cloud sync, keep it optional and user-directed:\n\n```bash\nhol-guard connect\nhol-guard connect status\nhol-guard connect repair\nhol-guard sync\n```\n\n## Scan A Plugin Or Skill Package\n\nUse scanner mode for Codex plugins, Claude Code project surfaces, `.agents` marketplaces, skills, MCP server configs, and release gates.\n\n```bash\nplugin-scanner lint .\nplugin-scanner verify .\n```\n\nIf scanning a specific package:\n\n```bash\nplugin-scanner lint \u003Cpath>\nplugin-scanner verify \u003Cpath>\n```\n\nIf the target is a Codex marketplace root with `.agents\u002Fplugins\u002Fmarketplace.json`, scan the repo root so local plugin entries can be discovered.\n\nScanner target guidance:\n\n- Codex plugin: scan the repo root or plugin folder containing `.codex-plugin\u002Fplugin.json`.\n- Codex marketplace: scan the repo root containing `.agents\u002Fplugins\u002Fmarketplace.json`.\n- Claude Code project: scan the workspace root containing `.claude\u002F`, `.mcp.json`, hooks, or agent folders.\n- MCP server package: scan the package root containing server config and package metadata.\n- Skill package: scan the folder containing `SKILL.md`.\n- Mixed agent workspace: scan the repo root so local plugin, skill, MCP, and harness config surfaces are discovered together.\n\n## Common Debug Commands\n\n```bash\nhol-guard doctor\nhol-guard doctor \u003Charness> --json\nhol-guard detect --json\nhol-guard settings show\nhol-guard explain install-connect\nplugin-scanner verify . --json\n```\n\n## Response Pattern\n\nWhen using Guard, report:\n\n- What command ran.\n- What Guard found.\n- What remains blocked or risky.\n- What proof exists.\n- Exact next command if user must act.\n\nDo not claim protection, approval, or release readiness without command output proving it.\n\n## Local Helper\n\nThis plugin includes:\n\n```bash\nbash scripts\u002Fhol-guard-plugin status\nbash scripts\u002Fhol-guard-plugin harnesses\nbash scripts\u002Fhol-guard-plugin protect claude-code\nbash scripts\u002Fhol-guard-plugin protect \u003Charness>\nbash scripts\u002Fhol-guard-plugin scan-system claude \u003Cpath>\nbash scripts\u002Fhol-guard-plugin scan-system codex \u003Cpath>\nbash scripts\u002Fhol-guard-plugin scan \u003Cpath>\nbash scripts\u002Fhol-guard-plugin evidence\n```\n\nUse the helper only when running from this plugin repository. Otherwise call `hol-guard` and `plugin-scanner` directly.\n",{"name":5,"license":14,"description":7},"main","9ba3c9fadff1092395837bf1502e1b8a7f98b1e1","plugins\u002Fcommunity\u002Fhol-guard-plugin\u002Fskills\u002Fhol-guard","https:\u002F\u002Fgithub.com\u002FConcertoNotes\u002Fcodex-plugins","https:\u002F\u002Fgithub.com\u002FConcertoNotes","2026-06-26 10:13:54",{"source":8,"skillName":5,"commands":30,"prompt":40,"zipAvailable":41},[31,34,37],{"tool":32,"command":33},"npx","npx skills add ConcertoNotes\u002Fcodex-plugins --skill hol-guard",{"tool":35,"command":36},"bunx","bunx skills add ConcertoNotes\u002Fcodex-plugins --skill hol-guard",{"tool":38,"command":39},"pnpm","pnpm dlx skills add ConcertoNotes\u002Fcodex-plugins --skill hol-guard","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FConcertoNotes\u002Fcodex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fcommunity\u002Fhol-guard-plugin\u002Fskills\u002Fhol-guard\u002FSKILL.md",true,[],[44,52,60,68,75,82],{"skillNo":45,"name":46,"nameZh":6,"description":47,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":48,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":18},"01M77YB7WW36DS9AERTWP673E0","android-emulator-qa","Use when validating Android feature flows in an emulator with adb-driven launch, input, UI-tree inspection, screenshots, and logcat capture.","https:\u002F\u002Fgithub.com\u002FConcertoNotes\u002Fcodex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fofficial\u002Ftest-android-apps\u002Fskills\u002Fandroid-emulator-qa\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FConcertoNotes\u002Fcodex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fofficial\u002Ftest-android-apps\u002Fskills\u002Fandroid-emulator-qa\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":56,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":18},"01M77Y7AA8N45G6NM0WJSS2W9C","supabase-postgres-best-practices","Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.","MIT","https:\u002F\u002Fgithub.com\u002FConcertoNotes\u002Fcodex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fofficial\u002Fsupabase\u002Fskills\u002Fsupabase-postgres-best-practices\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":64,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":18},"01M77Y2W5H5YGSW7MYWEJ8HYXD","sentry","Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.","https:\u002F\u002Fgithub.com\u002FConcertoNotes\u002Fcodex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fofficial\u002Fsentry\u002Fskills\u002Fsentry\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FConcertoNotes\u002Fcodex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fofficial\u002Fsentry\u002Fskills\u002Fsentry\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":56,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"01M77Y06GV1DAME7PN9KBFHWRX","render-workflows","Sets up, develops, tests, and deploys Render Workflows. Covers first-time scaffolding (via CLI or manual), SDK installation (Python or TypeScript), task patterns (retries, subtasks, fan-out), local development, Dashboard deployment, and troubleshooting. Use when a user wants to set up Render Workflows for the first time, scaffold a workflow service, add or modify workflow tasks, test workflows locally, or deploy workflows to Render.","https:\u002F\u002Fgithub.com\u002FConcertoNotes\u002Fcodex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fofficial\u002Frender\u002Fskills\u002Frender-workflows\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":56,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M77Y01A6RJA8VYT7CZ2TVETF","render-web-services","Configures Render web services—port binding, TLS, health checks, custom domains, auto-deploy, PR previews, persistent disks, and deploy lifecycle. Use when the user needs to set up a web service, fix health check failures, add a custom domain, configure zero-downtime deploys, or troubleshoot port binding issues.","https:\u002F\u002Fgithub.com\u002FConcertoNotes\u002Fcodex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fofficial\u002Frender\u002Fskills\u002Frender-web-services\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":56,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M77XZW1AZ6B6NZTWWFVY72T3","render-static-sites","Deploys and configures static sites on Render's global CDN—build commands, publish paths, SPA routing, redirects, custom headers, and PR previews. Use when the user needs to deploy a static site, set up a React\u002FVue\u002FHugo\u002FGatsby frontend, configure SPA fallback routing, add redirect rules, customize response headers, or choose between a static site and a web service for their frontend. Trigger terms: static site, CDN, SPA, single-page app, React deploy, Vue deploy, Hugo, Gatsby, Docusaurus, Jekyll, staticPublishPath.","https:\u002F\u002Fgithub.com\u002FConcertoNotes\u002Fcodex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fofficial\u002Frender\u002Fskills\u002Frender-static-sites\u002FSKILL.md",[],[]]