[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77MMZC7G677D93M57CSZ32H":3,"skill-same:01M77MMZC7G677D93M57CSZ32H":60},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M77MMZC7G677D93M57CSZ32H","nagent",null,"Launch a new bb worker thread with the right project, model, worktree, and task brief. Use for nagent, launching a bb session, or a standalone bb agent. Covers thread creation; use bb-cli for managing existing threads.","davidondrej\u002Fskills","davidondrej","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F131768515?v=4","01M77MHARFKYVNT9FV22807T8F","David Ondrej","01M77MHASHNDV507F9NTVKR2CY",4310,"MIT","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fnagent\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: nagent\ndescription: Launch a new bb worker thread with the right project, model, worktree, and task brief. Use for nagent, launching a bb session, or a standalone bb agent. Covers thread creation; use bb-cli for managing existing threads.\n---\n\n# nagent\n\nRead this before `bb thread spawn`. Use `bb-cli` for other thread operations.\n\n## Defaults\n\nUse Codex `gpt-5.6-sol`, reasoning `high`, service tier `fast` (\"GPT 5.6 Sol High Fast\"). Use `xhigh` for larger refactors. The user's explicit choices override these defaults.\n\nFor a different requested model, use its catalog `defaultReasoningEffort` when unspecified, and enable fast only when asked. Do not infer a higher reasoning level from the model name.\n\nPrefer bare `bb`; `\"$BB_CLI\"` is also valid when set.\n\n## Look Up the Target\n\n```bash\nbb project list --json\nbb provider list --json\nbb provider models \u003Cprovider-id> --json\n```\n\n- **Project:** Match the name and confirm `sources[].path` is the requested repository. Always pass `--project`; never hardcode an ID.\n- **Provider:** Look it up. Common mappings are Cursor CLI → `acp-cursor`, Codex\u002FChatGPT subscription → `codex`, and Claude Code → `claude-code`. Grok via Cursor is not `acp-grok`, which is Grok Build.\n- **Model:** Use the catalog ID. Match both `displayName` and `supportedReasoningEfforts[].description`; model IDs, reasoning labels, and service tiers are separate.\n\nFor Cursor\u002FGrok or Codex Max naming traps, read [provider details](references\u002Fproviders.md). Verify examples against the current catalog; do not guess IDs or substitute a different provider.\n\n## Pi Agent: billing safety\n\n`--provider pi` selects the harness; the full `--model provider\u002Fmodel` selects the inference and billing route. ChatGPT subscription example:\n\n```bash\n--provider pi --model openai-codex\u002Fgpt-6-astra --reasoning-level xhigh\n```\n\nQuery Pi's catalog on the target `--machine` or `--environment`. `openai-codex` uses the ChatGPT subscription; OpenRouter and Vercel AI Gateway bill separately. Never substitute routes without the user's approval; stop if unavailable. After spawning, verify the full model ID and reasoning in the `client\u002Fturn\u002Frequested` execution metadata, not just the display name.\n\n## Permission Checks\n\nThe user's investigation\u002Fbuild workers default to `full`. A child cannot exceed the parent's permission mode, so verify the parent before requesting it and the child after spawning.\n\nRun the bundled script relative to this skill's directory:\n\n```bash\nscripts\u002Fpermission-mode.sh \"$BB_THREAD_ID\"\n```\n\nFor a `full` worker, this must print `full`. Otherwise, stop and report that the requested mode is unavailable under the parent's limits. Do not bypass those limits. If the user requests another mode, confirm the provider supports it.\n\nThe modes are `accept-edits` (sandbox, human-reviewed escalations), `auto` (sandbox, automatic review), and `full` (no sandbox). A read-only brief must forbid writes regardless of mode. For Cursor permission issues, use the provider-details reference.\n\n## Spawn\n\nUse the resolved IDs and chosen settings. This example shows the default worker's reasoning, tier, and permissions; replace them when the user requests different settings.\n\n```bash\nbb thread spawn --json \\\n  --project \u003Cproject-id> \\\n  --new-environment worktree \\\n  --provider \u003Cprovider-id> \\\n  --model \u003Cmodel-id> \\\n  --reasoning-level high \\\n  --service-tier fast \\\n  --permission-mode full \\\n  --title \"Short title\" \\\n  --prompt \"$(cat \u003C\u003C'EOF'\nObjective: ...\nConstraints: ...\nSkills and files: ...\nDeliverable: ...\nValidation: ...\nReport back: ...\nEOF\n)\"\n```\n\nAlways include `--json`, `--title`, and a complete prompt. The quoted heredoc preserves quotes in the brief.\n\n## Parent and Sidebar Placement\n\n- Omit parent flags for a standalone, top-level thread: \"not as your own subagent\".\n- Use `--parent-self` when this thread coordinates the worker or the job is its subtask.\n- Use `--parent-thread \u003Cid>` to nest under another thread. Never combine the two parent flags.\n\nDo not nest unrelated one-off work by default.\n\n## Worktree\n\nUse `--new-environment worktree` for a bb-managed worktree. Do not create one manually unless the user asks.\n\n- Worktrees start with tracked files. Include required untracked files such as `.env` through the repo's `.worktreeinclude`; setup may also use `.bb-env-setup.sh`. See `bb guide environments`.\n- Omit `--base-branch` for the project default; specify it only when needed.\n- Do not combine `--machine` with an existing `--environment` ID.\n- A null `environmentId` in the spawn response can mean the worktree is still being created.\n\n## Task Brief\n\n**Preserve the user’s scope**\n\n- Write a focused assignment preserving intent, constraints, and corrections. Never invent requirements, deliverables, permissions, or approval.\n- Model, machine, repository, and thread placement guide the launcher. Give each worker only its task and necessary context.\n- Before sending, remove copied conversation, launcher instructions, and unrelated assignments. Never prepend the full user prompt; quote exact wording only when explicitly requested.\n\nThe worker does not see this conversation. State the objective, constraints, relevant skills\u002Ffiles, deliverable, validation, and expected report. Name the skills it must read rather than assuming your context carries over.\n\nFor read-only jobs, explicitly say **no code changes, no Git writes, no database writes**. For implementation, specify the allowed scope and any Git or production restrictions. Ask for a concise report, including changed files and validation when relevant.\n\n## Verify and Report\n\n```bash\nscripts\u002Fpermission-mode.sh \u003Cchild-thread-id>\n```\n\nConfirm the child received the requested mode. If it differs or is unknown, report the mismatch rather than claiming a successful setup.\n\nReport the thread ID, title, project, provider\u002Fmodel\u002Freasoning\u002Ftier, worktree yes\u002Fno, and read-only versus implementation scope. Then stop. Do not dump the prompt, open\u002Ffocus the thread, poll, wait, or read work logs unless the user asks.\n\n## Blocked Workers and Lifecycle\n\nIf bb reports a blocker, inspect it with `bb thread interactions list \u003Cid> --json`. Resolve routine input within the brief, and approve an action with `bb thread interactions approve \u003CinteractionId> \u003Cid>` only when it is authorized and safe. Ask the user about destructive actions, production access, unclear decisions, or work outside the brief. Do not monitor just to look for blockers.\n\nUse `bb-cli` for lifecycle commands. Archive only when the user asks, then stop the thread to release its runtime. Never delete without an explicit request, and do not use hiding as a substitute for archiving.\n","# nagent\n\nRead this before `bb thread spawn`. Use `bb-cli` for other thread operations.\n\n## Defaults\n\nUse Codex `gpt-5.6-sol`, reasoning `high`, service tier `fast` (\"GPT 5.6 Sol High Fast\"). Use `xhigh` for larger refactors. The user's explicit choices override these defaults.\n\nFor a different requested model, use its catalog `defaultReasoningEffort` when unspecified, and enable fast only when asked. Do not infer a higher reasoning level from the model name.\n\nPrefer bare `bb`; `\"$BB_CLI\"` is also valid when set.\n\n## Look Up the Target\n\n```bash\nbb project list --json\nbb provider list --json\nbb provider models \u003Cprovider-id> --json\n```\n\n- **Project:** Match the name and confirm `sources[].path` is the requested repository. Always pass `--project`; never hardcode an ID.\n- **Provider:** Look it up. Common mappings are Cursor CLI → `acp-cursor`, Codex\u002FChatGPT subscription → `codex`, and Claude Code → `claude-code`. Grok via Cursor is not `acp-grok`, which is Grok Build.\n- **Model:** Use the catalog ID. Match both `displayName` and `supportedReasoningEfforts[].description`; model IDs, reasoning labels, and service tiers are separate.\n\nFor Cursor\u002FGrok or Codex Max naming traps, read [provider details](references\u002Fproviders.md). Verify examples against the current catalog; do not guess IDs or substitute a different provider.\n\n## Pi Agent: billing safety\n\n`--provider pi` selects the harness; the full `--model provider\u002Fmodel` selects the inference and billing route. ChatGPT subscription example:\n\n```bash\n--provider pi --model openai-codex\u002Fgpt-6-astra --reasoning-level xhigh\n```\n\nQuery Pi's catalog on the target `--machine` or `--environment`. `openai-codex` uses the ChatGPT subscription; OpenRouter and Vercel AI Gateway bill separately. Never substitute routes without the user's approval; stop if unavailable. After spawning, verify the full model ID and reasoning in the `client\u002Fturn\u002Frequested` execution metadata, not just the display name.\n\n## Permission Checks\n\nThe user's investigation\u002Fbuild workers default to `full`. A child cannot exceed the parent's permission mode, so verify the parent before requesting it and the child after spawning.\n\nRun the bundled script relative to this skill's directory:\n\n```bash\nscripts\u002Fpermission-mode.sh \"$BB_THREAD_ID\"\n```\n\nFor a `full` worker, this must print `full`. Otherwise, stop and report that the requested mode is unavailable under the parent's limits. Do not bypass those limits. If the user requests another mode, confirm the provider supports it.\n\nThe modes are `accept-edits` (sandbox, human-reviewed escalations), `auto` (sandbox, automatic review), and `full` (no sandbox). A read-only brief must forbid writes regardless of mode. For Cursor permission issues, use the provider-details reference.\n\n## Spawn\n\nUse the resolved IDs and chosen settings. This example shows the default worker's reasoning, tier, and permissions; replace them when the user requests different settings.\n\n```bash\nbb thread spawn --json \\\n  --project \u003Cproject-id> \\\n  --new-environment worktree \\\n  --provider \u003Cprovider-id> \\\n  --model \u003Cmodel-id> \\\n  --reasoning-level high \\\n  --service-tier fast \\\n  --permission-mode full \\\n  --title \"Short title\" \\\n  --prompt \"$(cat \u003C\u003C'EOF'\nObjective: ...\nConstraints: ...\nSkills and files: ...\nDeliverable: ...\nValidation: ...\nReport back: ...\nEOF\n)\"\n```\n\nAlways include `--json`, `--title`, and a complete prompt. The quoted heredoc preserves quotes in the brief.\n\n## Parent and Sidebar Placement\n\n- Omit parent flags for a standalone, top-level thread: \"not as your own subagent\".\n- Use `--parent-self` when this thread coordinates the worker or the job is its subtask.\n- Use `--parent-thread \u003Cid>` to nest under another thread. Never combine the two parent flags.\n\nDo not nest unrelated one-off work by default.\n\n## Worktree\n\nUse `--new-environment worktree` for a bb-managed worktree. Do not create one manually unless the user asks.\n\n- Worktrees start with tracked files. Include required untracked files such as `.env` through the repo's `.worktreeinclude`; setup may also use `.bb-env-setup.sh`. See `bb guide environments`.\n- Omit `--base-branch` for the project default; specify it only when needed.\n- Do not combine `--machine` with an existing `--environment` ID.\n- A null `environmentId` in the spawn response can mean the worktree is still being created.\n\n## Task Brief\n\n**Preserve the user’s scope**\n\n- Write a focused assignment preserving intent, constraints, and corrections. Never invent requirements, deliverables, permissions, or approval.\n- Model, machine, repository, and thread placement guide the launcher. Give each worker only its task and necessary context.\n- Before sending, remove copied conversation, launcher instructions, and unrelated assignments. Never prepend the full user prompt; quote exact wording only when explicitly requested.\n\nThe worker does not see this conversation. State the objective, constraints, relevant skills\u002Ffiles, deliverable, validation, and expected report. Name the skills it must read rather than assuming your context carries over.\n\nFor read-only jobs, explicitly say **no code changes, no Git writes, no database writes**. For implementation, specify the allowed scope and any Git or production restrictions. Ask for a concise report, including changed files and validation when relevant.\n\n## Verify and Report\n\n```bash\nscripts\u002Fpermission-mode.sh \u003Cchild-thread-id>\n```\n\nConfirm the child received the requested mode. If it differs or is unknown, report the mismatch rather than claiming a successful setup.\n\nReport the thread ID, title, project, provider\u002Fmodel\u002Freasoning\u002Ftier, worktree yes\u002Fno, and read-only versus implementation scope. Then stop. Do not dump the prompt, open\u002Ffocus the thread, poll, wait, or read work logs unless the user asks.\n\n## Blocked Workers and Lifecycle\n\nIf bb reports a blocker, inspect it with `bb thread interactions list \u003Cid> --json`. Resolve routine input within the brief, and approve an action with `bb thread interactions approve \u003CinteractionId> \u003Cid>` only when it is authorized and safe. Ask the user about destructive actions, production access, unclear decisions, or work outside the brief. Do not monitor just to look for blockers.\n\nUse `bb-cli` for lifecycle commands. Archive only when the user asks, then stop the thread to release its runtime. Never delete without an explicit request, and do not use hiding as a substitute for archiving.\n",{"name":5,"description":7},"main","a9d4ad810cf3c303fde23bdcd5fc86df7c57daf3","skills\u002Fnagent",626,"https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills","https:\u002F\u002Fwww.cloudroom.dev","https:\u002F\u002Fgithub.com\u002Fdavidondrej","https:\u002F\u002Fwww.cloudroom.dev\u002F","founder of Cloudroom","2026-11-14 10:00:36",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add davidondrej\u002Fskills --skill nagent",{"tool":40,"command":41},"bunx","bunx skills add davidondrej\u002Fskills --skill nagent",{"tool":43,"command":44},"pnpm","pnpm dlx skills add davidondrej\u002Fskills --skill nagent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fnagent\u002FSKILL.md",true,[48,54],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fproviders.md","REFERENCE","参考文档",1525,"https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fnagent\u002Freferences\u002Fproviders.md",{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"scripts\u002Fpermission-mode.sh","SCRIPT","脚本",629,"https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fnagent\u002Fscripts\u002Fpermission-mode.sh",[61,68,75,82,89,96],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M77MPMR6DE13EZFSMY76S6YB","varied-search","Research a topic across the web, GitHub, and X\u002FTwitter with DeepAPI and produce a concise Markdown report. Use for varied-search or requests to compare web coverage, relevant repositories, and social discussion.","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fvaried-search\u002FSKILL.md",[],[],{"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":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M77MPG5F9H2JBW4VFHBY1VSM","total-review","Run five independent max-effort reviews (Fable 5.1, Opus 5.5, GPT-6 Astra, GPT-6.1 Sol, Muse Wonder), merge their findings, and fix only what the user approves. Use for \u002Ftotal-review, or when the user or another agent asks for a total review.","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftotal-review\u002FSKILL.md",[],[],{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M77MP8XZJ42ZJZQV8C76B353","stop-overthinking","Manually-invoked skill that stops overthinking and forces a short, practical decision. Use only when the user explicitly invokes stop-overthinking.","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fstop-overthinking\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M77MP5EGQSNF1VS9SY8CK60Q","state","Manually-invoked skill that recaps what the current thread is doing and how far along it is. Use when the user says \"state\", \"where are we\", or \"what % are we done\".","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fstate\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M77MP2H479SWAP7687RAVG7T","setup-help","Guide setup one step at a time and show what remains. Use only when the user explicitly asks for it by name.","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fsetup-help\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M77MNZV9X8NPC9JZMWP8WAF8","self-archive","Archive the current Cloudroom thread and release its runtime. Use only when the user explicitly asks to self-archive, archive yourself, or archive this thread.","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fself-archive\u002FSKILL.md",[],[]]