Creator · davidondrej
Last updated · Sep 1, 2026
Launch a new bb worker thread with an explicit project, provider, model, reasoning effort, fast/default tier, worktree, and prompt. Use when the user says "launch a bb session", "bb subagent", "spawn a bb thread", "new worktree agent", or asks to run Grok/Codex/Cursor CLI in bb o
Creator · davidondrej
Last updated · Sep 1, 2026
Launch a new bb worker thread with an explicit project, provider, model, reasoning effort, fast/default tier, worktree, and prompt. Use when the user says "launch a bb session", "bb subagent", "spawn a bb thread", "new worktree agent", or asks to run Grok/Codex/Cursor CLI in bb o
Creator · davidondrej
Last updated · Sep 1, 2026
Launch a new bb worker thread with an explicit project, provider, model, reasoning effort, fast/default tier, worktree, and prompt. Use when the user says "launch a bb session", "bb subagent", "spawn a bb thread", "new worktree agent", or asks to run Grok/Codex/Cursor CLI in bb o
Creator · davidondrej
Last updated · Sep 1, 2026
Launch a new bb worker thread with an explicit project, provider, model, reasoning effort, fast/default tier, worktree, and prompt. Use when the user says "launch a bb session", "bb subagent", "spawn a bb thread", "new worktree agent", or asks to run Grok/Codex/Cursor CLI in bb o
Sandbox only
Install targets
Codex install prompt
Install the "bb-subagents" agent skill from https://github.com/davidondrej/skills/tree/main/skills/agent-orchestration/bb-subagents. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Launch a new bb worker thread with an explicit project, provider, model, reasoning effort, fast/default tier, worktree, and prompt. Use when the user says "launch a bb session", "bb subagent", "spawn a bb thread", "new worktree agent", or asks to run Grok/Codex/Cursor CLI in bb on a repo. Differentiator vs bb-cli: this is only the spawn recipe. Differentiator vs codex-subagent/launch-subagent: those are Codex CLI and Cursor Task tool, not bb threads. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {"event_id":"install_<unique-id>","skill_slug":"davidondrej-bb-subagents","task":"Install bb-subagents","agent":"codex","outcome":"success","install_used":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.Supply asset profile
Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills.
Scenario
Coding agents
I need a coding agent that can understand a repository, edit code, and review pull requests.
Agent fit
Claude Code + OpenAI Agents + Cursor
Codex, Claude Code, Cursor, CLI, or custom agents.
Install
Ready
npx skills add davidondrej/skills --skill bb-subagents
Maintenance
fresh
3d since push
Risk
Needs review
Dependency or permission surface needs review
GitHub quality
3.8K
83/100 Quality · 76/100 Trust
Coverage tags
Review notes
Dependency or permission surface needs review · Permission surface may require sandboxing
Agent adoption scorecard
These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.
Quality
StrongSolid option that is likely worth shortlisting for production workflows.
Trust
Sandbox onlyUseful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
Audit
Needs reviewA machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
OpenAgentSkill Trust Score v5
Run only in a sandbox and compare close alternatives before using it for real work.
Stars
3.8K GitHub stars
Repo activity
3.8K stars, 554 forks
Maintenance
3d since push
License
MIT
Install
npx skills add davidondrej/skills --skill bb-subagents
Install safety
Agent-readable metadata
Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.
Suited tasks
Suited agents
Install decision
Trust and risk
Outcome loop
Install command
npx skills add davidondrej/skills --skill bb-subagentsDo not use when
Alternative
168.6K Stars
npx skills add mattpocock/skills --skill code-review
Alternative
40.8K Stars
npx skills add appsmithorg/appsmith
Alternative
175.7K Stars
npx skills add mattpocock/skills --skill implement
Alternative
30.9K Stars
npx skills add vercel-labs/agent-skills --skill vercel-react-best-practices
Agent safety v2
Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
Test manually in an isolated workspace and compare against safer alternatives.
high
Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.
medium
Skill likely fetches remote pages, APIs, repositories, or external services.
medium
Skill may read or write project files, documents, generated artifacts, or local workspace state.
high
Skill metadata references credentials, tokens, environment variables, or secret-bearing workflows.
Agent resolve plan
The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.
Open JSON
/api/agent/resolve?task=Use%20bb-subagents%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve text
/api/agent/resolve?task=Use%20bb-subagents%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
Install handoff
/api/skills/davidondrej-bb-subagents/install
Agent should check
Copy prompt
Task: Use bb-subagents in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20bb-subagents%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/davidondrej-bb-subagents/install
Install command: npx skills add davidondrej/skills --skill bb-subagents
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent handoff
Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.
Install handoff
/api/skills/davidondrej-bb-subagents/install
LLM text format
/api/skills/davidondrej-bb-subagents/install?format=text
Find alternatives
/api/skills/search?q=bb-subagents&limit=3
Agent prompt
Use bb-subagents for this task. Review https://www.openagentskill.com/api/skills/davidondrej-bb-subagents/install, then install with: npx skills add davidondrej/skills --skill bb-subagentsRegistry metadata
This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.
Manifest
/api/registry/manifest/davidondrej-bb-subagents
LLM text
/api/registry/manifest/davidondrej-bb-subagents?format=text
Install alias
/api/registry/install/davidondrej-bb-subagents
Recommend
/api/registry/recommend?task=Use%20bb-subagents%20in%20an%20agent%20workflow&limit=3
Agent fit
Local desktop
Use-case tags
Platforms
Claude Code, OpenAI Agents, Cursor
Audit report
A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
Agent decision cockpit
Use this as a leading candidate, then validate the README and install path in your own agent stack.
Role in stack
Primary pick
Primary fit
Local desktop
Trust label
Production-ready
Install path
Command ready
Use when
Evidence
review first
Implementation path
Trust profile
Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
GitHub adoption
PASS3.8K GitHub stars
Stars/forks activity
PASS3.8K stars, 554 forks; issue activity unavailable in current metadata
Recent maintenance
PASS3d since push
License clarity
PASSMIT
Good signals
Review before install
Recommended action
Run only in a sandbox and compare close alternatives before using it for real work.
Quality profile
Solid option that is likely worth shortlisting for production workflows.
Workflow fit
Operate local tools
I need my agent to operate local files and desktop apps in a repeatable workflow.
Automate repeated work
I need my agent to automate a repeated workflow across tools and files.
Build and ship code
I need a coding agent that can understand a repository, edit code, and review pull requests.
Workflow fit
Turn skills into distribution
A workflow for turning newly indexed skills into SEO briefs, social drafts, comparison pages, and reusable publishing workflows.
Find, compare, and synthesize
A workflow for agents that gather sources, compare claims, summarize long material, and draft useful research briefs.
Inspect, patch, and verify code
A workflow for software agents that inspect repositories, review pull requests, generate tests, and turn findings into shippable patches.
Alternative shortlist
Similar skills that may fit this task.
Review a branch or diff against repository standards and the originating spec in two independent analysis passes.
Platform to build admin panels, internal tools, and dashboards. Integrates with 25+ databases and any API.
Implement work from an approved spec or ticket set, run focused and full tests, invoke code review, and commit the result to the current branch.
React and Next.js performance guidance for writing, reviewing, and refactoring production UI code.
--- name: bb-subagents description: 'Launch a new bb worker thread with an explicit project, provider, model, reasoning effort, fast/default tier, worktree, and prompt. Use when the user says "launch a bb session", "bb subagent", "spawn a bb thread", "new worktree agent", or asks to run Grok/Codex/Cursor CLI in bb on a repo. Differentiator vs bb-cli: this is only the spawn recipe. Differentiator vs codex-subagent/launch-subagent: those are Codex CLI and Cursor Task tool, not bb threads.' ---
# bb-subagents
Spawn a bb thread the way the user launches them. Read this before any `bb thread spawn`.
Use `bb-cli` for status, tell, wait, inspect, automations. This skill is spawn-only.
**Default worker:** Codex `gpt-5.6-sol`, `--reasoning-level high`, `--service-tier fast` ("GPT 5.6 Sol High Fast"); bump to `xhigh` for larger refactors. Use this unless the user requests otherwise.
## Hard rules
- Pass `--project` explicitly. The CLI does not infer it from the current thread. - Never guess provider or model IDs. Lookup, then spawn. - After spawn: do **not** `bb thread open`, `--split`, or focus the new thread unless the user asks. Just launch. Report the thread id. Stop. - Do **not** poll, `bb thread wait`, or read logs unless the user asks. - Prefer bare `bb`. If `BB_CLI` is set, `"$BB_CLI"` is fine.
## Recipe
```bash bb project list --json bb provider list --json bb provider models <provider-id> --json
bb thread spawn --json \ --project <project-id> \ --new-environment worktree \ --provider <provider-id> \ --model <model-id> \ --reasoning-level <level> \ --permission-mode full \ --title "Short title" \ --prompt "..." ```
Add `--service-tier fast` only when the user says **fast**.
## Parent / sidebar nest
`--parent-self` and `--parent-thread` are optional. Use them when it makes sense — not on every spawn.
`--parent-self` parents the new thread to the current thread (`BB_THREAD_ID`). The left sidebar then nests the child under this thread (indented, expandable), like a worker under a manager.
`--parent-thread <id>` parents it to a specific other thread. Do not combine it with `--parent-self`.
Omit both for a **root** thread — its own top-level sidebar row, not nested.
When it makes sense: this thread is coordinating the work, the user asked for a worker under this session, or the job is a clear subtask of this thread. Skip it for unrelated one-off work that should sit as its own top-level thread.
```bash # add when it makes sense — not required --parent-self ```
`environmentId` is often `null` in the spawn JSON. The worktree is still creating. That is fine.
## Lookup
**Project.** Match `name` (e.g. `DeepAPI`) in `bb project list --json`. Use that `id`. Confirm `sources[].path` is the repo the user named. Do not hardcode project IDs.
**Provider.** From `bb provider list --json`:
| User says | Provider id | |---|---| | Cursor CLI / Cursor subscription | `acp-cursor` | | Codex / Codex subscription / ChatGPT sub | `codex` | | Claude Code | `claude-code` |
Do not use `acp-grok` for "Grok via Cursor CLI". That is Grok Build, a different product.
**Model + reasoning.** From `bb provider models <id> --json`. Use the catalog `id`. Match the user's words to `displayName` **and** `supportedReasoningEfforts[].description`. Those two are not the same field.
If the user does not name a reasoning level, use that model's `defaultReasoningEffort` from the catalog. Do not pick extra high or max on your own. Example: Claude Code Fable 5 defaults to `high`.
## Known mappings (re-fetch if spawn rejects them)
### Cursor CLI — Grok 4.6 Extra High Fast
User: "Grok 4.6 extra high fast (via Cursor CLI subscription)"
```bash --provider acp-cursor \ --model cursor-grok-4.6-medium \ --reasoning-level xhigh \ --service-tier fast ```
Traps:
- The model id stays `cursor-grok-4.6-medium` even for Extra High. Extra High is a **reasoning** value, not a different model id. - On this catalog, `high` displays as **Fast**. `xhigh` displays as **Extra High**. - "Extra High Fast" = `xhigh` **plus** `--service-tier fast`. Fast-the-reasoning-label and Fast-the-service-tier are different flags. - Cursor ACP has no `auto` permission mode. Use `full` or `accept-edits`. - Do not pass Cursor Task-tool slugs like `cursor-grok-4.6-high-fast`. Those are not bb model ids.
### Codex — GPT 5.6 Sol Max
User: "GPT 5.6 Sol Max, via the Codex subscription"
```bash --provider codex \ --model gpt-5.6-sol \ --reasoning-level max ```
Traps:
- Use native `gpt-5.6-sol`, not `cursor/gpt-5.6-sol` (opencodex routed through Cursor). - Max is `--reasoning-level max`, not a model id suffix. - Codex supports `auto` permission mode. Still use `full` when the worker must hit prod, network, or leave the sandbox. - Pass `--service-tier fast` only if the user asks for fast on Codex too.
## Worktree
`--new-environment worktree` is the bb-managed worktree. Do not create a git worktree by hand unless the user says so.
- New worktrees get **tracked files only**. - Untracked files (`.env`) copy only if the repo has `.worktreeinclude`. - Optional: `--base-branch <branch>`. Omit to use the project's default. - Do not combine `--machine` with an existing `--environment` id.
For repos that must keep `.env` in worktrees, the repo needs `.worktreeinclude` plus optional `.bb-env-setup.sh`. Details: `bb guide environments`.
## Prompt
The worker starts blind. It does not see this chat. Write the full brief into `--prompt`.
Include:
1. **Objective** — one sentence. 2. **Constraints** — read-only vs implement; no git push; no prod writes. 3. **Skills / files to use** — name them. Skills do not carry over. Example: prod reads → `~/.claude/skills/read-prod-database/SKILL.md`. 4. **Deliverable** — what to return. 5. **Validation** — how it knows it is done. 6. **Report back** — concise report only, or diff + files changed.
Read-only jobs must say **no code changes, no git writes, no database writes** in the prompt, even if permission mode is `full`.
Use a heredoc so quotes survive:
```bash --prompt "$(cat <<'EOF' Objective: ... Constraints: READ ONLY. ... Deliverable: ... Report back: ... EOF )" ```
Always pass `--json` and `--title`.
## Permission mode
| Mode | Meaning | |---|---| | `accept-edits` | Sandbox on. User approves escalations. | | `auto` | Sandbox on. Provider auto-approves. Codex/Claude have this. Cursor ACP does not. | | `full` | No sandbox. Needed for prod DB, many network tools, and "just go". |
Default for the user's investigation/build workers: `full`, with the prompt forbidding writes when the job is read-only.
## After spawn
Tell the user, then stop:
- thread id - title - project name - provider + model + reasoning (+ fast if set) - worktree, yes/no - read-only vs implement
Do not dump the prompt. Do not open the thread. Do not wait for it.
## Archive (only when the user asks)
Do not auto-archive after spawn.
```bash bb thread archive <id> --json bb thread stop <id> ```
Archive first, then stop. Archive also archives child threads. Stop frees the agent runtime; the thread history stays.
```bash bb thread unarchive <id> --json bb thread list --archived ```
Do not use `bb thread delete` unless the user wants it gone forever. Do not use `--visibility hidden` as a substitute for archive. Hidden is sidebar-only; archive is the lifecycle close-out.
Bulk, one worktree/environment: `bb environment archive-threads <environment-id>`.
Source provenance
Decision snapshot
3,828 GitHub stars
Audit
Install and adoption review
Agent-proven evidence
Outcome reports after resolve, review, install, and one narrow run.
No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.
Install
Free and open source. Review the report before installing into production agents.
Growth loop
Scenario-led draft for bb-subagents, ready for a manual X post.
A practical pick for a repeatable workflow: bb-subagents: Launch a new bb worker thread with an explicit project, provider, model, reasoning effort, fast/default tier, worktree, and... 3.8K stars https://www.openagentskill.com/skills/davidondrej-bb-subagents?ref=x
Listing + install path for bb-subagents: https://www.openagentskill.com/skills/davidondrej-bb-subagents?ref=x Install: npx skills add davidondrej/skills --skill bb-subagents
Listing source
This listing was indexed from public sources and is not marked official until a maintainer claim is approved.
Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.
Claim this skillOwner claim
This Registry indexed listing is attributed to davidondrej but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.
Creator backlink kit
Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.
[](https://www.openagentskill.com/skills/davidondrej-bb-subagents?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/davidondrej-bb-subagents?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/davidondrej-bb-subagents/audit)
[](https://www.openagentskill.com/skills/davidondrej-bb-subagents?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)davidondrej
@davidondrej
Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.
Sandbox only
Code Review
Review a branch or diff against repository standards and the originating spec in two independent analysis passes.
168.6K StarsAppsmith
Platform to build admin panels, internal tools, and dashboards. Integrates with 25+ databases and any API.
40.8K StarsImplement
Implement work from an approved spec or ticket set, run focused and full tests, invoke code review, and commit the result to the current branch.
175.7K StarsVercel React Best Practices
React and Next.js performance guidance for writing, reviewing, and refactoring production UI code.
30.9K StarsSandbox only
Install targets
Codex install prompt
Install the "bb-subagents" agent skill from https://github.com/davidondrej/skills/tree/main/skills/agent-orchestration/bb-subagents. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Launch a new bb worker thread with an explicit project, provider, model, reasoning effort, fast/default tier, worktree, and prompt. Use when the user says "launch a bb session", "bb subagent", "spawn a bb thread", "new worktree agent", or asks to run Grok/Codex/Cursor CLI in bb on a repo. Differentiator vs bb-cli: this is only the spawn recipe. Differentiator vs codex-subagent/launch-subagent: those are Codex CLI and Cursor Task tool, not bb threads. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {"event_id":"install_<unique-id>","skill_slug":"davidondrej-bb-subagents","task":"Install bb-subagents","agent":"codex","outcome":"success","install_used":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.Supply asset profile
Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills.
Scenario
Coding agents
I need a coding agent that can understand a repository, edit code, and review pull requests.
Agent fit
Claude Code + OpenAI Agents + Cursor
Codex, Claude Code, Cursor, CLI, or custom agents.
Install
Ready
npx skills add davidondrej/skills --skill bb-subagents
Maintenance
fresh
3d since push
Risk
Needs review
Dependency or permission surface needs review
GitHub quality
3.8K
83/100 Quality · 76/100 Trust
Coverage tags
Review notes
Dependency or permission surface needs review · Permission surface may require sandboxing
Agent adoption scorecard
These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.
Quality
StrongSolid option that is likely worth shortlisting for production workflows.
Trust
Sandbox onlyUseful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
Audit
Needs reviewA machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
OpenAgentSkill Trust Score v5
Run only in a sandbox and compare close alternatives before using it for real work.
Stars
3.8K GitHub stars
Repo activity
3.8K stars, 554 forks
Maintenance
3d since push
License
MIT
Install
npx skills add davidondrej/skills --skill bb-subagents
Install safety
Agent-readable metadata
Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.
Suited tasks
Suited agents
Install decision
Trust and risk
Outcome loop
Install command
npx skills add davidondrej/skills --skill bb-subagentsDo not use when
Alternative
168.6K Stars
npx skills add mattpocock/skills --skill code-review
Alternative
40.8K Stars
npx skills add appsmithorg/appsmith
Alternative
175.7K Stars
npx skills add mattpocock/skills --skill implement
Alternative
30.9K Stars
npx skills add vercel-labs/agent-skills --skill vercel-react-best-practices
Agent safety v2
Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
Test manually in an isolated workspace and compare against safer alternatives.
high
Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.
medium
Skill likely fetches remote pages, APIs, repositories, or external services.
medium
Skill may read or write project files, documents, generated artifacts, or local workspace state.
high
Skill metadata references credentials, tokens, environment variables, or secret-bearing workflows.
Agent resolve plan
The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.
Open JSON
/api/agent/resolve?task=Use%20bb-subagents%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve text
/api/agent/resolve?task=Use%20bb-subagents%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
Install handoff
/api/skills/davidondrej-bb-subagents/install
Agent should check
Copy prompt
Task: Use bb-subagents in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20bb-subagents%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/davidondrej-bb-subagents/install
Install command: npx skills add davidondrej/skills --skill bb-subagents
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent handoff
Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.
Install handoff
/api/skills/davidondrej-bb-subagents/install
LLM text format
/api/skills/davidondrej-bb-subagents/install?format=text
Find alternatives
/api/skills/search?q=bb-subagents&limit=3
Agent prompt
Use bb-subagents for this task. Review https://www.openagentskill.com/api/skills/davidondrej-bb-subagents/install, then install with: npx skills add davidondrej/skills --skill bb-subagentsRegistry metadata
This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.
Manifest
/api/registry/manifest/davidondrej-bb-subagents
LLM text
/api/registry/manifest/davidondrej-bb-subagents?format=text
Install alias
/api/registry/install/davidondrej-bb-subagents
Recommend
/api/registry/recommend?task=Use%20bb-subagents%20in%20an%20agent%20workflow&limit=3
Agent fit
Local desktop
Use-case tags
Platforms
Claude Code, OpenAI Agents, Cursor
Audit report
A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
Agent decision cockpit
Use this as a leading candidate, then validate the README and install path in your own agent stack.
Role in stack
Primary pick
Primary fit
Local desktop
Trust label
Production-ready
Install path
Command ready
Use when
Evidence
review first
Implementation path
Trust profile
Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
GitHub adoption
PASS3.8K GitHub stars
Stars/forks activity
PASS3.8K stars, 554 forks; issue activity unavailable in current metadata
Recent maintenance
PASS3d since push
License clarity
PASSMIT
Good signals
Review before install
Recommended action
Run only in a sandbox and compare close alternatives before using it for real work.
Quality profile
Solid option that is likely worth shortlisting for production workflows.
Workflow fit
Operate local tools
I need my agent to operate local files and desktop apps in a repeatable workflow.
Automate repeated work
I need my agent to automate a repeated workflow across tools and files.
Build and ship code
I need a coding agent that can understand a repository, edit code, and review pull requests.
Workflow fit
Turn skills into distribution
A workflow for turning newly indexed skills into SEO briefs, social drafts, comparison pages, and reusable publishing workflows.
Find, compare, and synthesize
A workflow for agents that gather sources, compare claims, summarize long material, and draft useful research briefs.
Inspect, patch, and verify code
A workflow for software agents that inspect repositories, review pull requests, generate tests, and turn findings into shippable patches.
Alternative shortlist
Similar skills that may fit this task.
Review a branch or diff against repository standards and the originating spec in two independent analysis passes.
Platform to build admin panels, internal tools, and dashboards. Integrates with 25+ databases and any API.
Implement work from an approved spec or ticket set, run focused and full tests, invoke code review, and commit the result to the current branch.
React and Next.js performance guidance for writing, reviewing, and refactoring production UI code.
--- name: bb-subagents description: 'Launch a new bb worker thread with an explicit project, provider, model, reasoning effort, fast/default tier, worktree, and prompt. Use when the user says "launch a bb session", "bb subagent", "spawn a bb thread", "new worktree agent", or asks to run Grok/Codex/Cursor CLI in bb on a repo. Differentiator vs bb-cli: this is only the spawn recipe. Differentiator vs codex-subagent/launch-subagent: those are Codex CLI and Cursor Task tool, not bb threads.' ---
# bb-subagents
Spawn a bb thread the way the user launches them. Read this before any `bb thread spawn`.
Use `bb-cli` for status, tell, wait, inspect, automations. This skill is spawn-only.
**Default worker:** Codex `gpt-5.6-sol`, `--reasoning-level high`, `--service-tier fast` ("GPT 5.6 Sol High Fast"); bump to `xhigh` for larger refactors. Use this unless the user requests otherwise.
## Hard rules
- Pass `--project` explicitly. The CLI does not infer it from the current thread. - Never guess provider or model IDs. Lookup, then spawn. - After spawn: do **not** `bb thread open`, `--split`, or focus the new thread unless the user asks. Just launch. Report the thread id. Stop. - Do **not** poll, `bb thread wait`, or read logs unless the user asks. - Prefer bare `bb`. If `BB_CLI` is set, `"$BB_CLI"` is fine.
## Recipe
```bash bb project list --json bb provider list --json bb provider models <provider-id> --json
bb thread spawn --json \ --project <project-id> \ --new-environment worktree \ --provider <provider-id> \ --model <model-id> \ --reasoning-level <level> \ --permission-mode full \ --title "Short title" \ --prompt "..." ```
Add `--service-tier fast` only when the user says **fast**.
## Parent / sidebar nest
`--parent-self` and `--parent-thread` are optional. Use them when it makes sense — not on every spawn.
`--parent-self` parents the new thread to the current thread (`BB_THREAD_ID`). The left sidebar then nests the child under this thread (indented, expandable), like a worker under a manager.
`--parent-thread <id>` parents it to a specific other thread. Do not combine it with `--parent-self`.
Omit both for a **root** thread — its own top-level sidebar row, not nested.
When it makes sense: this thread is coordinating the work, the user asked for a worker under this session, or the job is a clear subtask of this thread. Skip it for unrelated one-off work that should sit as its own top-level thread.
```bash # add when it makes sense — not required --parent-self ```
`environmentId` is often `null` in the spawn JSON. The worktree is still creating. That is fine.
## Lookup
**Project.** Match `name` (e.g. `DeepAPI`) in `bb project list --json`. Use that `id`. Confirm `sources[].path` is the repo the user named. Do not hardcode project IDs.
**Provider.** From `bb provider list --json`:
| User says | Provider id | |---|---| | Cursor CLI / Cursor subscription | `acp-cursor` | | Codex / Codex subscription / ChatGPT sub | `codex` | | Claude Code | `claude-code` |
Do not use `acp-grok` for "Grok via Cursor CLI". That is Grok Build, a different product.
**Model + reasoning.** From `bb provider models <id> --json`. Use the catalog `id`. Match the user's words to `displayName` **and** `supportedReasoningEfforts[].description`. Those two are not the same field.
If the user does not name a reasoning level, use that model's `defaultReasoningEffort` from the catalog. Do not pick extra high or max on your own. Example: Claude Code Fable 5 defaults to `high`.
## Known mappings (re-fetch if spawn rejects them)
### Cursor CLI — Grok 4.6 Extra High Fast
User: "Grok 4.6 extra high fast (via Cursor CLI subscription)"
```bash --provider acp-cursor \ --model cursor-grok-4.6-medium \ --reasoning-level xhigh \ --service-tier fast ```
Traps:
- The model id stays `cursor-grok-4.6-medium` even for Extra High. Extra High is a **reasoning** value, not a different model id. - On this catalog, `high` displays as **Fast**. `xhigh` displays as **Extra High**. - "Extra High Fast" = `xhigh` **plus** `--service-tier fast`. Fast-the-reasoning-label and Fast-the-service-tier are different flags. - Cursor ACP has no `auto` permission mode. Use `full` or `accept-edits`. - Do not pass Cursor Task-tool slugs like `cursor-grok-4.6-high-fast`. Those are not bb model ids.
### Codex — GPT 5.6 Sol Max
User: "GPT 5.6 Sol Max, via the Codex subscription"
```bash --provider codex \ --model gpt-5.6-sol \ --reasoning-level max ```
Traps:
- Use native `gpt-5.6-sol`, not `cursor/gpt-5.6-sol` (opencodex routed through Cursor). - Max is `--reasoning-level max`, not a model id suffix. - Codex supports `auto` permission mode. Still use `full` when the worker must hit prod, network, or leave the sandbox. - Pass `--service-tier fast` only if the user asks for fast on Codex too.
## Worktree
`--new-environment worktree` is the bb-managed worktree. Do not create a git worktree by hand unless the user says so.
- New worktrees get **tracked files only**. - Untracked files (`.env`) copy only if the repo has `.worktreeinclude`. - Optional: `--base-branch <branch>`. Omit to use the project's default. - Do not combine `--machine` with an existing `--environment` id.
For repos that must keep `.env` in worktrees, the repo needs `.worktreeinclude` plus optional `.bb-env-setup.sh`. Details: `bb guide environments`.
## Prompt
The worker starts blind. It does not see this chat. Write the full brief into `--prompt`.
Include:
1. **Objective** — one sentence. 2. **Constraints** — read-only vs implement; no git push; no prod writes. 3. **Skills / files to use** — name them. Skills do not carry over. Example: prod reads → `~/.claude/skills/read-prod-database/SKILL.md`. 4. **Deliverable** — what to return. 5. **Validation** — how it knows it is done. 6. **Report back** — concise report only, or diff + files changed.
Read-only jobs must say **no code changes, no git writes, no database writes** in the prompt, even if permission mode is `full`.
Use a heredoc so quotes survive:
```bash --prompt "$(cat <<'EOF' Objective: ... Constraints: READ ONLY. ... Deliverable: ... Report back: ... EOF )" ```
Always pass `--json` and `--title`.
## Permission mode
| Mode | Meaning | |---|---| | `accept-edits` | Sandbox on. User approves escalations. | | `auto` | Sandbox on. Provider auto-approves. Codex/Claude have this. Cursor ACP does not. | | `full` | No sandbox. Needed for prod DB, many network tools, and "just go". |
Default for the user's investigation/build workers: `full`, with the prompt forbidding writes when the job is read-only.
## After spawn
Tell the user, then stop:
- thread id - title - project name - provider + model + reasoning (+ fast if set) - worktree, yes/no - read-only vs implement
Do not dump the prompt. Do not open the thread. Do not wait for it.
## Archive (only when the user asks)
Do not auto-archive after spawn.
```bash bb thread archive <id> --json bb thread stop <id> ```
Archive first, then stop. Archive also archives child threads. Stop frees the agent runtime; the thread history stays.
```bash bb thread unarchive <id> --json bb thread list --archived ```
Do not use `bb thread delete` unless the user wants it gone forever. Do not use `--visibility hidden` as a substitute for archive. Hidden is sidebar-only; archive is the lifecycle close-out.
Bulk, one worktree/environment: `bb environment archive-threads <environment-id>`.
Source provenance
Decision snapshot
3,828 GitHub stars
Audit
Install and adoption review
Agent-proven evidence
Outcome reports after resolve, review, install, and one narrow run.
No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.
Install
Free and open source. Review the report before installing into production agents.
Growth loop
Scenario-led draft for bb-subagents, ready for a manual X post.
A practical pick for a repeatable workflow: bb-subagents: Launch a new bb worker thread with an explicit project, provider, model, reasoning effort, fast/default tier, worktree, and... 3.8K stars https://www.openagentskill.com/skills/davidondrej-bb-subagents?ref=x
Listing + install path for bb-subagents: https://www.openagentskill.com/skills/davidondrej-bb-subagents?ref=x Install: npx skills add davidondrej/skills --skill bb-subagents
Listing source
This listing was indexed from public sources and is not marked official until a maintainer claim is approved.
Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.
Claim this skillOwner claim
This Registry indexed listing is attributed to davidondrej but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.
Creator backlink kit
Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.
[](https://www.openagentskill.com/skills/davidondrej-bb-subagents?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/davidondrej-bb-subagents?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/davidondrej-bb-subagents/audit)
[](https://www.openagentskill.com/skills/davidondrej-bb-subagents?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)davidondrej
@davidondrej
Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.
Sandbox only
Code Review
Review a branch or diff against repository standards and the originating spec in two independent analysis passes.
168.6K StarsAppsmith
Platform to build admin panels, internal tools, and dashboards. Integrates with 25+ databases and any API.
40.8K StarsImplement
Implement work from an approved spec or ticket set, run focused and full tests, invoke code review, and commit the result to the current branch.
175.7K StarsVercel React Best Practices
React and Next.js performance guidance for writing, reviewing, and refactoring production UI code.
30.9K StarsSandbox only
Install targets
Codex install prompt
Install the "bb-subagents" agent skill from https://github.com/davidondrej/skills/tree/main/skills/agent-orchestration/bb-subagents. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Launch a new bb worker thread with an explicit project, provider, model, reasoning effort, fast/default tier, worktree, and prompt. Use when the user says "launch a bb session", "bb subagent", "spawn a bb thread", "new worktree agent", or asks to run Grok/Codex/Cursor CLI in bb on a repo. Differentiator vs bb-cli: this is only the spawn recipe. Differentiator vs codex-subagent/launch-subagent: those are Codex CLI and Cursor Task tool, not bb threads. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {"event_id":"install_<unique-id>","skill_slug":"davidondrej-bb-subagents","task":"Install bb-subagents","agent":"codex","outcome":"success","install_used":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.Supply asset profile
Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills.
Scenario
Coding agents
I need a coding agent that can understand a repository, edit code, and review pull requests.
Agent fit
Claude Code + OpenAI Agents + Cursor
Codex, Claude Code, Cursor, CLI, or custom agents.
Install
Ready
npx skills add davidondrej/skills --skill bb-subagents
Maintenance
fresh
3d since push
Risk
Needs review
Dependency or permission surface needs review
GitHub quality
3.8K
83/100 Quality · 76/100 Trust
Coverage tags
Review notes
Dependency or permission surface needs review · Permission surface may require sandboxing
Agent adoption scorecard
These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.
Quality
StrongSolid option that is likely worth shortlisting for production workflows.
Trust
Sandbox onlyUseful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
Audit
Needs reviewA machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
OpenAgentSkill Trust Score v5
Run only in a sandbox and compare close alternatives before using it for real work.
Stars
3.8K GitHub stars
Repo activity
3.8K stars, 554 forks
Maintenance
3d since push
License
MIT
Install
npx skills add davidondrej/skills --skill bb-subagents
Install safety
Agent-readable metadata
Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.
Suited tasks
Suited agents
Install decision
Trust and risk
Outcome loop
Install command
npx skills add davidondrej/skills --skill bb-subagentsDo not use when
Alternative
168.6K Stars
npx skills add mattpocock/skills --skill code-review
Alternative
40.8K Stars
npx skills add appsmithorg/appsmith
Alternative
175.7K Stars
npx skills add mattpocock/skills --skill implement
Alternative
30.9K Stars
npx skills add vercel-labs/agent-skills --skill vercel-react-best-practices
Agent safety v2
Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
Test manually in an isolated workspace and compare against safer alternatives.
high
Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.
medium
Skill likely fetches remote pages, APIs, repositories, or external services.
medium
Skill may read or write project files, documents, generated artifacts, or local workspace state.
high
Skill metadata references credentials, tokens, environment variables, or secret-bearing workflows.
Agent resolve plan
The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.
Open JSON
/api/agent/resolve?task=Use%20bb-subagents%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve text
/api/agent/resolve?task=Use%20bb-subagents%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
Install handoff
/api/skills/davidondrej-bb-subagents/install
Agent should check
Copy prompt
Task: Use bb-subagents in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20bb-subagents%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/davidondrej-bb-subagents/install
Install command: npx skills add davidondrej/skills --skill bb-subagents
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent handoff
Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.
Install handoff
/api/skills/davidondrej-bb-subagents/install
LLM text format
/api/skills/davidondrej-bb-subagents/install?format=text
Find alternatives
/api/skills/search?q=bb-subagents&limit=3
Agent prompt
Use bb-subagents for this task. Review https://www.openagentskill.com/api/skills/davidondrej-bb-subagents/install, then install with: npx skills add davidondrej/skills --skill bb-subagentsRegistry metadata
This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.
Manifest
/api/registry/manifest/davidondrej-bb-subagents
LLM text
/api/registry/manifest/davidondrej-bb-subagents?format=text
Install alias
/api/registry/install/davidondrej-bb-subagents
Recommend
/api/registry/recommend?task=Use%20bb-subagents%20in%20an%20agent%20workflow&limit=3
Agent fit
Local desktop
Use-case tags
Platforms
Claude Code, OpenAI Agents, Cursor
Audit report
A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
Agent decision cockpit
Use this as a leading candidate, then validate the README and install path in your own agent stack.
Role in stack
Primary pick
Primary fit
Local desktop
Trust label
Production-ready
Install path
Command ready
Use when
Evidence
review first
Implementation path
Trust profile
Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
GitHub adoption
PASS3.8K GitHub stars
Stars/forks activity
PASS3.8K stars, 554 forks; issue activity unavailable in current metadata
Recent maintenance
PASS3d since push
License clarity
PASSMIT
Good signals
Review before install
Recommended action
Run only in a sandbox and compare close alternatives before using it for real work.
Quality profile
Solid option that is likely worth shortlisting for production workflows.
Workflow fit
Operate local tools
I need my agent to operate local files and desktop apps in a repeatable workflow.
Automate repeated work
I need my agent to automate a repeated workflow across tools and files.
Build and ship code
I need a coding agent that can understand a repository, edit code, and review pull requests.
Workflow fit
Turn skills into distribution
A workflow for turning newly indexed skills into SEO briefs, social drafts, comparison pages, and reusable publishing workflows.
Find, compare, and synthesize
A workflow for agents that gather sources, compare claims, summarize long material, and draft useful research briefs.
Inspect, patch, and verify code
A workflow for software agents that inspect repositories, review pull requests, generate tests, and turn findings into shippable patches.
Alternative shortlist
Similar skills that may fit this task.
Review a branch or diff against repository standards and the originating spec in two independent analysis passes.
Platform to build admin panels, internal tools, and dashboards. Integrates with 25+ databases and any API.
Implement work from an approved spec or ticket set, run focused and full tests, invoke code review, and commit the result to the current branch.
React and Next.js performance guidance for writing, reviewing, and refactoring production UI code.
--- name: bb-subagents description: 'Launch a new bb worker thread with an explicit project, provider, model, reasoning effort, fast/default tier, worktree, and prompt. Use when the user says "launch a bb session", "bb subagent", "spawn a bb thread", "new worktree agent", or asks to run Grok/Codex/Cursor CLI in bb on a repo. Differentiator vs bb-cli: this is only the spawn recipe. Differentiator vs codex-subagent/launch-subagent: those are Codex CLI and Cursor Task tool, not bb threads.' ---
# bb-subagents
Spawn a bb thread the way the user launches them. Read this before any `bb thread spawn`.
Use `bb-cli` for status, tell, wait, inspect, automations. This skill is spawn-only.
**Default worker:** Codex `gpt-5.6-sol`, `--reasoning-level high`, `--service-tier fast` ("GPT 5.6 Sol High Fast"); bump to `xhigh` for larger refactors. Use this unless the user requests otherwise.
## Hard rules
- Pass `--project` explicitly. The CLI does not infer it from the current thread. - Never guess provider or model IDs. Lookup, then spawn. - After spawn: do **not** `bb thread open`, `--split`, or focus the new thread unless the user asks. Just launch. Report the thread id. Stop. - Do **not** poll, `bb thread wait`, or read logs unless the user asks. - Prefer bare `bb`. If `BB_CLI` is set, `"$BB_CLI"` is fine.
## Recipe
```bash bb project list --json bb provider list --json bb provider models <provider-id> --json
bb thread spawn --json \ --project <project-id> \ --new-environment worktree \ --provider <provider-id> \ --model <model-id> \ --reasoning-level <level> \ --permission-mode full \ --title "Short title" \ --prompt "..." ```
Add `--service-tier fast` only when the user says **fast**.
## Parent / sidebar nest
`--parent-self` and `--parent-thread` are optional. Use them when it makes sense — not on every spawn.
`--parent-self` parents the new thread to the current thread (`BB_THREAD_ID`). The left sidebar then nests the child under this thread (indented, expandable), like a worker under a manager.
`--parent-thread <id>` parents it to a specific other thread. Do not combine it with `--parent-self`.
Omit both for a **root** thread — its own top-level sidebar row, not nested.
When it makes sense: this thread is coordinating the work, the user asked for a worker under this session, or the job is a clear subtask of this thread. Skip it for unrelated one-off work that should sit as its own top-level thread.
```bash # add when it makes sense — not required --parent-self ```
`environmentId` is often `null` in the spawn JSON. The worktree is still creating. That is fine.
## Lookup
**Project.** Match `name` (e.g. `DeepAPI`) in `bb project list --json`. Use that `id`. Confirm `sources[].path` is the repo the user named. Do not hardcode project IDs.
**Provider.** From `bb provider list --json`:
| User says | Provider id | |---|---| | Cursor CLI / Cursor subscription | `acp-cursor` | | Codex / Codex subscription / ChatGPT sub | `codex` | | Claude Code | `claude-code` |
Do not use `acp-grok` for "Grok via Cursor CLI". That is Grok Build, a different product.
**Model + reasoning.** From `bb provider models <id> --json`. Use the catalog `id`. Match the user's words to `displayName` **and** `supportedReasoningEfforts[].description`. Those two are not the same field.
If the user does not name a reasoning level, use that model's `defaultReasoningEffort` from the catalog. Do not pick extra high or max on your own. Example: Claude Code Fable 5 defaults to `high`.
## Known mappings (re-fetch if spawn rejects them)
### Cursor CLI — Grok 4.6 Extra High Fast
User: "Grok 4.6 extra high fast (via Cursor CLI subscription)"
```bash --provider acp-cursor \ --model cursor-grok-4.6-medium \ --reasoning-level xhigh \ --service-tier fast ```
Traps:
- The model id stays `cursor-grok-4.6-medium` even for Extra High. Extra High is a **reasoning** value, not a different model id. - On this catalog, `high` displays as **Fast**. `xhigh` displays as **Extra High**. - "Extra High Fast" = `xhigh` **plus** `--service-tier fast`. Fast-the-reasoning-label and Fast-the-service-tier are different flags. - Cursor ACP has no `auto` permission mode. Use `full` or `accept-edits`. - Do not pass Cursor Task-tool slugs like `cursor-grok-4.6-high-fast`. Those are not bb model ids.
### Codex — GPT 5.6 Sol Max
User: "GPT 5.6 Sol Max, via the Codex subscription"
```bash --provider codex \ --model gpt-5.6-sol \ --reasoning-level max ```
Traps:
- Use native `gpt-5.6-sol`, not `cursor/gpt-5.6-sol` (opencodex routed through Cursor). - Max is `--reasoning-level max`, not a model id suffix. - Codex supports `auto` permission mode. Still use `full` when the worker must hit prod, network, or leave the sandbox. - Pass `--service-tier fast` only if the user asks for fast on Codex too.
## Worktree
`--new-environment worktree` is the bb-managed worktree. Do not create a git worktree by hand unless the user says so.
- New worktrees get **tracked files only**. - Untracked files (`.env`) copy only if the repo has `.worktreeinclude`. - Optional: `--base-branch <branch>`. Omit to use the project's default. - Do not combine `--machine` with an existing `--environment` id.
For repos that must keep `.env` in worktrees, the repo needs `.worktreeinclude` plus optional `.bb-env-setup.sh`. Details: `bb guide environments`.
## Prompt
The worker starts blind. It does not see this chat. Write the full brief into `--prompt`.
Include:
1. **Objective** — one sentence. 2. **Constraints** — read-only vs implement; no git push; no prod writes. 3. **Skills / files to use** — name them. Skills do not carry over. Example: prod reads → `~/.claude/skills/read-prod-database/SKILL.md`. 4. **Deliverable** — what to return. 5. **Validation** — how it knows it is done. 6. **Report back** — concise report only, or diff + files changed.
Read-only jobs must say **no code changes, no git writes, no database writes** in the prompt, even if permission mode is `full`.
Use a heredoc so quotes survive:
```bash --prompt "$(cat <<'EOF' Objective: ... Constraints: READ ONLY. ... Deliverable: ... Report back: ... EOF )" ```
Always pass `--json` and `--title`.
## Permission mode
| Mode | Meaning | |---|---| | `accept-edits` | Sandbox on. User approves escalations. | | `auto` | Sandbox on. Provider auto-approves. Codex/Claude have this. Cursor ACP does not. | | `full` | No sandbox. Needed for prod DB, many network tools, and "just go". |
Default for the user's investigation/build workers: `full`, with the prompt forbidding writes when the job is read-only.
## After spawn
Tell the user, then stop:
- thread id - title - project name - provider + model + reasoning (+ fast if set) - worktree, yes/no - read-only vs implement
Do not dump the prompt. Do not open the thread. Do not wait for it.
## Archive (only when the user asks)
Do not auto-archive after spawn.
```bash bb thread archive <id> --json bb thread stop <id> ```
Archive first, then stop. Archive also archives child threads. Stop frees the agent runtime; the thread history stays.
```bash bb thread unarchive <id> --json bb thread list --archived ```
Do not use `bb thread delete` unless the user wants it gone forever. Do not use `--visibility hidden` as a substitute for archive. Hidden is sidebar-only; archive is the lifecycle close-out.
Bulk, one worktree/environment: `bb environment archive-threads <environment-id>`.
Source provenance
Decision snapshot
3,828 GitHub stars
Audit
Install and adoption review
Agent-proven evidence
Outcome reports after resolve, review, install, and one narrow run.
No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.
Install
Free and open source. Review the report before installing into production agents.
Growth loop
Scenario-led draft for bb-subagents, ready for a manual X post.
A practical pick for a repeatable workflow: bb-subagents: Launch a new bb worker thread with an explicit project, provider, model, reasoning effort, fast/default tier, worktree, and... 3.8K stars https://www.openagentskill.com/skills/davidondrej-bb-subagents?ref=x
Listing + install path for bb-subagents: https://www.openagentskill.com/skills/davidondrej-bb-subagents?ref=x Install: npx skills add davidondrej/skills --skill bb-subagents
Listing source
This listing was indexed from public sources and is not marked official until a maintainer claim is approved.
Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.
Claim this skillOwner claim
This Registry indexed listing is attributed to davidondrej but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.
Creator backlink kit
Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.
[](https://www.openagentskill.com/skills/davidondrej-bb-subagents?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/davidondrej-bb-subagents?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/davidondrej-bb-subagents/audit)
[](https://www.openagentskill.com/skills/davidondrej-bb-subagents?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)davidondrej
@davidondrej
Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.
Sandbox only
Code Review
Review a branch or diff against repository standards and the originating spec in two independent analysis passes.
168.6K StarsAppsmith
Platform to build admin panels, internal tools, and dashboards. Integrates with 25+ databases and any API.
40.8K StarsImplement
Implement work from an approved spec or ticket set, run focused and full tests, invoke code review, and commit the result to the current branch.
175.7K StarsVercel React Best Practices
React and Next.js performance guidance for writing, reviewing, and refactoring production UI code.
30.9K StarsSandbox only
Install targets
Codex install prompt
Install the "bb-subagents" agent skill from https://github.com/davidondrej/skills/tree/main/skills/agent-orchestration/bb-subagents. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Launch a new bb worker thread with an explicit project, provider, model, reasoning effort, fast/default tier, worktree, and prompt. Use when the user says "launch a bb session", "bb subagent", "spawn a bb thread", "new worktree agent", or asks to run Grok/Codex/Cursor CLI in bb on a repo. Differentiator vs bb-cli: this is only the spawn recipe. Differentiator vs codex-subagent/launch-subagent: those are Codex CLI and Cursor Task tool, not bb threads. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {"event_id":"install_<unique-id>","skill_slug":"davidondrej-bb-subagents","task":"Install bb-subagents","agent":"codex","outcome":"success","install_used":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.Supply asset profile
Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills.
Scenario
Coding agents
I need a coding agent that can understand a repository, edit code, and review pull requests.
Agent fit
Claude Code + OpenAI Agents + Cursor
Codex, Claude Code, Cursor, CLI, or custom agents.
Install
Ready
npx skills add davidondrej/skills --skill bb-subagents
Maintenance
fresh
3d since push
Risk
Needs review
Dependency or permission surface needs review
GitHub quality
3.8K
83/100 Quality · 76/100 Trust
Coverage tags
Review notes
Dependency or permission surface needs review · Permission surface may require sandboxing
Agent adoption scorecard
These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.
Quality
StrongSolid option that is likely worth shortlisting for production workflows.
Trust
Sandbox onlyUseful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
Audit
Needs reviewA machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
OpenAgentSkill Trust Score v5
Run only in a sandbox and compare close alternatives before using it for real work.
Stars
3.8K GitHub stars
Repo activity
3.8K stars, 554 forks
Maintenance
3d since push
License
MIT
Install
npx skills add davidondrej/skills --skill bb-subagents
Install safety
Agent-readable metadata
Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.
Suited tasks
Suited agents
Install decision
Trust and risk
Outcome loop
Install command
npx skills add davidondrej/skills --skill bb-subagentsDo not use when
Alternative
168.6K Stars
npx skills add mattpocock/skills --skill code-review
Alternative
40.8K Stars
npx skills add appsmithorg/appsmith
Alternative
175.7K Stars
npx skills add mattpocock/skills --skill implement
Alternative
30.9K Stars
npx skills add vercel-labs/agent-skills --skill vercel-react-best-practices
Agent safety v2
Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
Test manually in an isolated workspace and compare against safer alternatives.
high
Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.
medium
Skill likely fetches remote pages, APIs, repositories, or external services.
medium
Skill may read or write project files, documents, generated artifacts, or local workspace state.
high
Skill metadata references credentials, tokens, environment variables, or secret-bearing workflows.
Agent resolve plan
The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.
Open JSON
/api/agent/resolve?task=Use%20bb-subagents%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve text
/api/agent/resolve?task=Use%20bb-subagents%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
Install handoff
/api/skills/davidondrej-bb-subagents/install
Agent should check
Copy prompt
Task: Use bb-subagents in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20bb-subagents%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/davidondrej-bb-subagents/install
Install command: npx skills add davidondrej/skills --skill bb-subagents
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent handoff
Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.
Install handoff
/api/skills/davidondrej-bb-subagents/install
LLM text format
/api/skills/davidondrej-bb-subagents/install?format=text
Find alternatives
/api/skills/search?q=bb-subagents&limit=3
Agent prompt
Use bb-subagents for this task. Review https://www.openagentskill.com/api/skills/davidondrej-bb-subagents/install, then install with: npx skills add davidondrej/skills --skill bb-subagentsRegistry metadata
This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.
Manifest
/api/registry/manifest/davidondrej-bb-subagents
LLM text
/api/registry/manifest/davidondrej-bb-subagents?format=text
Install alias
/api/registry/install/davidondrej-bb-subagents
Recommend
/api/registry/recommend?task=Use%20bb-subagents%20in%20an%20agent%20workflow&limit=3
Agent fit
Local desktop
Use-case tags
Platforms
Claude Code, OpenAI Agents, Cursor
Audit report
A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
Agent decision cockpit
Use this as a leading candidate, then validate the README and install path in your own agent stack.
Role in stack
Primary pick
Primary fit
Local desktop
Trust label
Production-ready
Install path
Command ready
Use when
Evidence
review first
Implementation path
Trust profile
Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
GitHub adoption
PASS3.8K GitHub stars
Stars/forks activity
PASS3.8K stars, 554 forks; issue activity unavailable in current metadata
Recent maintenance
PASS3d since push
License clarity
PASSMIT
Good signals
Review before install
Recommended action
Run only in a sandbox and compare close alternatives before using it for real work.
Quality profile
Solid option that is likely worth shortlisting for production workflows.
Workflow fit
Operate local tools
I need my agent to operate local files and desktop apps in a repeatable workflow.
Automate repeated work
I need my agent to automate a repeated workflow across tools and files.
Build and ship code
I need a coding agent that can understand a repository, edit code, and review pull requests.
Workflow fit
Turn skills into distribution
A workflow for turning newly indexed skills into SEO briefs, social drafts, comparison pages, and reusable publishing workflows.
Find, compare, and synthesize
A workflow for agents that gather sources, compare claims, summarize long material, and draft useful research briefs.
Inspect, patch, and verify code
A workflow for software agents that inspect repositories, review pull requests, generate tests, and turn findings into shippable patches.
Alternative shortlist
Similar skills that may fit this task.
Review a branch or diff against repository standards and the originating spec in two independent analysis passes.
Platform to build admin panels, internal tools, and dashboards. Integrates with 25+ databases and any API.
Implement work from an approved spec or ticket set, run focused and full tests, invoke code review, and commit the result to the current branch.
React and Next.js performance guidance for writing, reviewing, and refactoring production UI code.
--- name: bb-subagents description: 'Launch a new bb worker thread with an explicit project, provider, model, reasoning effort, fast/default tier, worktree, and prompt. Use when the user says "launch a bb session", "bb subagent", "spawn a bb thread", "new worktree agent", or asks to run Grok/Codex/Cursor CLI in bb on a repo. Differentiator vs bb-cli: this is only the spawn recipe. Differentiator vs codex-subagent/launch-subagent: those are Codex CLI and Cursor Task tool, not bb threads.' ---
# bb-subagents
Spawn a bb thread the way the user launches them. Read this before any `bb thread spawn`.
Use `bb-cli` for status, tell, wait, inspect, automations. This skill is spawn-only.
**Default worker:** Codex `gpt-5.6-sol`, `--reasoning-level high`, `--service-tier fast` ("GPT 5.6 Sol High Fast"); bump to `xhigh` for larger refactors. Use this unless the user requests otherwise.
## Hard rules
- Pass `--project` explicitly. The CLI does not infer it from the current thread. - Never guess provider or model IDs. Lookup, then spawn. - After spawn: do **not** `bb thread open`, `--split`, or focus the new thread unless the user asks. Just launch. Report the thread id. Stop. - Do **not** poll, `bb thread wait`, or read logs unless the user asks. - Prefer bare `bb`. If `BB_CLI` is set, `"$BB_CLI"` is fine.
## Recipe
```bash bb project list --json bb provider list --json bb provider models <provider-id> --json
bb thread spawn --json \ --project <project-id> \ --new-environment worktree \ --provider <provider-id> \ --model <model-id> \ --reasoning-level <level> \ --permission-mode full \ --title "Short title" \ --prompt "..." ```
Add `--service-tier fast` only when the user says **fast**.
## Parent / sidebar nest
`--parent-self` and `--parent-thread` are optional. Use them when it makes sense — not on every spawn.
`--parent-self` parents the new thread to the current thread (`BB_THREAD_ID`). The left sidebar then nests the child under this thread (indented, expandable), like a worker under a manager.
`--parent-thread <id>` parents it to a specific other thread. Do not combine it with `--parent-self`.
Omit both for a **root** thread — its own top-level sidebar row, not nested.
When it makes sense: this thread is coordinating the work, the user asked for a worker under this session, or the job is a clear subtask of this thread. Skip it for unrelated one-off work that should sit as its own top-level thread.
```bash # add when it makes sense — not required --parent-self ```
`environmentId` is often `null` in the spawn JSON. The worktree is still creating. That is fine.
## Lookup
**Project.** Match `name` (e.g. `DeepAPI`) in `bb project list --json`. Use that `id`. Confirm `sources[].path` is the repo the user named. Do not hardcode project IDs.
**Provider.** From `bb provider list --json`:
| User says | Provider id | |---|---| | Cursor CLI / Cursor subscription | `acp-cursor` | | Codex / Codex subscription / ChatGPT sub | `codex` | | Claude Code | `claude-code` |
Do not use `acp-grok` for "Grok via Cursor CLI". That is Grok Build, a different product.
**Model + reasoning.** From `bb provider models <id> --json`. Use the catalog `id`. Match the user's words to `displayName` **and** `supportedReasoningEfforts[].description`. Those two are not the same field.
If the user does not name a reasoning level, use that model's `defaultReasoningEffort` from the catalog. Do not pick extra high or max on your own. Example: Claude Code Fable 5 defaults to `high`.
## Known mappings (re-fetch if spawn rejects them)
### Cursor CLI — Grok 4.6 Extra High Fast
User: "Grok 4.6 extra high fast (via Cursor CLI subscription)"
```bash --provider acp-cursor \ --model cursor-grok-4.6-medium \ --reasoning-level xhigh \ --service-tier fast ```
Traps:
- The model id stays `cursor-grok-4.6-medium` even for Extra High. Extra High is a **reasoning** value, not a different model id. - On this catalog, `high` displays as **Fast**. `xhigh` displays as **Extra High**. - "Extra High Fast" = `xhigh` **plus** `--service-tier fast`. Fast-the-reasoning-label and Fast-the-service-tier are different flags. - Cursor ACP has no `auto` permission mode. Use `full` or `accept-edits`. - Do not pass Cursor Task-tool slugs like `cursor-grok-4.6-high-fast`. Those are not bb model ids.
### Codex — GPT 5.6 Sol Max
User: "GPT 5.6 Sol Max, via the Codex subscription"
```bash --provider codex \ --model gpt-5.6-sol \ --reasoning-level max ```
Traps:
- Use native `gpt-5.6-sol`, not `cursor/gpt-5.6-sol` (opencodex routed through Cursor). - Max is `--reasoning-level max`, not a model id suffix. - Codex supports `auto` permission mode. Still use `full` when the worker must hit prod, network, or leave the sandbox. - Pass `--service-tier fast` only if the user asks for fast on Codex too.
## Worktree
`--new-environment worktree` is the bb-managed worktree. Do not create a git worktree by hand unless the user says so.
- New worktrees get **tracked files only**. - Untracked files (`.env`) copy only if the repo has `.worktreeinclude`. - Optional: `--base-branch <branch>`. Omit to use the project's default. - Do not combine `--machine` with an existing `--environment` id.
For repos that must keep `.env` in worktrees, the repo needs `.worktreeinclude` plus optional `.bb-env-setup.sh`. Details: `bb guide environments`.
## Prompt
The worker starts blind. It does not see this chat. Write the full brief into `--prompt`.
Include:
1. **Objective** — one sentence. 2. **Constraints** — read-only vs implement; no git push; no prod writes. 3. **Skills / files to use** — name them. Skills do not carry over. Example: prod reads → `~/.claude/skills/read-prod-database/SKILL.md`. 4. **Deliverable** — what to return. 5. **Validation** — how it knows it is done. 6. **Report back** — concise report only, or diff + files changed.
Read-only jobs must say **no code changes, no git writes, no database writes** in the prompt, even if permission mode is `full`.
Use a heredoc so quotes survive:
```bash --prompt "$(cat <<'EOF' Objective: ... Constraints: READ ONLY. ... Deliverable: ... Report back: ... EOF )" ```
Always pass `--json` and `--title`.
## Permission mode
| Mode | Meaning | |---|---| | `accept-edits` | Sandbox on. User approves escalations. | | `auto` | Sandbox on. Provider auto-approves. Codex/Claude have this. Cursor ACP does not. | | `full` | No sandbox. Needed for prod DB, many network tools, and "just go". |
Default for the user's investigation/build workers: `full`, with the prompt forbidding writes when the job is read-only.
## After spawn
Tell the user, then stop:
- thread id - title - project name - provider + model + reasoning (+ fast if set) - worktree, yes/no - read-only vs implement
Do not dump the prompt. Do not open the thread. Do not wait for it.
## Archive (only when the user asks)
Do not auto-archive after spawn.
```bash bb thread archive <id> --json bb thread stop <id> ```
Archive first, then stop. Archive also archives child threads. Stop frees the agent runtime; the thread history stays.
```bash bb thread unarchive <id> --json bb thread list --archived ```
Do not use `bb thread delete` unless the user wants it gone forever. Do not use `--visibility hidden` as a substitute for archive. Hidden is sidebar-only; archive is the lifecycle close-out.
Bulk, one worktree/environment: `bb environment archive-threads <environment-id>`.
Source provenance
Decision snapshot
3,828 GitHub stars
Audit
Install and adoption review
Agent-proven evidence
Outcome reports after resolve, review, install, and one narrow run.
No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.
Install
Free and open source. Review the report before installing into production agents.
Growth loop
Scenario-led draft for bb-subagents, ready for a manual X post.
A practical pick for a repeatable workflow: bb-subagents: Launch a new bb worker thread with an explicit project, provider, model, reasoning effort, fast/default tier, worktree, and... 3.8K stars https://www.openagentskill.com/skills/davidondrej-bb-subagents?ref=x
Listing + install path for bb-subagents: https://www.openagentskill.com/skills/davidondrej-bb-subagents?ref=x Install: npx skills add davidondrej/skills --skill bb-subagents
Listing source
This listing was indexed from public sources and is not marked official until a maintainer claim is approved.
Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.
Claim this skillOwner claim
This Registry indexed listing is attributed to davidondrej but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.
Creator backlink kit
Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.
[](https://www.openagentskill.com/skills/davidondrej-bb-subagents?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/davidondrej-bb-subagents?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/davidondrej-bb-subagents/audit)
[](https://www.openagentskill.com/skills/davidondrej-bb-subagents?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)davidondrej
@davidondrej
Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.
Sandbox only
Code Review
Review a branch or diff against repository standards and the originating spec in two independent analysis passes.
168.6K StarsAppsmith
Platform to build admin panels, internal tools, and dashboards. Integrates with 25+ databases and any API.
40.8K StarsImplement
Implement work from an approved spec or ticket set, run focused and full tests, invoke code review, and commit the result to the current branch.
175.7K StarsVercel React Best Practices
React and Next.js performance guidance for writing, reviewing, and refactoring production UI code.
30.9K StarsPermission surface
secrets or environment access, shell or command execution
Agent outcomes
No agent outcome data yet
Docs
Strong README/SKILL.md context
Risk summary
Install readiness
Permission surface
secrets or environment access, shell or command execution
Agent outcomes
No agent outcome data yet
Docs
Strong README/SKILL.md context
Risk summary
Install readiness
Permission surface
secrets or environment access, shell or command execution
Agent outcomes
No agent outcome data yet
Docs
Strong README/SKILL.md context
Risk summary
Install readiness
Permission surface
secrets or environment access, shell or command execution
Agent outcomes
No agent outcome data yet
Docs
Strong README/SKILL.md context
Risk summary
Install readiness