bb is an agentic IDE that lets users control, customize, and automate a software-development environment through a desktop app, web app, command-line interface, or HTTP API. Developers use it to run work in observable threads that can be steered or handed off to other agents. Its catalogue add-ons provide skills and instructions for working with bb.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add get-bb/bb --skill bb-cloud-aigit clone --depth 1 https://github.com/get-bb/bbWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/get-bb/bb/bb-cloud-ai)<a href="https://agentmods.dev/skills/get-bb/bb/bb-cloud-ai"><img src="https://agentmods.dev/badge/skills/get-bb/bb/bb-cloud-ai/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/get-bb/bb/bb-cloud-ai"><img src="https://agentmods.dev/badge/skills/get-bb/bb/bb-cloud-ai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00035 | $0.00723 |
| Opus 5.5 | $0.00014 | $0.00289 |
| Sonnet 5.5 | $0.00007 | $0.00145 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
bb-cloud-ai scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
bb cloud AI
bb cloud is the bb AI service from the bb-ai plugin. It writes thread
titles (branch names follow the title) and commit messages and transcribes
voice input for a signed-in bb account, within a daily spend limit per account.
bb cloud is on by default for a signed-in account. A user who turned it off stays off across restarts and upgrades. While off, it reports not ready, Automatic skips it, and nothing is sent to getbb.app. It has no settings page.
bb ai off [--json]turns bb cloud off and keeps the bb account signed in;bb ai on [--json]turns it back on. Only turn it on when the user asks: it sends prompt text, diffs, and voice recordings off the machine. Disabling thebb-aiplugin in Settings → Plugins also stops it.bb ai status [--json]shows the account, whether bb cloud is on and ready, and today's usage.bb ai usage [--json]shows today's spend against the limit and when it resets (00:00 UTC). Titles, commit messages, and voice input share one budget.- Sign in with
bb account login. Signed out, bb cloud is not ready and Automatic skips it. - Which service handles each task is a core setting:
bb settings ai-services set <thread-title|commit-message|voice> bbpicks bb cloud,automatictries bb cloud first, then other compatible registered services by plugin id and service id in lexicographic order, andoffturns the task off.bb settings ai-services test thread-titleruns a sample. - Voice input: without a Codex login, the microphone appears once bb cloud is
ready.
bb voice transcribe <file> [--type <mime>]transcribes a recording. bb cloud takes WebM, Ogg, MP4/M4A, MP3, WAV, FLAC, and AAC up to 10 MB; it reads the format from the MIME type, then the file extension, and refuses anything else before contacting getbb.app. Each transcription model gets 30 seconds, and a model that times out or fails falls back to the next one. - When an account's daily limit is used up, bb cloud reports not ready for
that account until the reset and Automatic moves on; a task set to
bbfalls back to the prompt text for titles andbb: automated commitfor commits, and the microphone hides unless another voice service is ready. Signing in to a different account clears the limit message.
While bb cloud is on, bb sends the text of a thread's first prompt (titles), the changed files with a diff excerpt (commit messages), and voice recordings with a vocabulary hint (voice input) to getbb.app, which forwards them to OpenRouter model providers with zero data retention. bb stores daily usage totals and, for 30 days, metadata about each request such as its time, model, token counts, and cost; it never stores prompts, recordings, or replies.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago Changed e2a2e88c2e95
- 14d ago Changed · +1 lines 0f97ce94eb43
- 15d ago Changed · +10 lines · +3 tokens per session de3315286bbe
- 16d ago First seen · 39 lines · 32 tokens per session scan A 3bcca44b1efb
bb-cloud-ai is a skill published in the GitHub repository get-bb/bb (4,324 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 723 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-30.
Other skills, from other repositories
git-commit
Create git commits using Nimbalyst's interactive commit proposal widget. ONLY use when the user explicitly clicks "Commit with AI" button or asks for "smart commit". For regular commit requests, use standard git commands instead.
conventional-commit
Conventional Commit - Generate Conventional Commits 1.0.0 compliant messages. MANDATORY for all git commits. Invoke when user says 'commit', 'commit this', or asks to commit code.
working-in-grove
Use when working inside a Grove workspace, including reporting task phase, updating a workspace or its ticket links, using GROVEPHASEFILE, writing to another Grove agent through the mailbox, or waiting on slow work like CI by registering a watch instead of sleeping. Also use when a worktree has a phase file, when…
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
bitbottle
Reference for the bitbottle CLI — a gh-style tool for Bitbucket Server/DC and Cloud. Load when the user asks about bitbottle commands, auth setup, PRs, repos, branches, tags, commits, pipelines, or why a command failed. Load even if the user just says "bitbottle", mentions "Bitbucket", or pastes a bitbottle error…
openclaw-github-repo-commander
7-stage super workflow for GitHub repo audit, cleanup, PR review, and competitor analysis.