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 prompt-librarygit 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/prompt-library)<a href="https://agentmods.dev/skills/get-bb/bb/prompt-library"><img src="https://agentmods.dev/badge/skills/get-bb/bb/prompt-library/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/prompt-library"><img src="https://agentmods.dev/badge/skills/get-bb/bb/prompt-library.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 | $0.00014 | $0.00735 |
| Opus 5.5 | $0.00006 | $0.00294 |
| Sonnet 5.5 | $0.00003 | $0.00147 |
| Haiku 4.5 | $0.00001 | $0.00073 |
Grade A, and why
prompt-library 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt library
Open + → Prompts… or press Ctrl+R in a composer. Search matches starred prompts and recent history. Select Thread, Project, or All; the scope is remembered per composer kind on this device. The new-thread composer offers Project and All. Arrow keys select, Tab switches scope, Enter inserts, and Escape closes. Desktop shows a full Markdown preview beside the list; narrow layouts open the preview when a row is tapped, with Back and Insert.
Click the star or press Cmd/Ctrl+S to star or unstar the selected prompt. Star current draft saves the draft. Starred prompts keep text and mentions, deduplicate by text, persist across reloads, and sort by most recent use. History attachments are retained when restoring into an empty composer. Starred prompts omit attachments. A nonempty composer receives text and mentions at the kept cursor. Inserting never sends a message.
The first search loads and indexes all prompt history; later searches fetch only
newer prompts. Each query word, ignoring case, must match a single word of the
prompt: exactly, as its start, with one typo (words of four or more letters),
inside it, or as an abbreviation that starts at its first letter (tmln finds
timeline). Letters are never matched across words. Results include up to 20
starred and 30 recent prompts in scope. Without a query, starred prompts come
first, then recent ones. A query returns one ranked list: prompts that start
with the query first, then by match type in that order, then starred prompts
and prompts of the composer's kind (prompts that started a thread in the
new-thread composer, follow-ups in a thread composer), then by relevance (rarer
words, repeated words, and shorter prompts score higher) decayed by age with a
seven-day half-life; a starred prompt's age counts from its last use.
A starred
prompt appears once, as its starred row. History contains user prompts; core records them without agent-only input. Prompts stay searchable until the server restarts, even if their
thread is deleted.
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.
- 7d ago Changed · +7 lines 616e0058520d
- 8d ago Changed · +3 lines 61e4f07f4598
- 10d ago First seen · 44 lines · 14 tokens per session scan A 58857bd439a4
prompt-library is a skill published in the GitHub repository get-bb/bb (4,324 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 735 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 2026-10-06.
Other skills, from other repositories
configuring-grove
Use when configuring Grove for a user or project, including agent rosters, init scripts, containers, private credentials, daemon or MCP setup, or the native-versus-terminal launch of a Claude Code or Codex agent. Also use when resolving config layers, validating a config schema, or explaining why a workspace starts…
computer-use
Use Avibe's local Computer Use CLI for carefully bounded desktop observation and actions.
termio
See and drive the sibling agent sessions running alongside you in this Termio project via the termio sessions CLI — list and watch their status, spawn new agent or plain-terminal sessions, send a prompt or an answer into a session, and read an agent's reply from its transcript. Use when delegating work to another…
workflow
A workflow skill for embedded-device projects that plans and runs building, flashing, debugging, observing, and diagnosis tasks.
develop-inspection-feature
End-to-end workflow for adding a new inspection or quick-fix feature to the explyt/spring-plugin repository: duplicate check, fact verification against authoritative javadoc, base-class and gating choice (isAvailableForFile), visible-element highlighting, registration, platform tests, branch and PR. Use when the user…
meeting-prep
Build a pre-meeting briefing — who's in the room, what they care about, your goal, and the questions to ask. Trigger when the user asks to prep for a meeting or call, "what should I know before", or names an upcoming meeting.