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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/get-bb/bbnpx agentmods add skills/get-bb/bb/docsWrote 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/docs)<a href="https://agentmods.dev/skills/get-bb/bb/docs"><img src="https://agentmods.dev/badge/skills/get-bb/bb/docs/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/docs"><img src="https://agentmods.dev/badge/skills/get-bb/bb/docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00022 | $0.01305 |
| Opus 5.5 | $0.00009 | $0.00522 |
| Sonnet 5.5 | $0.00004 | $0.00261 |
| Haiku 4.5 | $0.00002 | $0.00130 |
Grade A, and why
docs 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 yesterday.
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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs
Docs is the user's filesystem-first document library. Documents can live on
the server machine or another connected host, but the bb docs command
handles that routing through named vaults.
Access documents
Start with the smallest useful lookup:
bb docs vaults --json
bb docs list --vault <vault-id> --json
bb docs read <path> --vault <vault-id>
Use the path and vault exactly as returned. Paths are relative to the vault;
do not guess an absolute host path or inspect the vault outside bb docs.
Docs @-mentions
A Docs mention resolves at send time and appears in agent context as a
Docs document (<vault>/<path>) block. Treat that block as user-provided
source material from their document library:
- Read and use its current contents even if the prompt only says “this” or “the attached doc.”
- Preserve its meaning and distinguish its claims from your own inference.
- Do not rewrite the mentioned document unless the user asks you to change it.
- When your answer refers the user back to it, emit a Docs directive rather than an opaque filesystem path.
Create and update documents
Docs is a good destination for durable plans, specifications, write-ups, and HTML artifacts the user should be able to reopen.
bb docs pull plans/release-plan.md --vault personal --into ./docs-work
# Edit ./docs-work/plans/release-plan.md with normal file tools.
bb docs status ./docs-work --diff
bb docs push ./docs-work
bb docs status exits 0 when no changes exist. It exits 4 when it finds
changes that the output describes. Exit 4 is a successful status result.
Review that output, then run bb docs push as a separate command. Do not
connect the status and push commands with &&.
Pull a folder subtree with --folder, or the whole selected vault with
--all:
bb docs pull plans --folder --vault personal --into ./docs-work
bb docs pull --all --vault personal --into ./docs-work
Always edit the pulled files with ordinary workspace tools, then run status
before push. The manifest in .bb-docs-state.json records stable vault paths
and remote SHA-256 versions; do not edit it. Pull and push fail closed with
exit 3 when both the local and vault copies changed. Resolve the content
manually, then pull or push again. push --dry-run --diff previews without
writing. Inside a thread the workspace is on the thread's host; a standalone
CLI call targets the server machine unless it passes --workspace-host <id>.
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.
- yesterday Changed · +10 lines cb37af258ce0
- 24d ago Changed · +25 lines 843185083048
- 27d ago Changed · +6 lines 819d93b86e15
- 29d ago Changed 86b7eaec2716
- 1mo ago Changed · -42 tokens per session 021f553300d3
- 1mo ago First seen · 97 lines · 64 tokens per session scan A d90e3327e795
docs is a skill published in the GitHub repository get-bb/bb (4,324 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 1,305 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 2026-08-30.
Other skills, from other repositories
Extract and analyze information from PDF documents.
document-extraction
Parses documents into structured Markdown, extracts fields with JSON schemas, classifies pages, and splits mixed document batches using LandingAI's Agentic Document Extraction (ADE) REST APIs, with official Python and TypeScript libraries. Builds document pipelines: batch and async processing for large files…
generate-readme-screenshots
Regenerate high-resolution README screenshots from Storybook stories. Use this skill when visual diffs are detected in any story under "Docs/README Screenshots", or when story data/layout changes require updated documentation assets. Triggers on: visual regressions in readme screenshot stories, changes to…
novel-import-tomato-reference
A workflow for handling Tomato Novel Downloader material, including free-novel EPUB files and downloaded fiction. It organizes the material as Markdown references in a novel project workspace.
using-grove
Use when orchestrating Grove workspaces from outside, including creating or supervising host or container agents, steering a fleet, using Grove CLI or MCP tools, or having agents write to each other through the mailbox. Also use when splitting work across workspaces, reviewing a diff from several angles, managing…
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…