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 plugin-guide-maintenancegit 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/plugin-guide-maintenance)<a href="https://agentmods.dev/skills/get-bb/bb/plugin-guide-maintenance"><img src="https://agentmods.dev/badge/skills/get-bb/bb/plugin-guide-maintenance/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/plugin-guide-maintenance"><img src="https://agentmods.dev/badge/skills/get-bb/bb/plugin-guide-maintenance.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 | $0.00023 | $0.01116 |
| Opus 5.5 | $0.00009 | $0.00446 |
| Sonnet 5.5 | $0.00005 | $0.00223 |
| Haiku 4.5 | $0.00002 | $0.00112 |
Grade A, and why
plugin-guide-maintenance 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 20d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintain the Plugin Guide
The Plugin Guide is bb's public Plugin SDK reference. For a public API change, follow the full workflow. For annotation-only maintenance, start at Maintain annotation layout, skip the public-API section, and then follow the annotation-only verification path.
Confirm a public API change
Build the declarations and inspect the SDK change:
pnpm exec turbo run build:types --filter=@get-bb/plugin-sdk
git diff -- packages/plugin-sdk/package.json packages/plugin-sdk/src
Continue only when the API change affects a Guide card, API symbol list, or fixture. If the Guide remains accurate, do not change it.
New public members also require:
- an
experimental_name, or anExperimentaltype name; - an entry in
docs/api_to_audit.md; - compatibility with released SDK users unless the user approves the break.
Find the product source
For a visible method, inspect these sources:
- The app component that shows the surface.
- The slot, collector, or adapter that inserts the plugin content.
- The closest app test that defines the real states.
Record stable source paths and anchors in
plugins/plugin-api-docs/src/anatomy-manifest.json. Use labels, roles, data
attributes, class constants, and state names as anchors. The @bb/app tests
check the anchors against the source.
For a method without a visible surface, use the Plugin backend group. Do not invent interface elements.
Add the Guide entry
For a new Guide entry, run the scaffold command with its sources and symbols:
pnpm exec turbo run scaffold:surface-entry --filter=bb-plugin-plugin-api-docs -- \
--id <stable-id> \
--title "<visible-product-object>" \
--group <group> \
--source <source-path> \
--api-symbol <exported-name>
Complete the applicable changes:
- Update
plugins/plugin-api-docs/src/surfaces.ts. - Prefer an existing card unless the API creates a new product surface.
- Keep existing surface IDs stable and list each exact exported symbol.
- Name example plugins in
firstPartyby display name. A plugin missing fromplugins/plugin-api-docs/src/first-party-plugins.jsonneeds a row there; the@bb/scriptstests check each row against the plugin's manifest. - For a visible method, update
wireframes.tsxand its marker. - Match the real ownership, labels, roles, order, states, actions, and outcome.
- Keep Guide annotations separate from the product interface.
- Add focused tests for the entry, source anchors, trigger, and outcome.
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.
- 20d ago Changed · +2 lines b5a433224b06
- 22d ago Changed · +6 lines 7dc2649cd70f
- 1mo ago Changed b740c65a73aa
- 1mo ago Changed · -77 tokens per session 7f81ca2a0b38
- 1mo ago Changed · +27 lines · +15 tokens per session 6de426b58b0d
- 1mo ago First seen · 90 lines · 85 tokens per session scan A 16b5017c03a3
plugin-guide-maintenance is a skill published in the GitHub repository get-bb/bb (4,324 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 1,116 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
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…
collaborating-on-diagrams
Use when working with an existing .drawio diagram through Grove collaboration. Triggers on opening, reading, editing, updating, stopping, or recovering a diagram in a Grove workspace. Covers revisioned managed writes, XML-preserving edits, collaboration state, conflicts, read-only stop, and container/editor limits.
mocking-up-in-grove
Use when a visual or frontend task in a Grove workspace needs a mockup approved before code — a new control, a redesigned surface, a layout change. Covers drawing a draw.io mockup through Grove's diagram tools, previewing it in the browser, getting sign-off, filing the approved image on the tracker issue, and handing…
leading-in-grove
Use when you lead a fleet of Grove teammates toward one deliverable, including deciding how many to spawn and how to split the work, writing their onboarding prompt, getting acknowledgment, running scheduled check-ins, answering their mailbox questions, keeping tickets and your own status compaction-proof, reviewing…
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…