Use it when creating or changing a BB plugin, command, tool, service, provider, setting, panel, renderer, message action, or other Plugin SDK feature.

It helps you follow the current Plugin SDK contract and repository process instead of relying on outdated assumptions. It also covers building, testing, and installing plugins.

bb-plugin-authoring — Skill by get-bb

Q: What is bb-plugin-authoring?

A guide for creating and maintaining BB plugins. A BB plugin is a TypeScript package that can add server behavior, agent functions, user-interface elements, or other supported extensions.

Install

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.

agentmods

npx agentmods add skills/get-bb/bb/bb-plugin-authoring

Any agent

npx skills add get-bb/bb --skill bb-plugin-authoring

Clone the repo

git clone --depth 1 https://github.com/get-bb/bb

Made for: Claude Code, Codex.

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 939 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00058	$0.00939
Opus 5	$0.00029	$0.00469
Sonnet 5	$0.00012	$0.00188
Haiku 4.5	$0.00006	$0.00094

Measured yesterday against content hash f1f05a0fed14, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bb-plugin-authoring 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.

apps/server/src/services/skills/builtin-skills/bb-plugin-authoring/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Author BB plugins

A BB plugin is a TypeScript package that can add server behavior, agent capabilities, host-rendered UI, or a frontend bundle.

Use the current SDK types and repository source as the contract. This skill routes to detailed references, but the installed BB version decides the exact API.

Start

Read repository instructions and the existing package.
Decide whether the feature needs a backend, frontend, or both.
Inspect the exact current SDK declaration before you implement a surface.
Build with bb plugin build.
Test the contract and the user workflow.
Install or reload only when the task requires a live check.

Use bb plugin new for a new plugin. The scaffold includes frontend files. Remove bb.app and those files when the plugin is headless.

Every new public Plugin SDK surface starts with an experimental_ prefix and an entry in docs/api_to_audit.md. Add its Plugin Guide card and API inventory in the same change.

Read only the relevant reference

Start, package, and release

Read references/quickstart.md for package structure, manifest fields, scaffold output, build, install, and the first plugin.
Read references/distribution.md for exact API lookup, Git or npm release, multi-plugin repositories, and custom marketplaces.

Backend

Read references/backend-foundation.md for the factory, logging, settings, storage, server information, and host access.
Read references/backend-sdk.md for projects, environments, threads, interactions, provider models, browser sessions, and event history.
Read references/backend-api-index.md to check every public backend, host, AI-service, and test export.
Read references/backend-events.md for lifecycle events, HTTP, RPC, realtime, background services, and schedules.
Read references/backend-cli-agents.md for CLI commands, input forms, agent tools, agent configuration, and helper AI services.
Read references/providers.md only when the plugin registers an agent provider.
Read references/provider-bridge-api-index.md to check every public provider bridge, bridge-test, and ACP export.
Read references/backend-ui-lifecycle.md for host-rendered UI, status, cleanup, and reload behavior.

Read the full file on GitHub · 101 lines

Files

What ships with it

18 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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 First seen · 101 lines · 58 tokens per session scan A f1f05a0fed14

Subscribe to this mod's changes

bb-plugin-authoring is a skill published in the GitHub repository get-bb/bb (2,762 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 939 once invoked, about $0.0003 per session on Opus 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.

Languages Planning Testing ade agent-ide claude-code codex devtools ide

emil-design-eng

This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.

wibus-wee/cradle-app · 35 tokens

cradle-cli

Use whenever you need to read, inspect, wait on, or mutate Cradle-owned state or workflows, including issues, delegation, sessions, awaits, CI/review waits, timed waits, Work inspection, workspaces and git inspection, Chronicle, automations, usage, observability, skills, agents, profiles, providers, preferences…

wibus-wee/cradle-app · 152 tokens

elysiajs

Create backend with ElysiaJS, a type-safe, high-performance framework.

wibus-wee/cradle-app · 20 tokens

transitions-dev

Production-ready CSS transitions for web apps. Use when implementing notification badges, dropdowns, modals, panel reveals, page transitions, card resizes, number pop-ins, text swaps, icon swaps, success checks, avatar group hovers, or error state shakes. Triggers on "add a transition", "animate the dropdown", "make…

wibus-wee/cradle-app · 159 tokens

userinterface-wiki

UI/UX best practices for web interfaces. Use when reviewing animations, CSS, audio, typography, UX patterns, prefetching, or icon implementations. Covers 11 categories from animation principles to typography. Outputs file:line findings.

wibus-wee/cradle-app · 52 tokens

cradle-observability-debugger

Debug Cradle local observability data by querying SQLite events/incidents/timeline, runtime snapshots, metrics, and server logs.

wibus-wee/cradle-app · 33 tokens