BubbleLab: Skill for Claude Code

.claude/skills/create-bubble/SKILL.md

create-bubble is a skill for Claude Code from bubblelabai/BubbleLab. It costs 27 tokens per session (1,708 once invoked), scanned A, original, Apache-2.0.

A development guide for adding a new Bubble integration to Bubble Lab. A Bubble is a packaged connection between the system and an outside service.

In plain words
What is it for?
Use it when connecting Bubble Lab to an external service and defining its operations, authentication, credentials, schemas, utility code, and tests.
Why use it?
It provides the required questions, folder layout, schemas, tests, and implementation structure so a new integration follows the project's existing conventions.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

This is bubblelabai/BubbleLab's own configuration. It tells Claude Code how to work on BubbleLab itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything BubbleLab configures →

About the project

Bubble Lab is an open-core workflow engine that runs and coordinates automated tasks across tools, APIs, and other systems. It powers Bubble Lab’s Slack-based AI operator platform and can also be hosted and extended independently by teams, organizations, and developers. The catalogue entries provide rules, skills, and instructions for working with the engine.

bubblelabai/BubbleLab · 1,099 stars · on GitHub · bubblelab.ai

Reuse

Borrowing it

Nothing to install: this file belongs to bubblelabai/BubbleLab. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bubblelabai/BubbleLab/main/.claude/skills/create-bubble/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/bubblelabai/BubbleLab

Made for: Claude Code.

Wrote 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.

agentmods badge for create-bubble

README.md
[![agentmods](https://agentmods.dev/badge/skills/bubblelabai/bubblelab/create-bubble/github.svg)](https://agentmods.dev/skills/bubblelabai/bubblelab/create-bubble)
Your own site
<a href="https://agentmods.dev/skills/bubblelabai/bubblelab/create-bubble"><img src="https://agentmods.dev/badge/skills/bubblelabai/bubblelab/create-bubble/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.

agentmods 80×15 button for create-bubble

Your own site · 80×15
<a href="https://agentmods.dev/skills/bubblelabai/bubblelab/create-bubble"><img src="https://agentmods.dev/badge/skills/bubblelabai/bubblelab/create-bubble.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,708 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 21
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00027 $0.01708
Opus 5.5 $0.00011 $0.00683
Sonnet 5.5 $0.00005 $0.00342
Haiku 4.5 $0.00003 $0.00171

Measured 2mo ago against content hash 4d371a475e17, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

create-bubble 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 2mo 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.

.claude/skills/create-bubble/SKILL.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Bubble Skill

Create a new Bubble integration for: $ARGUMENTS

Follow the CREATE_BUBBLE_README.md guide at packages/bubble-core/CREATE_BUBBLE_README.md exactly.

Step 1: Gather Requirements

Before writing any code, ask the user:

  1. Service name: What external service is this integrating with?
  2. Operations: What operations should this bubble support? (single or multiple)
  3. Authentication: What auth type? (none, apikey, oauth, basic)
  4. Credentials: What credential types are needed? (API key, access token, etc.)

Step 2: Create Folder Structure

All bubbles use this folder structure in packages/bubble-core/src/bubbles/service-bubble/{service-name}/:

{service-name}/
├── {service-name}.schema.ts           # All Zod schemas
├── {service-name}.utils.ts            # Utility functions (optional)
├── {service-name}.ts                  # Main bubble class
├── index.ts                           # Exports
├── {service-name}.test.ts             # Unit tests
└── {service-name}.integration.flow.ts # Integration flow test

Step 3: Create Schema File ({service-name}.schema.ts)

Include:

  • Parameter schema with .describe() on ALL fields
  • Result schema with success and error fields
  • Both INPUT and OUTPUT type exports
  • Use z.discriminatedUnion() for multi-operation bubbles
  • Use z.transform() over z.preprocess() for type preservation
  • Always include credentials field

Step 4: Create Main Bubble Class ({service-name}.ts)

Required static properties:

  • service, authType, bubbleName, type, schema, resultSchema
  • shortDescription, longDescription, alias

Use INPUT type for generic constraint:

export class {ServiceName}Bubble<
  T extends {ServiceName}ParamsInput = {ServiceName}ParamsInput,
> extends ServiceBubble<T, Extract<{ServiceName}Result, { operation: T['operation'] }>>

Implement:

  • constructor with default values
  • chooseCredential() method
  • performAction() method with operation switch

Read the full file on GitHub · 222 lines

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.

  1. 2mo ago First seen · 222 lines · 27 tokens per session scan A 4d371a475e17

Subscribe to this mod's changes

create-bubble is a skill published in the GitHub repository bubblelabai/BubbleLab (1,099 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 1,708 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.

Related

create-bubble compared with skills from other repositories

create-bubble next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
create-bubblebubblelabai/BubbleLabSkill1.1k6mo agoApache-2.0A27Claude Code
knowledge-shared-api-and-runtime-schemasechoVic/blade-codeSkill18124d agoMITA149Claude Code, Codex
knowledge-interaction-surfaces-cli-bootstrap-headless-and-printechoVic/blade-codeSkill18124d agoMITA160Claude Code, Codex
knowledge-interaction-surfaces-hono-server-api-and-streamingechoVic/blade-codeSkill18124d agoMITA156Claude Code, Codex
knowledge-model-and-provider-runtimeechoVic/blade-codeSkill18124d agoMITA152Claude Code, Codex
knowledge-tool-contracts-and-registryechoVic/blade-codeSkill18124d agoMITA156Claude Code, Codex
supabasemnlt/teleportSkill86mo agoMITB67Claude Code, Codex