sdk: Skill for Claude Code

.claude/skills/create-flow-app/SKILL.md

create-flow-app is a skill for Claude Code from WaniWani-AI/sdk. It costs 90 tokens per session (1,592 once invoked), scanned A, original, MIT.

A starting structure for building a multi-step conversational app with createFlow from the Waniwani software development kit. The flow collects information through questions, keeps state in memory, and returns a result.

In plain words
What is it for?
Use it to add a new flow to an MCP server, replace legacy widget patterns, or scaffold a flow that asks questions and then produces a summary.
Why use it?
It gives a consistent way to build new conversational flows and avoids older createTool and createResource patterns. It also accounts for cases where some information is already supplied before the flow opens.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is WaniWani-AI/sdk's own configuration. It tells Claude Code how to work on sdk 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 sdk configures →

Reuse

Borrowing it

Nothing to install: this file belongs to WaniWani-AI/sdk. 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/WaniWani-AI/sdk/main/.claude/skills/create-flow-app/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/WaniWani-AI/sdk

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-flow-app

README.md
[![agentmods](https://agentmods.dev/badge/skills/waniwani-ai/sdk/create-flow-app/github.svg)](https://agentmods.dev/skills/waniwani-ai/sdk/create-flow-app)
Your own site
<a href="https://agentmods.dev/skills/waniwani-ai/sdk/create-flow-app"><img src="https://agentmods.dev/badge/skills/waniwani-ai/sdk/create-flow-app/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-flow-app

Your own site · 80×15
<a href="https://agentmods.dev/skills/waniwani-ai/sdk/create-flow-app"><img src="https://agentmods.dev/badge/skills/waniwani-ai/sdk/create-flow-app.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,592 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 pass 7 Sept 2026
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 $0.00090 $0.01592
Opus 5 $0.00045 $0.00796
Sonnet 5 $0.00018 $0.00318
Haiku 4.5 $0.00009 $0.00159

Measured 8d ago against content hash 4b690f590fd1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

create-flow-app 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 8d 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-flow-app/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create a flow app

When the user wants to build a new MCP server feature or replace legacy widget patterns, default to createFlow from @waniwani/sdk/mcp. Never recommend createTool / createResource for new code — they're legacy.

Scaffolding template

import { createFlow, END, MemoryKvStore, START } from "@waniwani/sdk/mcp";
import { z } from "zod";

export const myFlow = createFlow({
  id: "my_flow",
  title: "My Flow",
  description: "Use when the user wants to X.",
  state: {
    // Required: every field needs .describe()
    field1: z.string().describe("..."),
  },
})
  .addNode("step1", ({ interrupt }) =>
    interrupt({ field1: { question: "What's your ...?" } }),
  )
  .addNode("done", ({ state }) => ({ summary: `Got ${state.field1}` }))
  .addEdge(START, "step1")
  .addEdge("step1", "done")
  .addEdge("done", END)
  .compile({ store: new MemoryKvStore() });

await myFlow.register(server);

Opening message (intro)

If the flow should introduce the assistant or state a data/GDPR notice, put it on the config as intro — never as a first node. Pre-filled state skips opening nodes, so a greeting node is the one node most likely never to run.

createFlow({
  id: "my_flow",
  title: "My Flow",
  description: "Use when the user wants to X.",
  intro: {
    verbatim: "Acme is the data controller. Your answers are deleted after 30 days.",
    instructions: "Introduce yourself as Léa from Acme in one short sentence first.",
  },
  state: { /* … */ },
})

verbatim is reproduced word for word, instructions is guidance the model writes from, and either alone is fine (a bare string means verbatim).

The intro is not a node. It is seeded into the session's internal state at start and attached to the first non-error response, whichever node the flow lands on, then taken off so it is never repeated. Internal state is the engine's own state for a session, stored under internal on FlowTokenContent and kept strictly apart from the flow's state: nothing in it is declared by the author, reaches a node, or can be written through stateUpdates. Everything about it lives in internal-state.ts:

Read the full file on GitHub · 130 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. 8d ago First seen · 130 lines · 90 tokens per session scan A 4b690f590fd1

Subscribe to this mod's changes

create-flow-app is a skill published in the GitHub repository WaniWani-AI/sdk (17 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 1,592 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

codexless-browser-repair

Diagnose and temporarily repair Codexless Browser compatibility after a Codex, Chrome Skill, or Browser runtime update when Codexless Browser stopped working. Use for current-version Codexless Browser compatibility drift, not ordinary website bugs, general Browser operation, Codexless install/update work, or long-term…

liyana31811/Codexless · 70 tokens

codex-with-chatgpt

A connection that lets ChatGPT help plan and review coding work while Codex edits files, runs commands, tests code, and handles execution.

XiaoDuoYa/codex-with-chatgpt · 90 tokens

add-widget

Add a new widget (React UI + MCP tool) to this template. Use when asked to "add a widget", "add a new tool with UI", "create a new widget", "scaffold a widget", or "build a new MCP App feature".

pomerium/mcp-app-typescript-template · 56 tokens

create-mcp-tool

Add a plain (text-only) or UI-enhanced MCP tool to this template's server. Use when asked to "add a tool", "add an MCP tool", "create a new tool", "add a server-side tool without a widget", "add a tool with a UI", "add a tool with a widget", or "create a tool and a widget".

pomerium/mcp-app-typescript-template · 80 tokens

threebrowser-studio-mcp

Author, inspect, render, validate, animate, and save Three.js WebGPU projects in the native ThreeBrowser Studio through its real threestudio MCP tools. Use whenever Codex is asked to build or edit a ThreeBrowser Studio scene, material, Blender-style shader or texture graph, animation, lighting setup, camera, or…

SamG-Coder/ThreeBrowserStudio · 122 tokens

install-shellby-mcp

Install and verify Shellby MCP on a Mac using terminal access only. Use when a user asks an agent to install, set up, configure, or finish a new Shellby MCP installation from this repository.

serbyte-development/shellby-mcp · 47 tokens