agentmods.dev

sdk: Instructions file for Claude Code

CLAUDE.md

sdk CLAUDE.md is an instructions file for Claude Code from WaniWani-AI/sdk. It costs 3,352 tokens per session, scanned B, original, MIT.

A software development kit for WaniWani, an open-source flow engine with optional hosted services for tracking, a knowledge base and chat. It provides tools for building flows and storing their state.

In plain words
What is it for?
Use it to create and compile flows, provide a state store, connect to hosted flow tracking and state, or work with WaniWani’s knowledge-base and frontend features.
Why use it?
It lets applications use the open-source part without an API key, while a WANIWANI_API_KEY enables the hosted features. It also makes the separation between public and private API tiers clear.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths.

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 →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/maximeantoine/Projects/WaniWani/docs/docs/sdk/.

not rated 17repo 2d ago B scan 3,352 tokens original MIT
View source ↗ WaniWani-AI/sdk docs.waniwani.ai
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.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 sdk CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/waniwani-ai/sdk/claude-md"><img src="https://agentmods.dev/badge/instructions/waniwani-ai/sdk/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,352 This file is loaded in full into every session.
When invoked 3,352 The same file — it is already loaded in full.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.03352 $0.03352
Opus 5 $0.01676 $0.01676
Sonnet 5 $0.00670 $0.00670
Haiku 4.5 $0.00335 $0.00335

Measured 9d ago against content hash 4340b06ec620, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

sdk CLAUDE.md scanned grade B with 1 finding 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 9d 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.

Subtle steeringmediumPrompt injection

Instructions that bias recommendations or shape behaviour without the user noticing.

`@waniwani/sdk/internal` is a private entry point for the Waniwani platform (app.waniwani.ai) to reuse SDK primitives that should not be exposed to third-party consumers. **Never document these in user-facing docs. Never
CLAUDE.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Waniwani SDK

SDK for app.waniwani.ai — open-source flow engine plus optional hosted tier for tracking, KB, and chat.

Public API tiers

The SDK ships two public tiers plus a private one. The legacy tier was removed in 0.20.0: no src/legacy/, no re-exports, no entry point serving it.

OSS (no API key required)

Truly open source. Works standalone with any state backend.

  • createFlow, StateGraph, START, END, redacted, createFlowTestHarness from @waniwani/sdk/mcp
  • KvStore interface, MemoryKvStore from @waniwani/sdk/mcp

createFlow().compile() requires either an explicit { store } OR WANIWANI_API_KEY. With neither, it throws at compile time with a clear migration message.

Free tier (one env var: WANIWANI_API_KEY)

Same SDK, hosted features added when the key is present.

  • WaniwaniKvStore (hosted flow state) — used by createFlow default when key is set
  • waniwani(), tracking/*, createFrontendClient, EVENT_TYPES, withWaniwani, createTrackingRoute, widget-token, extractScopedClient / SCOPED_CLIENT_KEY from @waniwani/sdk and @waniwani/sdk/mcp
  • createKbClient from @waniwani/sdk/kb
  • useWaniwani from @waniwani/sdk/mcp/react (also OSS — degrades to no-op without config; BYO endpoint also supported). Host-agnostic: takes the tool-response _meta as data via the toolResponseMetadata option, or an explicit { endpoint, source }; it opens no host connection and reads no React context. Returns { sessionId, track, identify, flush } where track is the same typed TrackFn as the server client; emits one widget_render automatically.
  • useWaniwani from @waniwani/sdk/mcp/react/skybridge — the skybridge-host adapter. Reads skybridge's useToolInfo().responseMetadata and feeds it to the core hook, so skybridge-hosted widgets call useWaniwani() bare. skybridge is an optional peer dependency.
  • WaniwaniChat (hosted React chat — recommended), themes, embed.js (IIFE for non-React hosts), styles.css from @waniwani/sdk/chat. Both expose host-page tracking: WaniWani.chat.track / .identify on the embed global, track / identify on the ChatHandle ref.
  • ChatEmbed from @waniwani/sdk/chat — bare-bones bring-your-own-backend primitive (no track/identify). Exposed but not the recommended path for new code; reach for it only when self-hosting the chat backend.

Read the full file on GitHub · 165 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. 9d ago First seen · 165 lines · 3,352 tokens per session scan B 4340b06ec620

Subscribe to this mod's changes

sdk CLAUDE.md is an instructions file published in the GitHub repository WaniWani-AI/sdk (17 stars, last pushed 2d ago), licensed MIT. It adds 3,352 tokens to every session, about $0.0168 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Backend and APIschatgptclaudeconversational-ailead-generationmcpmodel-context-protocol
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens