iflow-search-js: Instructions file for Claude Code

CLAUDE.md

iflow-search-js CLAUDE.md is an instructions file for Claude Code from zhengyanglsun/iflow-search-js. It costs 2,412 tokens per session, scanned A, original, MIT.

Developer instructions for iFlow Search JS, a JavaScript workspace containing a web-search SDK and adapters for several AI frameworks. A monorepo is one repository that contains multiple related packages.

In plain words
What is it for?
Adding or changing packages, working with the pnpm workspace, and keeping search, image-search, and web-fetch tools consistent across runtimes.
Why use it?
They explain the workspace layout, required tools, package relationships, and rules that keep the different adapters compatible.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; built for openclaw.

This is zhengyanglsun/iflow-search-js's own configuration. It tells Claude Code how to work on iflow-search-js 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 iflow-search-js configures →

Reuse

Borrowing it

Nothing to install: this file belongs to zhengyanglsun/iflow-search-js. 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/zhengyanglsun/iflow-search-js/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/zhengyanglsun/iflow-search-js

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 iflow-search-js CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/zhengyanglsun/iflow-search-js/claude-md"><img src="https://agentmods.dev/badge/instructions/zhengyanglsun/iflow-search-js/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,412 This file is loaded in full into every session.
When invoked 2,412 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.02412 $0.02412
Opus 5 $0.01206 $0.01206
Sonnet 5 $0.00482 $0.00482
Haiku 4.5 $0.00241 $0.00241

Measured 10d ago against content hash 3a10c71badf7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

iflow-search-js CLAUDE.md 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 10d 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.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

This repo is iflow-search-js — a pnpm workspace monorepo for the iFlow Search SDK and framework adapters.

  • npm scope: @iflow-ai/*
  • GitHub: github.com/zhengyanglsun/iflow-search-js (owner ≠ npm scope)
  • Node ≥ 18, pnpm 11.0.8

Workspace layout

packages/
  search-core/        @iflow-ai/search-core         framework-agnostic SDK (zero runtime deps)
  search-langchain/   @iflow-ai/search-langchain    LangChain adapter
  search-mcp/         @iflow-ai/search-mcp          MCP stdio server (Claude Code / Claude Desktop / Hermes)
  search-openapi/     @iflow-ai/search-openapi      HTTP/OpenAPI 3.1 tool server (Open WebUI / Coze / generic OpenAPI hosts)
examples/
  langgraph-agent/    end-to-end LangGraph demo (not published)

Adapter packages (search-langchain, search-mcp, search-openapi) all depend on search-core via workspace:* and expose the same three tools — iflow_web_search, iflow_image_search, iflow_web_fetch — with identical input/output shapes so prompts written against one runtime keep working under another.

Workspace pinnings — landmines

pnpm-workspace.yaml pins @langchain/core via overrides: to ^1.1.44. Do not remove or relax this override. Removing it re-introduces ToolMessage cross-version serialization bugs in LangGraph agent loops. If you must touch it, rerun pnpm --filter @iflow-examples/langgraph-agent test and the langgraph-agent smoke before merging.

Architecture invariant — DO NOT VIOLATE

All HTTP, Authorization, attribution headers, and error mapping live only in @iflow-ai/search-core. Adapters (search-langchain, search-mcp) must never call fetch directly, never construct headers, and never parse iFlow error shapes. They only:

  1. Receive validated input from their framework.
  2. Call into createIFlowSearchClient(...) from @iflow-ai/search-core.
  3. Map the normalized result into the framework's expected shape.

Read the full file on GitHub · 172 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. 10d ago First seen · 172 lines · 2,412 tokens per session scan A 3a10c71badf7

Subscribe to this mod's changes

iflow-search-js CLAUDE.md is an instructions file published in the GitHub repository zhengyanglsun/iflow-search-js (32 stars, last pushed 3mo ago), licensed MIT. It adds 2,412 tokens to every session, about $0.0121 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 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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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