agentmods.dev

zhin: Instructions file for Claude Code

CLAUDE.md

zhin CLAUDE.md is an instructions file for Claude Code from zhinjs/zhin. It costs 3,287 tokens per session, scanned A, original, MIT.

A repository guide for Zhin.js, a TypeScript chatbot framework, covering its project structure, commands, development setup, and package-specific work.

In plain words
What is it for?
Use it to develop or maintain Zhin.js, including building packages, running tests, preparing the command-line tools, and starting development bots.
Why use it?
It gives coding agents the project’s required build, test, lint, type-checking, and bootstrap steps so changes can be checked consistently.

Instructions file for Claude Code

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

This is zhinjs/zhin's own configuration. It tells Claude Code how to work on zhin 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 zhin configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is "extends": "../../tsconfig.base.json",.

not rated 136repo +1 changed 5d ago A scan 3,287 tokens original MIT
View source ↗ zhinjs/zhin zhin.js.org
Reuse

Borrowing it

Nothing to install: this file belongs to zhinjs/zhin. 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/zhinjs/zhin/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/zhinjs/zhin

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 zhin CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/zhinjs/zhin/claude-md"><img src="https://agentmods.dev/badge/instructions/zhinjs/zhin/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,287 This file is loaded in full into every session.
When invoked 3,287 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 $0.03287 $0.03287
Opus 5.5 $0.01315 $0.01315
Sonnet 5.5 $0.00657 $0.00657
Haiku 4.5 $0.00329 $0.00329

Measured 5d ago against content hash ac2071b2f093, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

zhin 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 5d 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 · 238 lines

How it starts

The opening of the file, as written. The whole thing — 238 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.

See also: AGENTS.md for the universal agent entry point; .github/copilot-instructions.md for detailed API patterns and plugin examples.

Project Overview

Zhin.js is a TypeScript chatbot framework — AI-driven, plugin-based, hot-reload, multi-platform. ESM-only ("type": "module"), targets Node.js >=22.19.0.

Commands

pnpm build              # Full build (Turborepo: basic/ → packages/ → plugins/)
pnpm test               # Run all Vitest tests
pnpm test:watch         # Watch mode
pnpm test:coverage      # Coverage report
pnpm lint               # ESLint (.ts,.tsx)
pnpm type-check         # tsc --noEmit -p tsconfig.typecheck.json
pnpm dev                # Start minimal-bot (examples/minimal-bot); use pnpm dev:test for test-bot
pnpm clean              # Clean all lib/ dist/ directories
pnpm eval:chat --workspace <dir> --judge <alias/model>  # Real-model chat quality eval (local, not CI)

# Bootstrap (first-time or after clean)
pnpm prepare:logger     # Build @zhin.js/logger + install CLI deps
pnpm prepare:cli        # Build scaffold-wizard + CLI + reinstall

# Single package
pnpm --filter @zhin.js/core build
pnpm --filter @zhin.js/core test

# Run a single test file
pnpm vitest run packages/im/core/tests/plugin.test.ts

Custom lint checks:

  • pnpm check:harness-paths — 检测插件是否绕过 Adapter.sendMessage 直调 bot.$sendMessage
  • pnpm check:no-koa — 检测插件是否直接 import koa（应使用 RouterContext）
  • pnpm check:prod — 检查生产环境配置（无 console.log/debugger/TODO/FIXME）
  • pnpm check:plugin — 检查插件是否符合标准规范（入口文件、测试、README）
  • pnpm check:no-removed-plugin-api — 检测是否重新调用已从 public surface 删除的 Plugin lookup API
  • pnpm check:plugin-agent-publish — 带 agent/ 的插件发布清单（files、prepublishOnly）
  • pnpm check:all — 运行所有 harness 检查（含 type-check / lint / test）

Architecture

Monorepo managed with pnpm 9.0.2 workspaces + Turborepo (turbo.json). Versioning via Changesets.

Read the full file on GitHub · 238 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. 5d ago Changed · +1 lines · +29 tokens per session ac2071b2f093
  2. 13d ago Changed · -7 tokens per session 04cb9bd6cdcf
  3. 18d ago Changed · -3 tokens per session 623e7c48db28
  4. 1mo ago Changed · +3 lines · +13 tokens per session e64a90974304
  5. 2mo ago First seen · 234 lines · 3,255 tokens per session scan A 6807edfdbfe8

Subscribe to this mod's changes

zhin CLAUDE.md is an instructions file published in the GitHub repository zhinjs/zhin (136 stars, last pushed today), licensed MIT. It adds 3,287 tokens to every session, about $0.0131 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.

agentaichatbotdiscordframeworkhot-module-replacement
Related

Other instructions, from other repositories

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 · 9,715 tokens

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 · 7,461 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 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 · 4,261 tokens