agentmods.dev

claude-code-web CLAUDE.md

claude-code-web CLAUDE.md is an instructions file for Claude Code from dwqdaiwenqi/claude-code-web. It costs 1,087 tokens per session, scanned A, original, MIT.

Project instructions for Claude Code Web, a monorepo that exposes Claude Code as a web service with a React interface. The server provides an HTTP API, while the web interface is built into the server for delivery.

In plain words
What is it for?
Use it to run development mode, build or type-check either package, start the production server, or prepare a release.
Why use it?
It explains the separate server and web packages, required setup, and build steps so changes can be made and tested in the right place.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the AskUserQuestion tool.

not rated 43 3mo ago A scan 1,087 tokens original MIT
View the source file dwqdaiwenqi/claude-code-web
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/dwqdaiwenqi/claude-code-web/claude-md
Clone the repo
git clone --depth 1 https://github.com/dwqdaiwenqi/claude-code-web

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 claude-code-web CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dwqdaiwenqi/claude-code-web/claude-md.svg)](https://agentmods.dev/instructions/dwqdaiwenqi/claude-code-web/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dwqdaiwenqi/claude-code-web/claude-md"><img src="https://agentmods.dev/badge/instructions/dwqdaiwenqi/claude-code-web/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,087 This file is loaded in full into every session.
When invoked 1,087 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01087 $0.01087
Opus 5 $0.00544 $0.00544
Sonnet 5 $0.00217 $0.00217
Haiku 4.5 $0.00109 $0.00109

Measured 6d ago against content hash d817e1b809bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

claude-code-web 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 6d 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 · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 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.

Overview

A monorepo that wraps the @anthropic-ai/claude-agent-sdk as a REST/SSE HTTP service (packages/server) with a React web UI (packages/web). The server exposes Claude Code as an HTTP API; the built frontend is embedded into the server's public/ directory for serving.

Prerequisite: Claude Code CLI must be installed and logged in (claude command available).

Commands

Root (monorepo)

pnpm dev           # Run both server and web in parallel (watch mode)
pnpm dev:server    # Server only (tsx watch)
pnpm dev:web       # Web only (vite --host)
pnpm build         # Build both packages, then copy web/dist → server/public
pnpm start         # Run the built server

packages/server

pnpm --filter @claude-web/server dev        # tsx watch src/cli.ts start
pnpm --filter @claude-web/server build      # tsup
pnpm --filter @claude-web/server typecheck  # tsc --noEmit

packages/web

pnpm --filter @claude-web/ui dev    # vite --host (default port 5173)
pnpm --filter @claude-web/ui build  # tsc -b && vite build

Release

pnpm release:server   # bump patch, build, npm publish @claude-web/server
pnpm release:ui       # bump patch, build, npm publish @claude-web/ui

Architecture

packages/server

Fastify HTTP server with these layers:

  • src/cli.ts — Commander CLI (claude-web start / link / unlink)
  • src/server.ts — Fastify setup: CORS, WebSocket, static files, Swagger, route registration
  • src/agent.ts — Core logic. Wraps @anthropic-ai/claude-agent-sdk's query() in two modes:
    • runAgent() — blocking, waits for completion
    • runAgentStream() — SSE streaming, emits part / done / error / ask_user events
  • src/store.ts — In-memory runtime session map + ~/.claude/projects path helpers. Sessions persist via Claude CLI's native JSONL format; runtime state (status, abort controller) lives in memory only.
  • src/routes/ — Three route files:
    • project.ts — list, link, unlink projects; file tree; file read
    • session.ts — create/delete sessions, message history, send message (blocking or SSE)
    • terminal.ts — WebSocket PTY via node-pty

Read the full file on GitHub · 88 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. 6d ago First seen · 88 lines · 1,087 tokens per session scan A d817e1b809bf

Subscribe to this mod's changes

claude-code-web CLAUDE.md is an instructions file published in the GitHub repository dwqdaiwenqi/claude-code-web (43 stars, last pushed 3mo ago), licensed MIT. It adds 1,087 tokens to every session, about $0.0054 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.

FrontendReactcladueclihttprestful-apiui
Related

Other instructions, from other repositories

react CLAUDE.md

Claude Code instructions for react/react, covering react, monorepo overview and current active work.

react/react · 87 tokens

tamagui AGENTS.md

AGENTS.md instructions for tamagui/tamagui, covering tamagui — agent operating contract, finish what you start, then merge it back, tamagui testing guide, running tests and kitchen sink tests.

tamagui/tamagui · 1,464 tokens

ui-components AGENTS.md

AGENTS.md instructions for starc007/ui-components, covering beui v2 — agent guide, commands, layout, component catalog and components (motion category — primitives).

starc007/ui-components · 6,559 tokens

core CLAUDE.md

Claude Code instructions for ReactUnity/core, covering claude.md, what this repo is, two package universes, pnpm workspace membership and commands.

ReactUnity/core · 6,035 tokens

core AGENTS.md

AGENTS.md instructions for ReactUnity/core, covering release workflow, write changelog files, example, fix button hover state and package references.

ReactUnity/core · 245 tokens

synerise-design CLAUDE.md

Claude Code instructions for Synerise/synerise-design, covering claude.md — synerise design system, project overview, code quality, components and testing.

Synerise/synerise-design · 1,400 tokens