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.
npx agentmods add instructions/lkbaba/claude-code-chatinwindows/claude-mdgit clone --depth 1 https://github.com/LKbaba/Claude-code-ChatInWindowsWrote 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.
[](https://agentmods.dev/instructions/lkbaba/claude-code-chatinwindows/claude-md)<a href="https://agentmods.dev/instructions/lkbaba/claude-code-chatinwindows/claude-md"><img src="https://agentmods.dev/badge/instructions/lkbaba/claude-code-chatinwindows/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.03280 | $0.03280 |
| Opus 5 | $0.01640 | $0.01640 |
| Sonnet 5 | $0.00656 | $0.00656 |
| Haiku 4.5 | $0.00328 | $0.00328 |
Grade A, and why
Claude-code-ChatInWindows 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Environment
- OS: Windows 10.0.19045
- Shell: Git Bash
- Path format: Windows (use forward slashes in Git Bash)
- File system: Case-insensitive
- Line endings: CRLF (configure Git autocrlf)
Build & Package
Compile:
npm run compile
Package VSIX (must use cmd wrapper, Git Bash swallows vsce output):
cmd //c "npx @vscode/vsce package --no-dependencies"
--no-dependencies: skipsnpm installduring packaging — dependencies are already innode_modulesfrom development; without this flag, vsce may fail or produce a bloated package- Do NOT use
npx @vscode/vsce packagedirectly in Git Bash — it silently fails (exit 0 but no .vsix generated) - Output file:
claude-code-chatui-{version}.vsix
Install VSIX for testing:
- VS Code:
Ctrl+Shift+P→ "Install from VSIX" - CLI:
code --install-extension claude-code-chatui-{version}.vsix
Debug (Extension Development Host):
Ctrl+Shift+D→ select "Run Extension" → click green play button- Remote desktop: F5 may be intercepted, use the play button instead
Architecture Overview
Data Flow
User input → Webview postMessage → ClaudeChatProvider
→ ClaudeProcessService (stdin JSON) → Claude CLI
→ stdout JSON stream → MessageProcessor → postMessage → Webview
Key Components
| Component | File | Role |
|---|---|---|
| Entry point | src/extension.ts |
Registers commands, subscriptions, status bar |
| Webview orchestrator | src/providers/ClaudeChatProvider.ts |
Owns all managers/services, handles all webview messages |
| CLI lifecycle | src/services/ClaudeProcessService.ts |
Spawn, kill, temp-file cleanup |
| Stream parser | src/services/MessageProcessor.ts |
JSON-line parsing, tool-use extraction, token/cost dispatch |
| Process mgmt | src/managers/WindowsCompatibility.ts |
Executable discovery, taskkill tree kill, shell env |
| Config facade | src/managers/config/ConfigurationManagerFacade.ts |
Combines VsCode + MCP + API config managers |
| Undo/redo | src/managers/UndoRedoManager.ts |
Strategy pattern — one strategy class per operation type |
| UI HTML | src/ui-v2/index.ts |
Assembles full HTML: CSP header + styles + body + script |
| UI script | src/ui-v2/ui-script.ts |
Entire frontend JS as a TypeScript template literal |
| UI body | src/ui-v2/getBodyContent.ts |
HTML body markup (settings panel, chat area, footer) |
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.
- 4d ago First seen · 211 lines · 3,280 tokens per session scan A c1def6384d9e
Claude-code-ChatInWindows CLAUDE.md is an instructions file published in the GitHub repository LKbaba/Claude-code-ChatInWindows (221 stars, last pushed 19d ago), licensed MIT. It adds 3,280 tokens to every session, about $0.0164 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.
Other instructions, from other repositories
superpowers-zh CLAUDE.md
Claude Code instructions for jnMetaCode/superpowers-zh, covering superpowers — 贡献者指南, 如果你是 ai agent, pull request 要求, 我们不会接受的内容 and 第三方依赖.
superpowers-zh GEMINI.md
Gemini CLI instructions for jnMetaCode/superpowers-zh, covering superpowers-zh 中文增强版, 核心规则, 可用 skills and 如何使用.
spec-kit-zh AGENTS.md
AGENTS.md instructions for loulanyue/spec-kit-zh, covering agents.md, about spec kit and specify, general practices, adding new agent support and current supported agents.
Meta_Kim CLAUDE.md
Claude Code instructions for KimYx0207/Meta_Kim, covering metakim for claude code, fast read, what this repository is, claude code's role and canonical vs runtime files.
nopua AGENTS.md
Instructions for wuji-labs/nopua, covering nopua · codex 入仓规则, 一 · 项目定位, 二 · 起手必读, 三 · 工程与研究纪律 and 四 · 对外署名.
claude-code-blueprint CLAUDE.md
Instructions for faizkhairi/claude-code-blueprint, covering global claude behavior rules, verify-after-complete (mandatory), what to verify depends on what was built, verification mindset and after verification.