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/pickjason/cc-windows/agents-mdgit clone --depth 1 https://github.com/pickjason/cc-windowsWhat 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 | $0.03036 | $0.03036 |
| Opus 5 | $0.01518 | $0.01518 |
| Sonnet 5 | $0.00607 | $0.00607 |
| Haiku 4.5 | $0.00304 | $0.00304 |
Grade B, and why
cc-windows AGENTS.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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
npm run install-hooks # = bash scripts/install-hooks.sh,装监控 hooks 到 ~/.claude/settings.json Copies of this mod
1 near-identical copy found in the catalogue:
- cc-windows CLAUDE.md — 97% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to coding agents (Codex, etc.) when working with code in this repository.
注意:cc-window 监控/管理的目标产品是 Claude Code(它的
claudeCLI、~/.claude目录、agents --json等都是真实事实,请勿改写成你自己所属的 agent 名)。本文件只是「写给在本仓库干活的 agent」看的说明。
项目本质
cc-window 是一个本地网页版 Claude Code 多会话管理台:一屏监控全机所有 Claude Code 会话状态、网页里新建会话、操作每个会话的交互式终端。仅监听 127.0.0.1:4317。
奠基事实(动手前务必理解):Claude Code 没有对外的 socket / 端口 / HTTP 查询接口。本项目的全部可观测性来自三件事的叠加,改任何状态/会话逻辑都绕不开这三个源:
- 轮询
claude agents --json(源 A,全量会话真相 + busy/idle/waiting) - tail
~/.claude/monitor/events.jsonl(源 B,hooks 写的秒级事件流,给出精确等待原因) - 自管 PTY(用
node-pty启动会话并桥接到浏览器 xterm.js)
详尽且已核实的事实在 docs/02-claude-code-observability.md——它是本仓库的基石文档,涉及 Claude Code 行为时先读它,不要凭记忆推断。
除实时管理外,还有一块历史用量统计(看板顶栏「📊 统计」入口):解析 ~/.claude/projects/**/*.jsonl 历史记录,出活跃热力图 / token 趋势 / 日报等。它复用同一批 transcript 文件,但做的是「回看历史用量」,与上面三源「看实时状态」是不同维度。承接独立工具 cc-journal,合并设计见 docs/11-merge-cc-journal.md。
常用命令
npm install # postinstall 自动 chmod +x node-pty 的 spawn-helper(见下方坑)
npm run dev # 开发:vite(5173,HMR)+ 后端(4317),浏览器开 http://127.0.0.1:5173
npm run build && npm start # 生产:构建后由后端单端口托管,开 http://127.0.0.1:4317
npm run typecheck # tsc --noEmit —— strict + noUncheckedIndexedAccess,覆盖 server/web 含 *.test.ts
npx tsx web/terminalResize.test.ts # 跑单个单元测试(无 npm test / 无 runner,逐个 tsx 跑)
npm run install-hooks # = bash scripts/install-hooks.sh,装监控 hooks 到 ~/.claude/settings.json
- 没有 linter、没有测试 runner(无
npm test),但有单元测试:核心纯逻辑被抽到无副作用的小模块(web/terminalResize.ts、server/tmux-handoff.ts等),每个配一个同名*.test.ts,用node:assert/strict断言、末尾console.log("... passed"),逐个npx tsx <file>.test.ts跑。改这类逻辑前先看有没有对应.test.ts,改完把它跑绿。 - 完整校验仪式(见
docs/10):跑齐全部 8 个*.test.ts+npm run typecheck+npm run build。tsconfig开了strict+noUncheckedIndexedAccess。 - hooks 安装器支持
--dry-run(只看 diff)与--uninstall(只移除本工具的 8 个 hook,保留其它);写入前自动备份 settings.json。需要jq。 - UI 改动按项目惯例用浏览器实机截图验证(mcp__claude-in-chrome)。
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.
- 2d ago First seen · 73 lines · 3,036 tokens per session scan B e3510cf11494
cc-windows AGENTS.md is an instructions file published in the GitHub repository pickjason/cc-windows (5 stars, last pushed 2mo ago), licensed MIT. It adds 3,036 tokens to every session, about $0.0152 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.