Borrowing it
Nothing to install: this file belongs to neura-spheres/Ventus. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/neura-spheres/Ventus/main/CLAUDE.mdgit clone --depth 1 https://github.com/neura-spheres/VentusWrote 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/neura-spheres/ventus/claude-md)<a href="https://agentmods.dev/instructions/neura-spheres/ventus/claude-md"><img src="https://agentmods.dev/badge/instructions/neura-spheres/ventus/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.
<a href="https://agentmods.dev/instructions/neura-spheres/ventus/claude-md"><img src="https://agentmods.dev/badge/instructions/neura-spheres/ventus/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.03014 | $0.03014 |
| Opus 5 | $0.01507 | $0.01507 |
| Sonnet 5 | $0.00603 | $0.00603 |
| Haiku 4.5 | $0.00301 | $0.00301 |
Grade A, and why
Ventus 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 9d 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ventus — Claude Context File
Read
RULES.mdbefore writing any code. It defines naming, comments, wording, structure, and IPC conventions for this project. All code must match that style.
Rust desktop browser. Frameless window, Zen Browser-inspired UI, AI sidebar. Stack: WRY 0.38.2, TAO 0.28, WebView2 (Windows), SQLite (rusqlite), Tokio.
Architecture: Two-Layer WebView System
The most critical architectural concept. Two types of WebViews co-exist as Win32 child HWNDs:
Chrome WebView — full-window overlay (0,0,win_w,win_h), always on top via SetWindowPos(HWND_TOP).
- Contains all UI: toolbar, sidebar, AI sidebar, settings modal, new-tab page, overlays.
SetWindowRgnclips it to only the UI regions (toolbar strip + sidebar column + optional AI panel).- Outside the clip region: mouse events and painting fall through to the content WebViews below.
Content WebViews — one per tab, positioned below chrome in Z-order.
- Rect is
(content_x, toolbar_h, content_w, content_h). - In auto-hide-pinned mode:
content_x = sidebar_w. In all other modes:content_x = 0. - Managed by
build_content_webview()insrc/runtime/webviews.rs.
Key constraint: WM_MOUSELEAVE never fires when cursor moves from chrome clip region into content area (content is a sibling HWND, not the chrome's client). The content WebView's mousemove IPC is used instead to signal Rust to close the sidebar.
Single WebView2 environment (critical): The chrome WebView and all normal content tabs (+ popups) share ONE WebContext (content_web_context, profile webview_data). The context is created BEFORE the chrome builder, and chrome attaches via .with_web_context(...). WRY caches the ICoreWebView2Environment on the context and reuses it for every later WebView, so there is a SINGLE msedgewebview2.exe browser process tree (one GPU/network/storage utility set) under ventus.exe. Never build a WebView without a shared WebContext — a context-less WebViewBuilder makes WRY create a second environment (default <exe>.WebView2 dir) = a duplicate process tree in Task Manager. Incognito tabs intentionally use a separate incognito_web_context (ephemeral profile) → their own environment, only while incognito tabs exist. Because chrome shares the env, browser args (DoH, 3p-cookie block) can't be swapped at runtime — TabAction::ApplyWebSecurity relaunches the app (relaunch_self → --wait-for-pid + --restore-session). On exit, close_chrome_controller() runs before shutdown_webview2() so the shared browser process flushes its cookie DB before process::exit().
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.
- 9d ago First seen · 233 lines · 3,014 tokens per session scan A 3d799097d0d6
Ventus CLAUDE.md is an instructions file published in the GitHub repository neura-spheres/Ventus (2 stars, last pushed 11d ago), licensed MIT. It adds 3,014 tokens to every session, about $0.0151 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 2026-08-31.
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.
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.
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).
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).
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.
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.