Borrowing it
Nothing to install: this file belongs to johanjanssens/frankenwails. 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/johanjanssens/frankenwails/main/CLAUDE.mdgit clone --depth 1 https://github.com/johanjanssens/frankenwailsWrote 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/johanjanssens/frankenwails/claude-md)<a href="https://agentmods.dev/instructions/johanjanssens/frankenwails/claude-md"><img src="https://agentmods.dev/badge/instructions/johanjanssens/frankenwails/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/johanjanssens/frankenwails/claude-md"><img src="https://agentmods.dev/badge/instructions/johanjanssens/frankenwails/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 | $0.00755 | $0.00755 |
| Opus 5 | $0.00378 | $0.00378 |
| Sonnet 5 | $0.00151 | $0.00151 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
frankenwails 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 8d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FrankenWails
PHP as a native desktop app using FrankenPHP + Wails. No HTTP server.
Architecture
main.go— Wails app entry point. Initializes FrankenPHP, creates anhttp.Handlerthat serves PHP, and passes it to Wails'AssetServer. The WebView routes all requests through this handler in-process (no TCP).examples/— PHP demo pages served as the document root.calculator/— HTMX form posting to PHP (addition)htmx/— Four regions loading concurrently with staggered delaystodo/— SQLite-backed todo list (CRUD)files/— Local filesystem browser with file preview
Build
make php # Build PHP static library (first time only)
make build # Build the Go binary (dist/frankenwails)
make run # Build + launch the desktop app
make env # Auto-generate env.yaml for GoLand
Build tags: nowatcher desktop dev (required for Wails + FrankenPHP).
nowatcher— disables FrankenPHP's file watcher (not needed for desktop app, avoids building the watcher C++ dependency)desktop— required by Wails at runtimedev— required by Wails for development mode
The Go binary requires CGO with PHP headers. CGO flags are resolved from build/php. If env.yaml exists, the build skips flag resolution and assumes the environment is already configured (e.g., pointing to an external PHP build).
For GoLand, run make env to generate env.yaml, then configure GoLand to load it.
Key Patterns
Wails AssetServer (no HTTP server)
Wails intercepts all WebView navigation and routes it through a Go http.Handler. This is the core differentiator — FrankenPHP executes PHP without any network layer:
wails.Run(&options.App{
AssetServer: &assetserver.Options{
Handler: handler, // FrankenPHP handler
Middleware: func(next http.Handler) http.Handler {
return handler // Override Wails' default static handler
},
},
})
Request Flow
WebView URL request
→ Wails AssetServer intercept (in-process, no TCP)
→ http.Handler
→ Static file? → http.ServeFile()
→ .php file? → frankenphp.NewRequestWithContext() → frankenphp.ServeHTTP()
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.
- 8d ago First seen · 78 lines · 755 tokens per session scan A f7ae05f0beb7
frankenwails CLAUDE.md is an instructions file published in the GitHub repository johanjanssens/frankenwails (6 stars, last pushed 5mo ago), licensed MIT. It adds 755 tokens to every session, about $0.0038 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.
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.