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/aitobyte/safemask/claude-mdgit clone --depth 1 https://github.com/AiToByte/SafeMaskWrote 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/aitobyte/safemask/claude-md)<a href="https://agentmods.dev/instructions/aitobyte/safemask/claude-md"><img src="https://agentmods.dev/badge/instructions/aitobyte/safemask/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 5.1 | $0.03878 | $0.03878 |
| Opus 5 | $0.01939 | $0.01939 |
| Sonnet 5 | $0.00776 | $0.00776 |
| Haiku 4.5 | $0.00388 | $0.00388 |
Grade C, and why
SafeMask CLAUDE.md scanned grade C 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 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- `.cargo/config.toml` currently pins an HTTP proxy at `127.0.0.1:7890`. CI strips it (`rm -rf .cargo/config*`); if you don't run that proxy locally, either remove/comment the file or override with your own. How it starts
The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code (claude.ai/code) when working in this repository.
Authority note.
AGENTS.mdat the repo root remains the day-to-day operator handbook and takes precedence for command flags, session notes, and short-lived context. This file focuses on stable architectural facts and conventions.
Project Overview
SafeMask is a Tauri v2 desktop application for industrial-grade local privacy masking, version 2.0.0. All processing — rules, regex, AI NER, records — runs 100% offline. There are no telemetry or remote reporting paths in the codebase.
- Backend: Rust 2024 edition, Tauri v2, ONNX Runtime (
ort2.0.0-rc.12), Rayon, mmap - Frontend: React 19 + TypeScript + Zustand + Tailwind v3 + Vite 6 (no routing library — tab state in Zustand)
- AI model:
openai/privacy-filterq4-quantized ONNX, auto-discovered undersrc-tauri/models/privacy-filter/(multiple search paths, see below) - Distribution: Windows (MSI + portable ZIP), macOS (DMG, arm64), Linux (AppImage + deb) via
tauri-actiononv*tag push
The frontend stack is not Vue 3 / Pinia. Any older document that says so is out of date.
Development Commands
# Install dependencies
npm install
# Full-stack dev (Vite + Tauri window)
npm run tauri dev
# Frontend-only dev server (127.0.0.1:18924, strictPort)
npm run dev
# Frontend typecheck + build (tsc, NOT vue-tsc)
npm run build
# Production bundle
npm run tauri build
Rust commands — run from the repo root, not src-tauri/. The repo is a Cargo workspace (resolver 2), and src-tauri is a member named SafeMask.
cargo check -p SafeMask
cargo fmt -p SafeMask
cargo clippy -p SafeMask -- -D warnings
cargo test -p SafeMask
cargo test -p SafeMask test_name -- --nocapture
- Rust tests live inline in
#[cfg(test)]modules — there is notests/directory. .cargo/config.tomlcurrently pins an HTTP proxy at127.0.0.1:7890. CI strips it (rm -rf .cargo/config*); if you don't run that proxy locally, either remove/comment the file or override with your own.
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.
- 6d ago First seen · 256 lines · 3,878 tokens per session scan C 71a03826e8e3
SafeMask CLAUDE.md is an instructions file published in the GitHub repository AiToByte/SafeMask (58 stars, last pushed 1mo ago), licensed MIT. It adds 3,878 tokens to every session, about $0.0194 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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).
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 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).
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.
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.
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.