Borrowing it
Nothing to install: this file belongs to AiToByte/SafeMask. 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/AiToByte/SafeMask/main/AGENTS.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/agents-md)<a href="https://agentmods.dev/instructions/aitobyte/safemask/agents-md"><img src="https://agentmods.dev/badge/instructions/aitobyte/safemask/agents-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/aitobyte/safemask/agents-md"><img src="https://agentmods.dev/badge/instructions/aitobyte/safemask/agents-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 | $0.02565 | $0.02565 |
| Opus 5.5 | $0.01026 | $0.01026 |
| Sonnet 5.5 | $0.00513 | $0.00513 |
| Haiku 4.5 | $0.00257 | $0.00257 |
Grade C, and why
SafeMask AGENTS.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 2mo 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 proxy** in `.cargo/config.toml` (`127.0.0.1:7890`). CI explicitly strips it (`rm -rf .cargo/config*`). How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — SafeMask
First: existing CLAUDE.md is stale
The CLAUDE.md in this repo describes Vue 3 + Pinia — that is wrong. The frontend is React 19 + Zustand. Trust AGENTS.md over CLAUDE.md.
Commands
# Frontend typecheck (tsc, not vue-tsc — noEmit mode)
npm run build
# Rust (run from repo root, not src-tauri/)
cargo check -p SafeMask
cargo fmt -p SafeMask
cargo clippy -p SafeMask -- -D warnings
cargo test -p SafeMask # inline #[cfg(test)] modules
cargo test -p SafeMask test_name -- --nocapture
# Full dev
npm run tauri dev
# Frontend-only dev server (no Tauri window)
npm run dev
npm run build=tsc && vite build(TypeScript compiler, not vue-tsc)- Rust tests are inline
#[cfg(test)]modules only — notests/directory - Vite dev server runs on
127.0.0.1:18924, ports are strict
Architecture
Workspace (Cargo workspace, resolver 2)
SafeMask/ # repo root — Cargo workspace
├── src-tauri/ # workspace member
│ └── src/
│ ├── main.rs # binary entrypoint (Tauri setup)
│ ├── lib.rs # library entrypoint (re-exports modules)
│ ├── api/ # #[tauri::command] IPC handlers
│ ├── core/ # pure business logic (no Tauri deps)
│ │ ├── hybrid_engine.rs # main engine
│ │ ├── recognizer/ # pluggable recognizers (AC, regex, NER, checksum)
│ │ ├── resolver/ # conflict resolution
│ │ ├── masking/ # masking strategies
│ │ └── orchestrator/ # business orchestration (SceneMode)
│ ├── common/ # AppState, AppError, event constants
│ └── infra/ # clipboard, fs (mmap pipeline), config, AI (ONNX)
├── src/ # React 19 frontend
│ ├── App.tsx # root component
│ ├── main.tsx # ReactDOM.createRoot
│ ├── hooks/useAppStore.ts # Zustand store
│ └── services/api.ts # Tauri IPC wrappers (invoke)
├── tsconfig.json # paths: "@/*" -> "./src/*"
└── vite.config.ts # @vitejs/plugin-react
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.
- 2mo ago First seen · 139 lines · 2,565 tokens per session scan C 9107edcf70a0
SafeMask AGENTS.md is an instructions file published in the GitHub repository AiToByte/SafeMask (60 stars, last pushed 3mo ago), licensed MIT. It adds 2,565 tokens to every session, about $0.0103 per session on Opus 5.5. 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.
SafeMask AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| SafeMask AGENTS.mdAiToByte/SafeMask | Instructions file | 60 | 3mo ago | MIT | C | 2,565 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |