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/4da-systems/victauri/claude-mdgit clone --depth 1 https://github.com/4DA-Systems/VictauriWrote 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/4da-systems/victauri/claude-md)<a href="https://agentmods.dev/instructions/4da-systems/victauri/claude-md"><img src="https://agentmods.dev/badge/instructions/4da-systems/victauri/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 | $0.27686 | $0.27686 |
| Opus 5 | $0.13843 | $0.13843 |
| Sonnet 5 | $0.05537 | $0.05537 |
| Haiku 4.5 | $0.02769 | $0.02769 |
Grade A, and why
Victauri 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 4d 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 — 1,109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Victauri — Claude Code Instructions
What Is Victauri
Victauri — Verified Introspection & Control for Tauri Applications.
X-ray vision and hands for AI agents inside Tauri apps. A browser tool with JS eval can poke a Tauri backend (Tauri exposes window.__TAURI_INTERNALS__.invoke, so it can invoke commands) — but only Victauri can read it safely. The database and the command registry have no eval_js equivalent — the backend tools read them through direct AppHandle access, independent of the webview; the IPC history is captured with request and response bodies (a browser's Performance API reports only HTTP 200 and exposes no bodies). And on macOS WKWebView / Linux WebKitGTK there is no Chrome DevTools Protocol surface for a CDP-based tool to attach to (those engines have their own, separate remote-inspector protocols; only WebView2 on Windows exposes a CDP-class surface). Victauri is one integration that sits inside the process on both sides of the boundary, giving agents simultaneous read-only access to the webview DOM, the Rust backend, the IPC layer, the database, and native window state — through a single MCP interface.
Stack: Pure Rust workspace (6 crates) | Target: Tauri 2.0 applications
Browser mode removed (2026-06-09). The
victauri-browsercrate + Chrome/Firefox extensions + npm package (@4da/victauri-browser) — an exploration to inspect any website — were deleted: off-thesis (Victauri's moat is being inside the Tauri process, where CDP/Playwright can't attach), the highest-risk surface (the only hostile-page boundary), and unused. Browser automation is better served by Playwright/CDP. Some deep historical "Current State" entries below still describe it as past context.
Commands
cargo build --workspace # Build all crates
cargo test --workspace # Run all Rust tests
cargo bench -p victauri-core # Criterion benchmarks (16)
cargo clippy --workspace --all-targets # Lint (20 enforced lints)
cargo fmt --all -- --check # Format check
RUSTDOCFLAGS="-D warnings" cargo doc --workspace --no-deps # Generate docs (zero warnings)
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.
- 4d ago First seen · 1,109 lines · 27,686 tokens per session scan A eea8f014ee27
Victauri CLAUDE.md is an instructions file published in the GitHub repository 4DA-Systems/Victauri (5 stars, last pushed 22d ago), licensed Apache-2.0. It adds 27,686 tokens to every session, about $0.1384 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
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
second-brain AGENTS.md
Instructions for LindaHaviv/second-brain, covering instructions for ai coding agents, what to read first, the rules (non-negotiable), common tasks, the sanctioned way and enforcement, not just instructions.