Borrowing it
Nothing to install: this file belongs to cesarandreslopez/tauri-agent-tools. 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/cesarandreslopez/tauri-agent-tools/main/CLAUDE.mdgit clone --depth 1 https://github.com/cesarandreslopez/tauri-agent-toolsWrote 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/cesarandreslopez/tauri-agent-tools/claude-md)<a href="https://agentmods.dev/instructions/cesarandreslopez/tauri-agent-tools/claude-md"><img src="https://agentmods.dev/badge/instructions/cesarandreslopez/tauri-agent-tools/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 | $0.02869 | $0.02869 |
| Opus 5 | $0.01435 | $0.01435 |
| Sonnet 5 | $0.00574 | $0.00574 |
| Haiku 4.5 | $0.00287 | $0.00287 |
Grade A, and why
tauri-agent-tools 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 today.
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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project
tauri-agent-tools — A TypeScript CLI tool for agent-driven inspection and interaction with Tauri desktop applications. Captures real platform pixels of DOM elements by combining getBoundingClientRect positions with native screenshot tools (not canvas renders). DOM/storage/screenshot inspection reads state; evaluation can modify it and monitors install temporary instrumentation. Interaction commands (click, type, scroll, etc.) are debug-only.
Commands
npm run build # Compile TypeScript → dist/
npm test # Run vitest once
npm run test:watch # Vitest in watch mode
npm run dev # tsc --watch
Run a single test file:
npx vitest run tests/commands/screenshot.test.ts
Key Source Locations
| Location | Purpose |
|---|---|
src/cli.ts |
Entry point — registers all 38 commands via commander |
src/schemas/ |
Zod schemas split by domain: bridge.ts, dom.ts, commands.ts, platform.ts, interact.ts |
src/types.ts |
Pure interfaces: WindowInfo, PlatformAdapter, DisplayServer, WindowListEntry |
src/commands/ |
One file per command (screenshot.ts, dom.ts, eval.ts, wait.ts, info.ts, listWindows.ts, ipcMonitor.ts, consoleMonitor.ts, rustLogs.ts, storage.ts, pageState.ts, diff.ts, mutations.ts, snapshot.ts, check.ts, capture.ts, probe.ts, invoke.ts, storeInspect.ts, plus v0.7 additions: appPaths.ts, configInspect.ts, osLogs.ts, sidecarTap.ts, sidecarReplay.ts, forensics.ts, processTree.ts, capabilitiesAudit.ts, webviewAttach.ts, health.ts, diagnose.ts, plus v0.8 additions: logs.ts, bundle.ts) |
src/commands/interact/ |
Interaction commands: click.ts, type.ts, scroll.ts, focus.ts, navigate.ts, select.ts, shared.ts |
src/commands/shared.ts |
addBridgeOptions() and resolveBridge() — shared bridge option wiring |
src/platform/detect.ts |
detectDisplayServer() and ensureTools() — runtime platform detection |
src/platform/x11.ts |
X11 adapter: xdotool + ImageMagick import |
src/platform/wayland.ts |
Wayland/Sway adapter: swaymsg + grim |
src/platform/hyprland.ts |
Wayland/Hyprland adapter: hyprctl + grim |
src/platform/macos.ts |
macOS adapter: screencapture + osascript + sips |
src/bridge/client.ts |
BridgeClient class — HTTP POST to /eval and /logs endpoints |
src/bridge/tokenDiscovery.ts |
Token file scanning (/tmp/tauri-dev-bridge-*.token), PID liveness, stale cleanup |
src/util/image.ts |
cropImage(), resizeImage(), computeCropRect() — ImageMagick operations |
src/util/magick.ts |
magickCommand(), detectMagickVersion() — ImageMagick v6/v7 version detection and command resolution |
src/util/exec.ts |
exec() wrapper around execFile(), validateWindowId() |
src/util/logMerge.ts |
parseLogLine(), normalizeRustLog(), inferCorrelation() — log parsing/normalization for the logs command |
src/util/redactText.ts |
redactText(), redactJson(), redactDir(), scanResidualSecrets() — secrets/PII redaction for shared artifacts (bundle) |
src/util/mergeByTimestamp.ts |
mergeByTimestamp() — stable merge of timestamped streams into one UTC-ordered timeline |
src/util/psTree.ts |
snapshotProcesses(), buildDescendantTree() — OS process-tree walk for process-tree --deep / bundle |
examples/tauri-bridge/src/dev_bridge.rs |
Reference Rust bridge — compiled and tested in CI |
src/errors.ts |
Dependency-free CLI error codes, messages, and hints |
src/bridge/evaluate.ts / observers.ts / logReader.ts |
Typed global evaluation, independent collector sessions, and Rust log cursors |
src/util/monitor.ts |
Collector-lifetime signal scopes and final-sample polling |
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.
- today Changed · +8 lines · +254 tokens per session 94ef811f91e3
- 8d ago First seen · 134 lines · 2,615 tokens per session scan A 70301ad38050
tauri-agent-tools CLAUDE.md is an instructions file published in the GitHub repository cesarandreslopez/tauri-agent-tools (22 stars, last pushed yesterday), licensed MIT. It adds 2,869 tokens to every session, about $0.0143 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 2026-08-30.
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.