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 commands/cesarandreslopez/tauri-agent-tools/domgit 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/commands/cesarandreslopez/tauri-agent-tools/dom)<a href="https://agentmods.dev/commands/cesarandreslopez/tauri-agent-tools/dom"><img src="https://agentmods.dev/badge/commands/cesarandreslopez/tauri-agent-tools/dom.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 | $0.00000 | $0.00772 |
| Opus 5 | $0.00000 | $0.00386 |
| Sonnet 5 | $0.00000 | $0.00154 |
| Haiku 4.5 | $0.00000 | $0.00077 |
Grade A, and why
dom 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 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.
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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dom
Query DOM structure from the Tauri app.
!!! note "Bridge Required" This command requires an active bridge connection.
Usage
tauri-agent-tools dom [selector] [options]
Options
| Option | Description | Default |
|---|---|---|
[selector] |
Root element to explore (positional argument) | body |
-s, --selector <css> |
Root element to explore (flag alternative) | — |
--mode <mode> |
Output mode: dom or accessibility |
dom |
--depth <number> |
Max child depth | 3 |
--tree |
Compact tree view (default) | — |
--styles |
Include computed styles (display, visibility, opacity, position, overflow) | — |
--text <pattern> |
Find elements containing this text (case-insensitive) | — |
--count |
Just output match count | — |
--first |
Only return first match (depth 0) | — |
--json |
Full structured JSON output | — |
--port <number> |
Bridge port (auto-discover if omitted) | — |
--token <string> |
Bridge token (auto-discover if omitted) | — |
Examples
Explore full page
tauri-agent-tools dom --depth 3
body (1920x1080)
div#app (1920x1080)
header.navbar (1920x64)
nav.nav-links (400x64)
main.content (1920x1016)
div.sidebar (300x1016)
Explore a subtree
tauri-agent-tools dom ".sidebar" --depth 2
Count matching elements
tauri-agent-tools dom --count ".list-item"
12
Include computed styles
tauri-agent-tools dom ".toolbar" --styles --json
Accessibility tree
tauri-agent-tools dom --mode accessibility --depth 2
[document]
[banner]
[navigation] "Main menu"
[link] "Home"
[link] "Settings"
[main]
[heading] "Dashboard" (level=1)
Find elements by text
# Find all elements containing "Settings"
tauri-agent-tools dom --text "Settings"
# Find within a specific subtree
tauri-agent-tools dom "#sidebar" --text "Settings"
# Get just the first match
tauri-agent-tools dom --text "Settings" --first
# Count matches
tauri-agent-tools dom --text "Settings" --count
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 · 125 lines · 0 tokens per session scan A b673ee16fb00
dom is a command published in the GitHub repository cesarandreslopez/tauri-agent-tools (22 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 772 tokens. 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 commands, from other repositories
recette
Tests d'acceptance automatises avec Claude in Chrome.
nodebench-qa
Full QA loop: crawl → findings → fix suggestions → re-crawl → savings report.
run-test
Execute AI agent test script in real browser.
can-i-use
Check browser support for web platform features against the project's browser targets.
interactive-dev
Start a persistent interactive development session with natural language browser control, auto-error monitoring, and full dev tool access.
scaffold
Scaffold a new project from a Starter Series template (Discord/Telegram bot, MCP server, browser/VS Code extension, Electron, React Native, Cloudflare Pages, npm package, Docker deploy).