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.
git clone --depth 1 https://github.com/christopherlouet/claude-baseWrote 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/christopherlouet/claude-base/qa-chrome)<a href="https://agentmods.dev/commands/christopherlouet/claude-base/qa-chrome"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/qa-chrome/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/commands/christopherlouet/claude-base/qa-chrome"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/qa-chrome.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 | $0.00000 | $0.00219 |
| Opus 5.5 | $0.00000 | $0.00088 |
| Sonnet 5.5 | $0.00000 | $0.00044 |
| Haiku 4.5 | $0.00000 | $0.00022 |
Grade A, and why
qa-chrome 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 1mo 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.
What it actually says
QA-CHROME Agent (Chrome visual tests)
Visual tests and browser debugging via Claude Code's Chrome integration.
Prerequisites
- Launch Claude Code with:
claude --chrome - "Claude in Chrome" extension installed (v1.0.36+)
Usage
Performs a visual audit of the specified page or URL: $ARGUMENTS
Capabilities
- Navigation and interaction with web pages
- Reading console errors and logs
- DOM inspection and CSS styles
- Network request monitoring
- Screenshots and GIF recording
- Responsive testing (mobile, tablet, desktop)
Workflow
- Verify Chrome connection (
/chrome) - Open the target page
- Inspect: console, errors, layout
- Test responsive: 375px, 768px, 1440px
- User journey: main interactions
- Capture anomalies
- Generate the report
Output
Structured report:
- Critical errors with captures
- Warnings and suggestions
- Overall score (/10)
- Improvement recommendations
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.
- 1mo ago First seen · 40 lines · 0 tokens per session scan A 1c20c5c15f7d
qa-chrome is a command published in the GitHub repository christopherlouet/claude-base (5 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 219 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 2026-09-03.
Other commands, from other repositories
bootstrap
Verify and repair the Claude Code toolkit installation.
health-check
Run diagnostics on Claude Code toolkit configuration and status.
deps-update
Audit and update dependencies safely.
run
Execute prompt(s) from ./prompts/ with automatic archiving - for structured prompt-based work.
auto-claude
Invoke Auto-Claude autonomous coding framework for complex feature implementation.
fix-issue
Analyze and fix the GitHub issue: $ARGUMENTS.