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/iliaal/whetstoneWrote 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/iliaal/whetstone/ia-test-browser)<a href="https://agentmods.dev/commands/iliaal/whetstone/ia-test-browser"><img src="https://agentmods.dev/badge/commands/iliaal/whetstone/ia-test-browser/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/iliaal/whetstone/ia-test-browser"><img src="https://agentmods.dev/badge/commands/iliaal/whetstone/ia-test-browser.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 | $0.00015 | $0.02795 |
| Opus 5.5 | $0.00006 | $0.01118 |
| Sonnet 5.5 | $0.00003 | $0.00559 |
| Haiku 4.5 | $0.00002 | $0.00280 |
Grade A, and why
ia-test-browser 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 12d 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 — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Test Command
<command_purpose>Run end-to-end browser tests on pages affected by a PR or branch changes using agent-browser CLI.</command_purpose>
CRITICAL: Use agent-browser CLI Only
DO NOT use Chrome MCP tools (mcp__claude-in-chrome__*).
This command uses the agent-browser CLI exclusively. The agent-browser CLI is a Bash-based tool from Vercel that runs headless Chromium. It is NOT the same as Chrome browser automation via MCP.
If you find yourself calling mcp__claude-in-chrome__* tools, STOP. Use agent-browser Bash commands instead.
Introduction
QA Engineer specializing in browser-based end-to-end testing
This command tests affected pages in a real browser, catching issues that unit tests miss:
- JavaScript integration bugs
- CSS/layout regressions
- User workflow breakages
- Console errors
Pipeline context: Only an explicit caller delegation enables non-interactive mode. Use headless mode, test the supplied revision/scope, return failures as findings with severity, and report human-only checks or failures to the parent. Do not prompt from an unattended worker, install tools globally, or fix code unless that action is within the delegated scope.
Prerequisites
Setup
For agent-browser install/verify steps and the full command reference, see shared-references/agent-browser-cli.md. Step 0 below performs the runtime install check.
Main Tasks
0. Verify agent-browser Installation
Before starting ANY browser testing, verify agent-browser is installed:
command -v agent-browser
If unavailable, report the missing dependency. Install only when authorized; a pipeline worker returns the gap to its parent.
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.
- 12d ago Changed · +5 lines 0ab746bdef9a
- 14d ago Changed 2d882fa3cb3a
- 20d ago Changed · +27 lines d14537814f2b
- 27d ago Changed 73d400b04b84
- 29d ago Changed e71d5bea4ec8
- 1mo ago Changed · +6 lines ae5c3ef34ee9
- 1mo ago First seen · 300 lines · 15 tokens per session scan A dc44f89e3d65
ia-test-browser is a command published in the GitHub repository iliaal/whetstone (35 stars, last pushed 2d ago), licensed MIT. It adds 15 tokens to every session and 2,795 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-07.
Other commands, from other repositories
recette
Tests d'acceptance automatises avec Claude in Chrome.
record
Record a browser walkthrough of a URL using Antigravity (agy). Generates .webm video, screenshots, and a report. Auto-converts to MP4 if ffmpeg is available.
playwright-cli
Automate browser interactions and inspect or test web pages through Playwright commands. Use when the task requires deterministic browser navigation, screenshots, selectors, or Playwright-test work. For a full local-webapp test workflow, use $webapp-testing.
webapp-testing
Exercise and verify a local web application through Playwright, including user flows and rendered behaviour. Use when testing a running local app rather than issuing an isolated browser command. For ad hoc automation, use $playwright-cli.
qa
Dispatch a verifiable browser task to the qa-tester subagent. Use for regression checks, smoke tests, and any task with a clean pass/fail outcome. Supports an EXHAUSTIVE mode that verifies every control behind an honesty gate.
qa
Pre-PR quality gate — browser-driven QA for web changes with a mandatory evidence packet against a provisioned environment. No QA-passed claim without artifacts. Workspace-aware. For a quick behavioral check without the evidence packet, prefer the bundled /verify or /run.