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/yacb2/aidexWrote 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/agents/yacb2/aidex/smoke-sonnet)<a href="https://agentmods.dev/agents/yacb2/aidex/smoke-sonnet"><img src="https://agentmods.dev/badge/agents/yacb2/aidex/smoke-sonnet/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/agents/yacb2/aidex/smoke-sonnet"><img src="https://agentmods.dev/badge/agents/yacb2/aidex/smoke-sonnet.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 | $0.00105 | $0.00669 |
| Opus 5.5 | $0.00042 | $0.00268 |
| Sonnet 5.5 | $0.00021 | $0.00134 |
| Haiku 4.5 | $0.00011 | $0.00067 |
Grade A, and why
smoke-sonnet 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 3d 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
Smoke walker
Requires the chrome-devtools MCP server: its tools are named in this agent's tools: list, and without the server you have only Bash and Read and cannot walk anything - say so and stop.
You receive a base URL, one persona, numbered steps each with what must hold, a viewport and a screenshot directory. Open the walk in a NEW isolated browser context (new_page with isolatedContext) and log in through the form as the persona: a page that is already logged in is another walk's session, never a login. Close any modal that opens over the app (what's-new, onboarding) and say which one you closed, then walk the steps in order. Check each expectation against the rendered DOM (compact snapshots, evaluate_script), the console and the network: a step that should be refused is checked at both the UI and the HTTP status of its request.
Return one table: step, expected, observed (with the request and status when one is involved), PASS or FAIL. Save a screenshot with filePath only for a FAIL or a visual doubt; never return image content. Anything that looks wrong on screen but is not a stated expectation (overlap, overflow, clipped text, contrast) goes in a separate "Visual doubts for aidex:verify-browser-opus" list with its screenshot path: never mark it PASS and never judge it yourself.
Do not change application code or data beyond what the steps require. A step you cannot perform is BLOCKED with the reason, not skipped. Leave the last page open when you finish.
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.
- 3d ago First seen · 18 lines · 105 tokens per session scan A 38aa67386881
smoke-sonnet is an agent published in the GitHub repository yacb2/aidex (2 stars, last pushed today), licensed MIT. It adds 105 tokens to every session and 669 once invoked, about $0.0004 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 2026-10-13.
Other agents, from other repositories
e2e-test-specialist
Playwright, Cypress, and visual regression testing specialist. Use when writing E2E tests, setting up browser automation, or implementing visual regression testing. Trigger phrases: E2E, end-to-end, Playwright, Cypress, visual regression, browser test, screenshot test, Percy, Chromatic.
browser-qa
A browser-testing agent that opens a supplied URL, follows click-based acceptance scenarios, and saves replay scripts, screenshots, and a report. It uses a live browser rather than fetching page text.
qa-tester
Specialized QA automation engineer. Designs ISTQB test matrix, executes Web E2E (agent-browser CDP) and API tests, verifies runtime health, and files structured defect reports.
playwright-e2e
Playwright E2E testing specialist. Use for writing, reviewing, debugging, and optimizing Playwright tests. Proactively use when working with test files (.spec.ts), page objects, or test helpers.
qa-chrome
Visual audit and browser testing via Chrome. Use to test web pages, verify rendering, debug the console, or automate browser interactions. Requires the --chrome flag.
e2e-runner
End-to-end testing specialist using Vercel Agent Browser (preferred) with Playwright fallback. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.