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 skills add companion-inc/introspect --skill browser-form-automationgit clone --depth 1 https://github.com/companion-inc/introspectWrote 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/skills/companion-inc/introspect/browser-form-automation)<a href="https://agentmods.dev/skills/companion-inc/introspect/browser-form-automation"><img src="https://agentmods.dev/badge/skills/companion-inc/introspect/browser-form-automation/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/skills/companion-inc/introspect/browser-form-automation"><img src="https://agentmods.dev/badge/skills/companion-inc/introspect/browser-form-automation.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 | $0.00083 | $0.00804 |
| Opus 5 | $0.00042 | $0.00402 |
| Sonnet 5 | $0.00017 | $0.00161 |
| Haiku 4.5 | $0.00008 | $0.00080 |
Grade A, and why
browser-form-automation 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 11d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Form Automation
Use When
- The user asks you to configure or verify an authenticated web console, admin page, or form.
- You are editing origins, redirect URIs, secrets, settings, or multi-field config in Chrome, Browser, or another browser automation surface.
- A click/type attempt misses focus, typing lands nowhere,
cmd+aselects the page, a console or side panel steals focus, or coordinates have changed after scrolling.
Near misses:
- Read-only inspection or screenshots: use the Browser/Chrome skill directly.
- A single visible button/link with no text entry: a coordinate or vision click is fine, then check state.
- A provider API or secret-retrieval task: use
local-secret-retrievalfirst; use this skill only when you must operate the web UI.
Procedure
- Start with the relevant Browser/Chrome skill and its runtime docs. Prefer the browser's semantic API: Playwright locators, accessible labels,
form_input, or JavaScript DOM writes with dispatchedinput/changeevents. - Map the form before changing it: list visible inputs/buttons with labels, placeholders, current values, disabled state, and the current URL/account/project. Confirm it is the expected account/project before writing.
- Use coordinates only to expose or open a control. Do not use stale x/y clicks as the main data-entry method for text fields.
- After any missed-focus signal, stop coordinate typing immediately. Switch to locator/DOM entry before retrying. A second blind click/type sequence without new DOM evidence is the failure pattern.
- When using DOM writes, mimic user input enough for frameworks: set the value through the native setter when needed, dispatch
inputandchange, then read the field value back. - Verify the result from the page's own state before saving/submitting: current input values, selected options, validation messages, success toast, or saved detail page.
- If saving transmits secrets, credentials, or external state and the user's request did not already authorize that exact destination/action, follow browser safety confirmation. Otherwise finish the authorized flow.
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.
- 11d ago First seen · 48 lines · 83 tokens per session scan A 47b8f6fd4ebf
browser-form-automation is a skill published in the GitHub repository companion-inc/introspect (10 stars, last pushed 22d ago), licensed MIT. It adds 83 tokens to every session and 804 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…