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 5.5 | $0.00033 | $0.00322 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 2mo ago), licensed MIT. It adds 83 tokens to every session and 804 once invoked, about $0.0003 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 2026-08-31.
browser-form-automation compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| browser-form-automationcompanion-inc/introspect | Skill | 10 | 2mo ago | MIT | A | 83 | Claude Code, Codex |
| interactive-loginyc-software/qm | Skill | 16k | yesterday | MIT | A | 46 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |
| azure-messaging-webpubsub-javamicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 43 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | 3d ago | MIT | A | 68 | Claude Code, Codex |
| open-design-browsercompozy/compozy | Skill | 2.8k | yesterday | MIT | A | 56 | Claude Code, Codex |
| southwestborski/travel-hacking-toolkit | Skill | 895 | yesterday | MIT | A | 40 | Claude Code |