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 agentmods add skills/codeinfinity1/stram/web-form-automationnpx skills add CodeInfinity1/Stram --skill web-form-automationgit clone --depth 1 https://github.com/CodeInfinity1/StramWhat 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 | $0.00031 | $0.00507 |
| Opus 5 | $0.00015 | $0.00253 |
| Sonnet 5 | $0.00006 | $0.00101 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
web-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 2d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Form Automation
Purpose
Help the assistant complete browser forms without guessing fields or submitting unintended data. This skill applies Actionbook-style form discipline through Stram's native browser tools.
When To Use
Use for account forms, contact forms, filters, search boxes, checkout-like forms, surveys, onboarding screens, and browser workflows with text fields, selects, or submit buttons.
Inputs And Evidence
- Target URL or existing browser session.
- Exact field values and any fields the user wants left blank.
- Observed form or element IDs.
- Confirmation/submit policy and final page state.
Tool Map
browser_openbrowser_observebrowser_typebrowser_fill_formbrowser_submit_formbrowser_live_observebrowser_live_typebrowser_live_fill_formbrowser_live_select_optionbrowser_live_press_keybrowser_live_click
Workflow
- Observe the form and identify fields from structured browser evidence.
- Map each user-provided value to a field; ask or stop when mapping is ambiguous.
- Fill fields through native browser tools.
- Re-observe and verify values before any submission.
- Submit only when the user explicitly asked and policy approval is satisfied.
- Verify the post-submit state or report the exact blocker.
Native Implementation Boundaries
- Use Stram browser tools and schemas.
- Do not import external reference Actionbook, browser-use, or upstream automation code.
- Do not use deterministic keyword matching to decide field semantics; use observed labels and model reasoning.
Safety And Approval
- Submitting forms, purchases, applications, messages, uploads, or account changes requires approval.
- Do not enter secrets, credentials, or payment details unless the user explicitly provides them for that session.
Verification
- Field values must be observed before submission.
- Submit result must be verified by page text, URL, status, or screenshot.
- If a captcha/login/payment appears, stop and report.
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.
- 2d ago First seen · 73 lines · 31 tokens per session scan A e64415ec5ea1
web-form-automation is a skill published in the GitHub repository CodeInfinity1/Stram (10 stars, last pushed 22d ago), licensed MIT. It adds 31 tokens to every session and 507 once invoked, about $0.0002 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
capture-screens
Automatically navigates a web app using Playwright MCP and captures context-aware named screenshots at each product feature state. Names each file semantically based on context (e.g., checkout-payment-form-filled.png). Outputs a manifest.json mapping filenames to descriptions and a summary report. Use when documenting…
fill-form
Fill out web forms with human-like anti-detection typing. Applications, registration, checkout, surveys, contact forms. Use when: "fill out form", "complete application", "register on", "submit form", "fill in details", "checkout", "sign up on".
get-started
Guide users through the get started setup and Chrome DevTools demo.
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.