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 rayven122/mcp-ie-migration-vrt --skill ie-migration-vrtgit clone --depth 1 https://github.com/rayven122/mcp-ie-migration-vrtWrote 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/rayven122/mcp-ie-migration-vrt/ie-migration-vrt)<a href="https://agentmods.dev/skills/rayven122/mcp-ie-migration-vrt/ie-migration-vrt"><img src="https://agentmods.dev/badge/skills/rayven122/mcp-ie-migration-vrt/ie-migration-vrt/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/rayven122/mcp-ie-migration-vrt/ie-migration-vrt"><img src="https://agentmods.dev/badge/skills/rayven122/mcp-ie-migration-vrt/ie-migration-vrt.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 | $0.00074 | $0.00566 |
| Opus 5.5 | $0.00030 | $0.00226 |
| Sonnet 5.5 | $0.00015 | $0.00113 |
| Haiku 4.5 | $0.00007 | $0.00057 |
Grade A, and why
ie-migration-vrt 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IE Migration VRT
Use the mcp-ie-migration-vrt tools to keep the legacy and migrated pages in separate Selenium sessions. Treat the IE session as expected and the Chromium Edge session as actual.
Workflow
- Call
start_vrt_browserswith the legacy and migrated URLs. Keep both returned session IDs. - Inspect each page through the accessibility resource or Selenium read tools. Always pass the intended
sessionId. - Operate each session independently until both represent the same business state. Do not assume the locators or navigation steps are identical.
- Wait for asynchronous content, fonts, and layout to settle. Avoid comparing loading indicators or transient animations.
- Call
vrtwithbeforeSessionId,afterSessionId, a stable checkpoint name, and the agreed viewport. - If the result is
different, inspect the returned before, after, and diff images together with the capture diagnostics. Distinguish an IE Driver edge, scrollbar, or DPI artifact from an application regression before modifying the migrated implementation. - Reload or navigate the after session back to the checkpoint and call
vrtagain. Repeat until it passes or a genuine intended design difference is identified. - Close both sessions explicitly.
Read capture-contract.md before changing viewport, zoom, scrolling, masking, or comparison thresholds.
Safety
- Do not submit, save, delete, approve, send, or trigger external actions unless the user explicitly authorizes that mutation.
- Use stable test data and reproduce the same state in both sessions.
- Do not resize or crop screenshots to force equal dimensions. Review raw dimension differences with their source images and diagnostics.
- Do not update the IE expectation merely to make a failure pass.
Failure handling
- If
start_vrt_browsersfails, confirm Windows, IEDriverServer, Edge IE mode policy, matching Protected Mode zone settings, and that the MCP server runs non-elevated in the logged-on interactive session. - If capture dimensions differ, first check the requested and measured viewport, document mode, browser zoom, DPI, overflow, and edge-only diff regions. Retry after fixing the environment when possible; otherwise record a confirmed environment-specific difference.
- If differences are limited to font antialiasing, adjust the threshold only after confirming there is no layout or typography regression.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 35 lines · 74 tokens per session scan A 8996a3a71949
ie-migration-vrt is a skill published in the GitHub repository rayven122/mcp-ie-migration-vrt (1 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 566 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.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.