stagehand-browser SKILL.md skillB

stagehand-browser from badmuriss/my-llm-kit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add badmuriss/my-llm-kit/stagehand-browser@git:20260930.7adf45e

Pins git:20260930.7adf45e in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
badmuriss/my-llm-kit
Path
skills/stagehand-browser/SKILL.md
Versions recorded
2
Latest version
git:20260930.7adf45e, committed Sep 30, 2026
First version recorded
Sep 30, 2026
Size
8,509 bytes
Repository stars
3
License
MIT

Automate Chromium with local Stagehand 4 scripts for navigation, interaction, extraction, screenshots and deterministic browser checks in any harness. An optional OMP extension exposes the same runtime as a tool. Preserve existing Playwright runners where their fixtures, WebKit/Firefox coverage or visual assertions are required.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Stagehand Browser

Use the current agent to decide actions and Stagehand to execute them. This path
uses no separate model key, Browserbase account, Model Gateway or OAuth-token bridge.
It is deterministic browser automation, not `act`, `observe` or AI `extract`.

## Installation and ownership

Use the kit's README installation instructions to link or copy this complete
skill into the shared skill directory. Resolve the installed skill's `tools/`
directory and install its locked dependencies there:

```text
npm ci --ignore-scripts --no-audit --no-fund
```

Run that command with `tools/` as its working directory, outside the consumer
project. `package.json` and its lockfile pin Stagehand 4.1.0; Node >=22.18 and
installed Chrome are required. Any harness can import `openSession` from
`<skill-dir>/tools/session.mjs` in local scripts and close the session in `finally`.
Model roles, credentials, MCP servers and other browser tools stay untouched.

When the user selects the OMP tool, use OMP's actual native extension directory.
Add a loader that re-exports the default from this skill's `tools/omp-extension.mjs`
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add badmuriss/my-llm-kit/stagehand-browser@sha256:1fbd5009918b9bfc

The line at the top of this page pins the label git:20260930.7adf45e, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_fngs2fjgvisms2b2.svg)](https://markdownregistry.com/a/art_fngs2fjgvisms2b2)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, all committed on Sep 30, 2026.

versioncommittedcommitsizeaudit
git:20260930.7adf45e latest2026-09-30 7adf45e 8,509 BB view · diff
git:20260930.52333682026-09-30 5233368 8,211 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No link to a raw IP address (matched: http://127.0.0.1:3000)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8509 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

badmuriss/my-llm-kit · 3 stars · license MIT · pushed 2026-10-15 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_fngs2fjgvisms2b2
GET https://markdownregistry.com/api/v1/resolve?ref=badmuriss/my-llm-kit/stagehand-browser
GET https://markdownregistry.com/api/v1/blob/1fbd5009918b9bfc58ac2ffda2b6abb9ad76486f1351aed99b9de46a71a73774

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from badmuriss/my-llm-kit

AGENTS.md AGENTS.md file
badmuriss/my-llm-kit · AGENTS.md
git:20260930.7adf45e · audit A · 3 stars
AGENTS.md@instructions AGENTS.md file
badmuriss/my-llm-kit · instructions/AGENTS.md
git:20261014.e072b16 · audit A · 3 stars
agent-graph SKILL.md skill
badmuriss/my-llm-kit · skills/agent-graph/SKILL.md · Run durable task graphs when independent work needs ownership, integration checks and recovery. Use for graph…
git:20260930.5233368 · audit A · 3 stars
computer-use SKILL.md skill
badmuriss/my-llm-kit · skills/computer-use/SKILL.md · Inspect and operate browser or desktop interfaces with an available backend. Preserve existing browser suites; use…
git:20260930.5233368 · audit A · 3 stars
frontend-visual-validation SKILL.md skill
badmuriss/my-llm-kit · skills/frontend-visual-validation/SKILL.md · Verify rendered UI changes with reproducible screenshots and vision review on their supported platforms.
git:20260930.5233368 · audit A · 3 stars
remove-ai-marks SKILL.md skill
badmuriss/my-llm-kit · skills/remove-ai-marks/SKILL.md · Inspect and remove requested metadata or invisible marks from user-owned files. Use when provenance cleanup is…
git:20261001.2d71fc1 · audit B · 3 stars
research SKILL.md skill
badmuriss/my-llm-kit · skills/research/SKILL.md · Research external questions and compare evidence with source attribution. Use for research or fact-checking, not facts…
git:20261001.2d71fc1 · audit A · 3 stars
rule-curator SKILL.md skill
badmuriss/my-llm-kit · skills/rule-curator/SKILL.md · Audit an existing corpus of agent instructions for conflicts, duplication and unnecessary process. Use for a…
git:20260906.3d137c0 · audit A · 3 stars
CLAUDE.md@skills/rule-curator/evals/baseline-corpus CLAUDE.md file
badmuriss/my-llm-kit · skills/rule-curator/evals/baseline-corpus/CLAUDE.md
git:20260808.b08c042 · audit A · 3 stars
scrapingdog SKILL.md skill
badmuriss/my-llm-kit · skills/scrapingdog/SKILL.md · Collect specialized public data through ScrapingDog when its configured route is selected. Use for Maps, social…
git:20261001.2d71fc1 · audit A · 3 stars

Every file in badmuriss/my-llm-kit

Browse by kind, by grade B, or by owner.