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/steerlabs/opensteer/agent_skillsnpx skills add steerlabs/opensteer --skill agent_skillsgit clone --depth 1 https://github.com/steerlabs/opensteerWrote 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/steerlabs/opensteer/agent_skills)<a href="https://agentmods.dev/skills/steerlabs/opensteer/agent_skills"><img src="https://agentmods.dev/badge/skills/steerlabs/opensteer/agent_skills.svg" alt="Measured on agentmods" 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 | $0.00031 | $0.01617 |
| Opus 5 | $0.00015 | $0.00809 |
| Sonnet 5 | $0.00006 | $0.00323 |
| Haiku 4.5 | $0.00003 | $0.00162 |
Grade A, and why
opensteer 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 5d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Opensteer
Opensteer is a global browser-control runtime. It exposes small CDP primitives to agents and harness packs.
Usage
opensteer -c "open_browser(profile='fresh'); new_tab('https://example.com'); print(page_info())"
Python snippets run with helpers pre-imported:
opensteer -c "new_tab('https://docs.opensteer.com'); wait_for_load(); print(page_info())"
For harness code, import helpers from the installed package:
from opensteer.helpers import goto_url, js, click_at_xy, type_text, wait_for_load
Explicit Browser Sessions
For browser work, explicitly choose the browser profile and reuse mode. The returned handle is bound to exactly one platform session, and its stable identity makes the browser reusable by later CLI invocations and later agent runs:
opensteer -c "browser = open_browser(label='research', profile='fresh'); browser.new_tab('https://example.com')"
opensteer -c "browser = open_browser(label='work', profileId='bp_...'); print(browser.page_info())"
opensteer -c "browser = open_browser(profileId='bp_...'); print(browser.page_info())"
Use profile='auto' only when you deliberately want the platform to select the
sole granted profile (or an unprofiled browser when no grants exist).
mode='reuse' is the default. It selects the stable primary browser for this
agent, location, and profile. label is optional mutable display metadata: an
explicit different label renames that same browser in the UI; omitting it preserves
the current label. It never selects or creates a different browser. Use
mode='new' only when another independent logical browser is intentional.
profile='fresh' means no saved profile is attached. It does not guarantee a
new, clean, or signed-out browser because mode='reuse' may return a
previously used unprofiled browser, including from an earlier run. Use
profile='fresh', mode='new' when separate
clean state is required.
Read helpers never create a cloud browser. If no browser is active, call
open_browser(...) first.
What ships with it
16 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.
- interaction-skills/connection.md 2.0 KB
- interaction-skills/cookies.md 119 B
- interaction-skills/cross-origin-iframes.md 165 B
- interaction-skills/dialogs.md 2.3 KB
- interaction-skills/downloads.md 160 B
- interaction-skills/drag-and-drop.md 168 B
- interaction-skills/dropdowns.md 193 B
- interaction-skills/iframes.md 168 B
- interaction-skills/network-requests.md 196 B
- interaction-skills/print-as-pdf.md 171 B
- interaction-skills/screenshots.md 1.0 KB
- interaction-skills/scrolling.md 173 B
- interaction-skills/shadow-dom.md 147 B
- interaction-skills/tabs.md 2.1 KB
- interaction-skills/uploads.md 10 B
- interaction-skills/viewport.md 128 B
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.
- 5d ago First seen · 161 lines · 31 tokens per session scan A a77a8797d06b
opensteer is a skill published in the GitHub repository steerlabs/opensteer (202 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 1,617 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 2026-08-30.
Other skills, from other repositories
CBrowser
Cognitive Browser — AI browser automation that simulates real user cognition. 122 MCP tools, 21 personas, 25 cognitive traits, constitutional safety, cognitive journeys with LLM-free trace replay, screen capture to GIF/WebP/WebM with an AI-readable frame manifest (v18.69.3). USE WHEN browser automation OR cognitive…
webcmd-browser
Use when a live browser task requires Playwright interaction, authenticated handoff, visible UI verification, or ad-hoc page inspection.
browser-automation
Playwright-based browser automation patterns for autonomous web interaction.
moli-webfetch
Fetch, inspect, crawl, and capture live, JavaScript-rendered websites with Moli. Use when Codex needs current web content, web research, fact lookup, link following, a bounded crawl, client-rendered or response-gated content, network diagnostics, or a standalone HTML, Markdown, JSON, semantic-tree, viewport or…
moli-cdp-server
Start Moli's CDP server and connect Playwright, Puppeteer, or raw CDP clients. Use to run a headless-browser CDP endpoint, replace a Chromium process, attach over CDP, enable real layout and screenshot surfaces, or diagnose CDP discovery, connection, and target startup—even when Moli is not named.
playwright-bot-bypass
This skill should be used when the user asks to "bypass bot detection", "avoid CAPTCHA", "stealth browser automation", "undetected playwright", "bypass Google bot check", "rebrowser-playwright", or needs to automate websites that detect and block bots.