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/yonatangross/orchestkit/browser-toolsnpx skills add yonatangross/orchestkit --skill browser-toolsgit clone --depth 1 https://github.com/yonatangross/orchestkitWrote 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/yonatangross/orchestkit/browser-tools)<a href="https://agentmods.dev/skills/yonatangross/orchestkit/browser-tools"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/browser-tools.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 | $0.00040 | $0.05139 |
| Opus 5 | $0.00020 | $0.02570 |
| Sonnet 5 | $0.00008 | $0.01028 |
| Haiku 4.5 | $0.00004 | $0.00514 |
Grade A, and why
browser-tools scanned grade A with 1 finding 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **`cookies set --curl <file>`** — auto-detects JSON, cURL, and Cookie-header formats for bulk cookie import. Hook still treats cookie-set as auth-state injection. How it starts
The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Tools — Security Wrapper
OrchestKit security wrapper for agent-browser. For command reference and usage patterns, use the upstream agent-browser skill directly. This skill adds safety guardrails only.
Command docs: Refer to the upstream
agent-browserskill for the full command reference (50+ commands: interaction, wait, capture, extraction, storage, semantic locators, tabs, debug, mobile, network, cookies, state, vault).
Upstream coverage (do not restate)
These topics belong to the vendor. Read them at the source; do not copy them back into this skill.
| Topic | First-party source |
|---|---|
| CLI command reference, snapshot and ref loop, waits, auth options, eval, config file | agent-browser skill · https://github.com/vercel-labs/agent-browser/blob/main/skills/agent-browser/SKILL.md |
Electron and desktop-app automation over CDP (connect, --cdp, webviews, tabs) |
https://github.com/vercel-labs/agent-browser/blob/main/skill-data/electron/SKILL.md |
| Slack workspace navigation and extraction recipes | https://github.com/vercel-labs/agent-browser/blob/main/skill-data/slack/SKILL.md |
| Running headless in a Vercel Sandbox microVM (deps, snapshots, cron) | vercel:vercel-sandbox skill · https://github.com/vercel-labs/agent-browser/blob/main/skill-data/vercel-sandbox/SKILL.md |
| Exploratory QA sweep with repro evidence (issue taxonomy, report template) | dogfood skill · https://github.com/vercel-labs/agent-browser/blob/main/skill-data/dogfood/SKILL.md |
Named .localhost dev URLs |
ork:portless skill · https://github.com/vercel-labs/portless |
Our delta over all of the above: references/ork-delta.md, covering where the safety hook does and does not apply, the shared rate-limit budget, and the local-URL policy.
Decision Tree
# Fallback decision tree for web content
# 1. Try WebFetch first (fast, no browser overhead)
# 2. If empty/partial -> Try Tavily extract/crawl
# 3. If SPA or interactive -> use agent-browser
# 4. If login required -> authentication flow + state save
# 5. If dynamic -> wait @element or wait --text
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.
- metadata.json 389 B
- references/ork-delta.md 4.0 KB
- references/upstream-dogfood.md 10 KB
- references/upstream-electron.md 6.2 KB
- references/upstream-sandbox.md 9.1 KB
- references/upstream-slack.md 7.5 KB
- references/upstream.md 2.5 KB
- rules/_sections.md 1.3 KB
- rules/_template.md 339 B
- rules/browser-auth-security.md 5.2 KB
- rules/browser-debug-recording.md 4.5 KB
- rules/browser-mobile-testing.md 2.8 KB
- rules/browser-portless-local-dev.md 3.3 KB
- rules/browser-rate-limiting.md 3.9 KB
- rules/browser-scraping-ethics.md 2.8 KB
- test-cases.json 3.6 KB
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.
- today First seen · 289 lines · 40 tokens per session scan A 469eb1307b02
browser-tools is a skill published in the GitHub repository yonatangross/orchestkit (225 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 5,139 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
seo-crawl
Agent-wide core connector rule: when any connected search console is used, discover its operations with listconnectortools and invoke each selected operation through callconnectortool; naming listsites or an analytics operation without the core invocation is not execution.
seo-tech-audit
Judge the technical SEO facts produced by seo-crawl and return falsifiable findings + a health score. This is pure analysis — it does no network I/O and only reasons over the crawl JSON.
geo-score
Score how citable/ready a page is for AI answer engines, from crawl facts. Pure analysis — no network, no model calls. Deterministic so it is drift-comparable.
seo-content
Heuristic content/GEO-readiness analysis of the visible text from seo-crawl. No network. Judgments are heuristic (marked Estimated); raw counts are Measured.
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).