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/sendblue-api/sendblue-browser-use/sendblue-browsernpx skills add sendblue-api/sendblue-browser-use --skill sendblue-browsergit clone --depth 1 https://github.com/sendblue-api/sendblue-browser-useWrote 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/sendblue-api/sendblue-browser-use/sendblue-browser)<a href="https://agentmods.dev/skills/sendblue-api/sendblue-browser-use/sendblue-browser"><img src="https://agentmods.dev/badge/skills/sendblue-api/sendblue-browser-use/sendblue-browser.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 | $0.00075 | $0.02110 |
| Opus 5 | $0.00037 | $0.01055 |
| Sonnet 5 | $0.00015 | $0.00422 |
| Haiku 4.5 | $0.00007 | $0.00211 |
Grade A, and why
sendblue-browser scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://127.0.0.1:8787/health How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sendblue-browser
Long-running stealth Chromium (patchright) exposed via a tiny REST API. One process, many named sessions, durable cookies, one-click purge, and a CDP url for Playwright/Puppeteer to attach. Passes typical Cloudflare Turnstile and similar low-friction checks; not for hostile scraping at scale.
Repo: https://github.com/sendblue-api/sendblue-browser-use
Is the daemon running?
curl -s http://127.0.0.1:8787/health
If you get a JSON { ok: true, ... } response, skip to "Drive a session". Otherwise:
# Local dev (Bun)
cd <path-to-sendblue-browser-use>
touch .env
if [ -z "${BROWSER_USE_API_KEY:-}" ] && grep -q '^BROWSER_USE_API_KEY=' .env; then
export BROWSER_USE_API_KEY="$(grep '^BROWSER_USE_API_KEY=' .env | tail -1 | cut -d= -f2-)"
fi
export BROWSER_USE_API_KEY="${BROWSER_USE_API_KEY:-$(openssl rand -hex 32)}"
if grep -q '^BROWSER_USE_API_KEY=' .env; then
sed -i.bak "s/^BROWSER_USE_API_KEY=.*/BROWSER_USE_API_KEY=$BROWSER_USE_API_KEY/" .env && rm -f .env.bak
else
printf '\nBROWSER_USE_API_KEY=%s\n' "$BROWSER_USE_API_KEY" >> .env
fi
bun src/index.ts &
# Docker
docker compose up -d
Wait ~3s, then re-check /health. For later shell commands, reload the token with source .env.
Auth
Every endpoint except /health requires a bearer token (BROWSER_USE_API_KEY env var):
Authorization: Bearer $BROWSER_USE_API_KEY
Treat the token as local browser/network control: a token holder can run page scripts and navigate Chromium to private or localhost services reachable from the daemon host.
Drive a session
TOKEN="Authorization: Bearer $BROWSER_USE_API_KEY"
# 1. Create a session. persistent=false exposes a CDP url; persistent=true backs to an on-disk profile.
curl -s -X POST http://127.0.0.1:8787/sessions \
-H "$TOKEN" -H "Content-Type: application/json" \
-d '{"name":"qa","persistent":false,"viewport":{"width":1440,"height":900}}'
# 2. Navigate. http/https only; file:// and chrome:// are rejected. timeoutMs default 30s.
curl -s -X POST http://127.0.0.1:8787/sessions/qa/navigate \
-H "$TOKEN" -H "Content-Type: application/json" \
-d '{"url":"https://example.com/","waitUntil":"networkidle","timeoutMs":15000}'
# 3. Screenshot. ?fullPage=true and ?selector=CSS supported. Returns image/png.
# With NAV_SCREENSHOT_POLICY=headless (default), headed sessions skip automatic
# nav screenshots to avoid visible capture flicker. Call this explicitly for headed evidence.
curl -s "http://127.0.0.1:8787/sessions/qa/screenshot?fullPage=true" \
-H "$TOKEN" -o /tmp/shot.png
# 4. Eval JS in page. EXPRESSION FORM ONLY — wrap statements in an IIFE.
# Body cap 200 kB. 422 if the eval throws inside the page.
curl -s -X POST http://127.0.0.1:8787/sessions/qa/script \
-H "$TOKEN" -H "Content-Type: application/json" \
-d '{"code":"(() => ({ title: document.title, h1: document.querySelector(\"h1\")?.innerText }))()"}'
# 5. Cookies (Playwright shape: name+value + url OR domain+path)
curl -s -X POST http://127.0.0.1:8787/sessions/qa/cookies \
-H "$TOKEN" -H "Content-Type: application/json" \
-d '{"cookies":[{"name":"session","value":"abc","url":"https://example.com"}]}'
curl -s "http://127.0.0.1:8787/sessions/qa/cookies?url=https://example.com" -H "$TOKEN"
# 6. Console ring buffer (last N messages from page)
curl -s "http://127.0.0.1:8787/sessions/qa/console?limit=50" -H "$TOKEN"
# 7. Clear cookies + active-page storage but keep the session id
curl -s -X POST http://127.0.0.1:8787/sessions/qa/purge -H "$TOKEN"
# 8. Close + delete profile
curl -s -X DELETE http://127.0.0.1:8787/sessions/qa -H "$TOKEN"
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.
- 3d ago First seen · 172 lines · 75 tokens per session scan A 024a0f6f9459
sendblue-browser is a skill published in the GitHub repository sendblue-api/sendblue-browser-use (3 stars, last pushed 2mo ago), licensed MIT. It adds 75 tokens to every session and 2,110 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…
web-browser
Automate and interact with web pages through Chrome or Chromium using the Chrome DevTools Protocol (CDP): navigate, click, fill forms, inspect content, take screenshots, and debug console or network activity. Use when an agent needs a real browser. Prefer headless Chrome unless visible browser interaction is required.