Borrowing it
Nothing to install: this file belongs to sendblue-api/sendblue-browser-use. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sendblue-api/sendblue-browser-use/main/AGENTS.mdgit 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/instructions/sendblue-api/sendblue-browser-use/agents-md)<a href="https://agentmods.dev/instructions/sendblue-api/sendblue-browser-use/agents-md"><img src="https://agentmods.dev/badge/instructions/sendblue-api/sendblue-browser-use/agents-md/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/instructions/sendblue-api/sendblue-browser-use/agents-md"><img src="https://agentmods.dev/badge/instructions/sendblue-api/sendblue-browser-use/agents-md.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 | $0.01064 | $0.01064 |
| Opus 5.5 | $0.00426 | $0.00426 |
| Sonnet 5.5 | $0.00213 | $0.00213 |
| Haiku 4.5 | $0.00106 | $0.00106 |
Grade A, and why
sendblue-browser-use AGENTS.md 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 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.
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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — sendblue-browser-use
Spec: https://agents.md. This file is read by Codex, Cursor, Antigravity, Windsurf, Aider, Cline, Jules, Zed, and most other agents that follow the convention.
What this repo is
A standalone HTTP daemon that runs a stealth-patched Chromium (patchright) for browser automation. Long-lived process, bearer-token-gated REST API, optional CDP attach for any client (Playwright, Puppeteer, custom scripts). Passes typical Cloudflare Turnstile and similar low-friction checks; not for hostile scraping at scale.
Source layout:
src/— Bun + Hono HTTP servermcp/— MCP server wrapper (npm-publishable assendblue-browser-mcp)skills/sendblue-browser/SKILL.md— cross-agent skill (Claude / Codex / Antigravity / Cline).claude-plugin/plugin.json— Claude Code plugin manifestexamples/— Playwright / Puppeteer / multi-agent CDP attach snippetsDockerfile+docker-compose.yml— self-contained deploy
Setup
bun install
bun --bun x patchright install chromium
cp .env.example .env
# Set BROWSER_USE_API_KEY (any string ≥ 8 chars; generator: openssl rand -hex 32)
bun run dev # starts daemon on http://127.0.0.1:8787
Or Docker: docker compose up -d.
Common commands
# Health (no auth)
curl -s http://127.0.0.1:8787/health
# Create a session
curl -s -X POST http://127.0.0.1:8787/sessions \
-H "Authorization: Bearer $BROWSER_USE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"name":"qa","persistent":false}'
# Navigate (http/https only)
curl -s -X POST http://127.0.0.1:8787/sessions/qa/navigate \
-H "Authorization: Bearer $BROWSER_USE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"url":"https://example.com/","waitUntil":"networkidle","timeoutMs":15000}'
# Screenshot
curl -s "http://127.0.0.1:8787/sessions/qa/screenshot?fullPage=true" \
-H "Authorization: Bearer $BROWSER_USE_API_KEY" -o /tmp/shot.png
# Eval JS — expression form (wrap statements in IIFE)
curl -s -X POST http://127.0.0.1:8787/sessions/qa/script \
-H "Authorization: Bearer $BROWSER_USE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"code":"(() => document.title)()"}'
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 · 91 lines · 1,064 tokens per session scan A 84733567f004
sendblue-browser-use AGENTS.md is an instructions file published in the GitHub repository sendblue-api/sendblue-browser-use (3 stars, last pushed 4mo ago), licensed MIT. It adds 1,064 tokens to every session, about $0.0043 per session on Opus 5.5. 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.
sendblue-browser-use AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sendblue-browser-use AGENTS.mdsendblue-api/sendblue-browser-use | Instructions file | 3 | 4mo ago | MIT | A | 1,064 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |