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 mcp/bhuman-ai/qabro/beforeusersdogit clone --depth 1 https://github.com/bhuman-ai/QAbroGrade A, and why
beforeusersdo 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 2d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 2d ago First seen · 6 lines scan A 1731ecfe843b
beforeusersdo is an MCP server published in the GitHub repository bhuman-ai/QAbro (0 stars, last pushed 10d ago), with no licence file. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 2026-08-31.
Other mcp servers, from other repositories
vibe-testing
Code-aware browser testing agent — 13 Playwright tools for AI code editors via MCP. Runs locally from the vibe-testing npm package.
dsh-verify
Agent-built web app quality gate. Real browser is the judge. PASS/FAIL with receipts. Runs locally from the dsh-verify npm package.
writ-mcp
Official Writ MCP server connector — bridges a stdio MCP client (Claude Code, Claude Desktop, Cursor) to Writ Cloud or a self-hosted Writ coordinator. Turns your saved browser workflows into callable tools. Runs locally from the writ-mcp npm package.
arachne-mcp
🕷️ MCP server for Arachne — 56 tools: search, scrape, browser, vision, transcribe, RAG, Social Research, GitHub (trending/PRs/activity) + VRT visual (Oito Olhos). Runs locally from the arachne-mcp Python package. Needs 2 environment variables to run.
quanticdata-mcp
Live web access for agents: scrape, SERP search, crawl/map, 74 collectors, datasets, proxies. Runs locally from the quanticdata-mcp npm package. Needs 1 environment variable to run.
vibelens
VibeLens — an MCP server that gives AI coding assistants eyes on localhost: screenshots, console errors, and a token-optimized DOM snapshot. Runs locally from the mcp-vibelens npm package.