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 instructions/navin2031992/mcpselenium/agents-mdgit clone --depth 1 https://github.com/navin2031992/mcpseleniumWhat 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 | $0.00948 | $0.00948 |
| Opus 5 | $0.00474 | $0.00474 |
| Sonnet 5 | $0.00190 | $0.00190 |
| Haiku 4.5 | $0.00095 | $0.00095 |
Grade A, and why
mcpselenium AGENTS.md 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.
This is a copy
100% identical to mcp-selenium AGENTS.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
MCP server for Selenium WebDriver browser automation. JavaScript (ES Modules), Node.js, stdio transport (JSON-RPC 2.0).
File Map
src/lib/server.js ← ALL server logic: tool definitions, state, helpers, cleanup
src/lib/accessibility-snapshot.js ← Browser-side JS injected via executeScript to build accessibility tree
bin/mcp-selenium.js ← CLI entry point, spawns server.js as child process
test/mcp-client.mjs ← Reusable MCP test client (JSON-RPC over stdio)
test/*.test.mjs ← Tests grouped by feature
test/fixtures/*.html ← HTML files loaded via file:// URLs in tests
Architecture
Server logic lives in server.js, with browser-injected scripts in separate files. 18 tools, 2 resources.
State is a module-level object:
const state = {
drivers: new Map(), // sessionId → WebDriver instance
currentSession: null, // active session ID
bidi: new Map() // sessionId → { available, consoleLogs, pageErrors, networkLogs }
};
Related operations are consolidated into single tools with action enum parameters (interact, window, frame, alert, diagnostics). This is intentional — it reduces context window token cost for LLM consumers.
BiDi (WebDriver BiDi) is auto-enabled on start_browser for passive capture of console logs, JS errors, and network activity. Modules are dynamically imported — if unavailable, BiDi is silently skipped.
Conventions
- ES Modules —
import/export, notrequire. - Zod schemas — tool inputs defined with Zod, auto-converted to JSON Schema by MCP SDK.
- Error pattern — every handler:
try/catch, return{ content: [...], isError: true }on failure. - No
console.log()— stdio transport. Useconsole.error()for debug output. send_keysclears first — callselement.clear()before typing. Intentional.- MCP compliance — before modifying server behavior, read the MCP spec. Don't violate it.
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 · 85 lines · 948 tokens per session scan A 72ebe56b99f3
mcpselenium AGENTS.md is an instructions file published in the GitHub repository navin2031992/mcpselenium (0 stars, last pushed 1mo ago), licensed MIT. It adds 948 tokens to every session, about $0.0047 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to mcp-selenium AGENTS.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
agentic-playwright selectors.instructions.md
Instructions for idavidov13/agentic-playwright, covering selector strategy, critical, instructions, phase 1: open and authenticate and phase 2: explore like a user.
scrapai-cli CLAUDE.md
Instructions for discourselab/scrapai-cli, covering claude.md, 1. who you are, 2. hard rules, 3. tools and 4. before you start: confirm the project.
chromeboost CLAUDE.md
Instructions for lordamdal/chromeboost, covering chromeboost — repo-developer guide, what chromeboost is, repository layout, development commands and tests/antibot/ (run locally; not in ci).
skills CLAUDE.md
Instructions for aemcoder/skills, covering claude.md, repository structure, slicc browser automation conventions, stateless tab targeting (since slicc pr #188) and tab-new returns a targetid.
xgrower-extension CLAUDE.md
Instructions for JoyyyceD/xgrower-extension, covering x grower extension — architecture notes, architecture, key files, auth flow and quota system.