Rail-Connector-MCP AGENTS.md

Rail-Connector-MCP AGENTS.md is an instructions file for Codex, OpenCode from SNComrade/Rail-Connector-MCP. It costs 251 tokens per session, scanned A, original, MIT.

A repository instruction file that tells coding agents how to work safely in the Rail Connector MCP project, including engineering rules and required checks.

In plain words
What is it for?
Guiding code changes, deciding which tests to run, protecting credentials and private data, and checking changes before pull requests or releases.
Why use it?
It keeps agent changes consistent with the project's security, privacy, testing, and same-computer requirements.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; mentions Codex.

Install

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.

agentmods
npx agentmods add instructions/sncomrade/rail-connector-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/SNComrade/Rail-Connector-MCP

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for Rail-Connector-MCP AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sncomrade/rail-connector-mcp/agents-md.svg)](https://agentmods.dev/instructions/sncomrade/rail-connector-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/sncomrade/rail-connector-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sncomrade/rail-connector-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 251 This file is loaded in full into every session.
When invoked 251 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00251 $0.00251
Opus 5 $0.00125 $0.00125
Sonnet 5 $0.00050 $0.00050
Haiku 4.5 $0.00025 $0.00025

Measured 5d ago against content hash 85894c865fa9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

Rail-Connector-MCP 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 5d 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.

AGENTS.md · 29 lines

What it actually says

Agent Instructions

This repository is public source. Never add credentials, session transcripts, Remote Control URLs, real conversation identifiers, local usernames, machine names, absolute personal paths, customer data, or private project references.

Engineering Rules

  • Preserve the same-OS contract: Codex, this MCP server, and Claude Code run in the same operating-system context.
  • Keep bypassPermissions behind both the process-level policy acknowledgement and the per-launch confirmation.
  • Treat requested, resolved, and observed launch posture as separate evidence.
  • Prefer transcript-backed completion over terminal spinner wording.
  • Add a focused regression test for parser, renderer, broker, session, or prompt transport changes.
  • Keep real-account acceptance opt-in and out of hosted CI.
  • Do not weaken workspace-root, broker-token, ownership, generation, or mutation lease checks.

Required Checks

Run npm test before submitting a pull request. Run the platform-specific installer and transport tests when changing installers, Windows broker code, or the tmux backend. Run npm run check:privacy before any release candidate.

Security reports belong in GitHub private vulnerability reporting, not public issues. See SECURITY.md.

Changes

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.

  1. 5d ago First seen · 29 lines · 251 tokens per session scan A 85894c865fa9

Subscribe to this mod's changes

Rail-Connector-MCP AGENTS.md is an instructions file published in the GitHub repository SNComrade/Rail-Connector-MCP (0 stars, last pushed 2d ago), licensed MIT. It adds 251 tokens to every session, about $0.0013 per session on Opus 5. 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.