mcp-control-plane AGENTS.md

mcp-control-plane AGENTS.md is an instructions file for Codex, OpenCode from albertik322-sudo/mcp-control-plane. It costs 163 tokens per session, scanned A, original, MIT.

Repository instructions for an MCP control plane, a system that manages connections to tools and services used by coding agents.

In plain words
What is it for?
Use them when changing MCP servers or control-plane code, including running audits and tests and restarting long-running MCP processes.
Why use it?
They set a cautious workflow for checking health and permissions, protecting secrets, limiting remote changes, and testing runtime updates.

Instructions file for CodexOpenCode

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/albertik322-sudo/mcp-control-plane/agents-md
Clone the repo
git clone --depth 1 https://github.com/albertik322-sudo/mcp-control-plane

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 mcp-control-plane AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/albertik322-sudo/mcp-control-plane/agents-md.svg)](https://agentmods.dev/instructions/albertik322-sudo/mcp-control-plane/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/albertik322-sudo/mcp-control-plane/agents-md"><img src="https://agentmods.dev/badge/instructions/albertik322-sudo/mcp-control-plane/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 163 This file is loaded in full into every session.
When invoked 163 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 $0.00163 $0.00163
Opus 5 $0.00081 $0.00081
Sonnet 5 $0.00033 $0.00033
Haiku 4.5 $0.00016 $0.00016

Measured 5d ago against content hash 2b65ac37f90a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

mcp-control-plane 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 · 19 lines

What it actually says

Agent instructions

This repository is an MCP control plane. Begin with Context Store orientation and prefer the relevant MCP server over ad-hoc infrastructure shell commands.

Safe workflow

  1. Use codex_memory for project and tool capability context.
  2. Use read-only health, audit, and snapshot tools before mutations.
  3. Keep remote changes narrow, reversible, and explicitly authorized.
  4. Never print or store secret values.
  5. Preserve authorization checks inside MCP/API implementations.
  6. Run offline tests, the control-plane audit, and stateless conformance after MCP runtime changes.
  7. Restart long-lived MCP processes after code or dependency changes.

Do not commit .env, runtime state, infrastructure snapshots, captures, firmware, generated artifacts, vendored tools, or private operational data.

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 · 19 lines · 163 tokens per session scan A 2b65ac37f90a

Subscribe to this mod's changes

mcp-control-plane AGENTS.md is an instructions file published in the GitHub repository albertik322-sudo/mcp-control-plane (2 stars, last pushed 3d ago), licensed MIT. It adds 163 tokens to every session, about $0.0008 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.