agentmods.dev

cnpg-mcp: Instructions file for Codex

AGENTS.md

cnpg-mcp AGENTS.md is an instructions file for Codex, OpenCode from waTeim/cnpg-mcp. It costs 879 tokens per session, scanned A, original, MIT.

An AGENTS.md instruction file that defines how an AI assistant should use an MCP server called MCP Base. It grants standing permission for the assistant to inspect and use that server’s available capabilities.

In plain words
What is it for?
Guiding assistants when they discover tools, resources, prompts, templates, or generated files exposed by MCP Base.
Why use it?
It removes repeated permission questions and sets a clear interaction style and authorization scope for work involving MCP Base.

Instructions file for CodexOpenCode

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

This is waTeim/cnpg-mcp's own configuration. It tells Codex and OpenCode how to work on cnpg-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cnpg-mcp configures →

not rated 1repo 2mo ago A scan 879 tokens original MIT
View source ↗ waTeim/cnpg-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to waTeim/cnpg-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/waTeim/cnpg-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/waTeim/cnpg-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 cnpg-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/wateim/cnpg-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/wateim/cnpg-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/wateim/cnpg-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/wateim/cnpg-mcp/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.

agentmods 80×15 button for cnpg-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/wateim/cnpg-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/wateim/cnpg-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 879 This file is loaded in full into every session.
When invoked 879 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00879 $0.00879
Opus 5.5 $0.00352 $0.00352
Sonnet 5.5 $0.00176 $0.00176
Haiku 4.5 $0.00088 $0.00088

Measured 2mo ago against content hash e579a5586a7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cnpg-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 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.

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 · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Standing authorization for MCP Base

The user grants standing permission to use the MCP server named MCP Base for any capability it exposes.

Assume full permission to discover, inspect, retrieve, invoke, and use everything available through MCP Base without asking the user first.

This authorization applies to all categories of MCP Base functionality, including but not limited to:

  • tools
  • tool schemas
  • resources
  • resource contents
  • prompts
  • prompt contents
  • templates
  • generated artifacts
  • read operations
  • write operations
  • multi-step tool chains
  • repeated follow-up calls needed to complete a task

Default behavior

Whenever MCP Base is relevant, use it proactively and immediately.

Do not ask the user for permission to:

  • list or inspect tools
  • call tools
  • list, open, or read resources
  • list, retrieve, or use prompts
  • follow links or references exposed by MCP Base
  • generate or retrieve artifacts
  • perform additional MCP Base calls that become relevant during the workflow

Do not pause to ask for confirmation for each new tool, prompt, resource, artifact, or follow-up action from MCP Base.

Authorization scope

Treat all capabilities exposed by MCP Base as pre-authorized, including actions that may modify, create, update, delete, or otherwise have side effects, whenever the task calls for them.

If a task can be completed more efficiently through MCP Base, prefer that route over asking the user to manually provide information or approve intermediate steps.

Interaction style

Do not ask questions such as:

  • “Should I use MCP Base?”
  • “Can I call this tool?”
  • “Can I open this resource?”
  • “May I use this prompt?”
  • “Do you want me to continue with MCP Base?”

Instead, act first and report what was done.

Example phrasing:

  • “I’m using MCP Base to complete this.”
  • “I retrieved the needed resource from MCP Base.”
  • “I invoked the relevant MCP Base tools and continued through the full workflow.”

Workflow expectation

Read the full file on GitHub · 102 lines

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. 2mo ago First seen · 102 lines · 879 tokens per session scan A e579a5586a7c

Subscribe to this mod's changes

cnpg-mcp AGENTS.md is an instructions file published in the GitHub repository waTeim/cnpg-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 879 tokens to every session, about $0.0035 per session on Opus 5.5. 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.

Related

cnpg-mcp AGENTS.md compared with instructions from other repositories

cnpg-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
cnpg-mcp AGENTS.mdwaTeim/cnpg-mcpInstructions file12mo agoMITA879Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,649GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot