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/wateim/cnpg-mcp/agents-mdgit clone --depth 1 https://github.com/waTeim/cnpg-mcpWrote 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.
[](https://agentmods.dev/instructions/wateim/cnpg-mcp/agents-md)<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="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00879 | $0.00879 |
| Opus 5 | $0.00439 | $0.00439 |
| Sonnet 5 | $0.00176 | $0.00176 |
| Haiku 4.5 | $0.00088 | $0.00088 |
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 4d 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.
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
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.
- 4d ago First seen · 102 lines · 879 tokens per session scan A e579a5586a7c
cnpg-mcp AGENTS.md is an instructions file published in the GitHub repository waTeim/cnpg-mcp (1 stars, last pushed 13d ago), licensed MIT. It adds 879 tokens to every session, about $0.0044 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.