mcp-farmer AGENTS.md

mcp-farmer AGENTS.md is an instructions file for Codex, OpenCode from boldare/mcp-farmer. It costs 617 tokens per session, scanned A, original, MIT.

A set of project instructions for mcp-farmer, a command-line tool for managing and analyzing MCP servers. It defines commands, exit codes, code style, validation, resource handling, and comment guidance.

In plain words
What is it for?
Use it when working on mcp-farmer’s TypeScript CLI, especially when running checks, designing functions, handling external input, or managing network and other resources.
Why use it?
It gives coding agents consistent rules for changing the project and helps catch unsafe input handling, unbounded operations, and unclear code structure.

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/boldare/mcp-farmer/agents-md
Clone the repo
git clone --depth 1 https://github.com/boldare/mcp-farmer

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-farmer AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/boldare/mcp-farmer/agents-md.svg)](https://agentmods.dev/instructions/boldare/mcp-farmer/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/boldare/mcp-farmer/agents-md"><img src="https://agentmods.dev/badge/instructions/boldare/mcp-farmer/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 617 This file is loaded in full into every session.
When invoked 617 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 $0.00617 $0.00617
Opus 5 $0.00309 $0.00309
Sonnet 5 $0.00123 $0.00123
Haiku 4.5 $0.00062 $0.00062

Measured 3d ago against content hash 7303ea222313, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-farmer 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 3d 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 · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

CLI tool for managing and analyzing MCP (Model Context Protocol) servers.

Quick Reference

  • Package manager: bun
  • Entry point: cli.ts
Command Purpose
bun run type-check TypeScript type checking
bun run lint ESLint
bun run test Run tests

Exit Codes

Code Meaning
0 Success/pass
1 Findings/fail
2 Invalid usage/error

Code Style

Function Design

  • Keep functions small and locally understandable
  • Push branching up; keep helpers mostly branch-free
  • Prefer helpers that compute values rather than mutate shared state

Boundaries

  • Validate and normalize all external inputs (CLI args, env, config files, network responses)
  • Prefer unknown + narrowing over any
  • Use exhaustiveness checks for unions (switch + assertNever) when the set of cases is fixed

Resource Limits

  • Time out all network operations
  • Bound retries, concurrency, and loops
  • Always use try/finally for connections and resources.

Comments

Add a comment when the reader would otherwise have to reverse-engineer intent, tradeoffs, or invariants. If a comment restates what the code already says, delete it.

Abstraction

Extract a helper only when it provides:

  • Reuse across multiple files
  • A type guard or assertion
  • A clear readability win in the calling code

Refactor after behavior is correct, not before.

Dependencies

Add a dependency only when it clearly reduces risk or complexity compared to writing it in-repo.

Testing

Workflow

Follow TDD (Red -> Green -> Refactor):

  1. Write a failing test that describes the next behavior
  2. Implement the smallest change to pass
  3. Refactor

Keep steps small: one behavior per test, small diffs, run tests frequently.

Test Structure

Use table-style tests when testing similar inputs with varying expected outputs.

Read the full file on GitHub · 105 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. 3d ago First seen · 105 lines · 617 tokens per session scan A 7303ea222313

Subscribe to this mod's changes

mcp-farmer AGENTS.md is an instructions file published in the GitHub repository boldare/mcp-farmer (5 stars, last pushed 7mo ago), licensed MIT. It adds 617 tokens to every session, about $0.0031 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.