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/boldare/mcp-farmer/agents-mdgit clone --depth 1 https://github.com/boldare/mcp-farmerWrote 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/boldare/mcp-farmer/agents-md)<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>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 | $0.00617 | $0.00617 |
| Opus 5 | $0.00309 | $0.00309 |
| Sonnet 5 | $0.00123 | $0.00123 |
| Haiku 4.5 | $0.00062 | $0.00062 |
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.
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 overany - 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/finallyfor 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):
- Write a failing test that describes the next behavior
- Implement the smallest change to pass
- 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.
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.
- 3d ago First seen · 105 lines · 617 tokens per session scan A 7303ea222313
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.
Other instructions, from other repositories
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
second-brain AGENTS.md
Instructions for LindaHaviv/second-brain, covering instructions for ai coding agents, what to read first, the rules (non-negotiable), common tasks, the sanctioned way and enforcement, not just instructions.