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/ghost-maxi/fivem-enhanced-mcp/agents-mdgit clone --depth 1 https://github.com/ghost-maxi/fivem-enhanced-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/ghost-maxi/fivem-enhanced-mcp/agents-md)<a href="https://agentmods.dev/instructions/ghost-maxi/fivem-enhanced-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ghost-maxi/fivem-enhanced-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 | $0.00445 | $0.00445 |
| Opus 5 | $0.00222 | $0.00222 |
| Sonnet 5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
fivem-enhanced-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 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Instructions
Scope
This repository contains one product: an unofficial, read-first MCP server and Codex skill for FiveM on GTAV Enhanced. Do not add support for FiveM Legacy, RedM, ESX, QBCore, ox_lib, or other frameworks without an approved design.
Structure
src/: MCP server, domain services, source adapters, and validators.tests/: unit, integration, and evaluation tests.skills/: bundled Codex workflow instructions and focused references.docs/: architecture, decisions, runbooks, and source policy..github/: CI, security automation, and contribution templates.assets/: repository and plugin presentation assets.
The reproducible standalone plugin bundle dist/index.cjs is committed so a
Git-backed plugin installation runs without lifecycle scripts. Other generated
output, coverage output, caches, and secrets are never committed. Official FiveM
documents and native corpora are referenced or cached at runtime; do not vendor
them into this repository without explicit license clearance.
Canonical commands
npm ci
npm run format:check
npm run lint
npm run typecheck
npm test
npm run test:coverage
npm run build
Use npm.cmd on Windows systems where PowerShell script execution blocks
npm.ps1.
Definition of done
- Tool schemas, annotations, structured outputs, and direct source URLs are accurate.
- Unknown or conflicting facts return an explicit status; they are never invented or silently resolved.
- Behavioral changes include tests and relevant evaluation cases.
- Format, lint, typecheck, tests, build, plugin validation, and Docker smoke tests pass.
- Performance claims include reproducible profiler, resmon, network, or NUI evidence.
- Security-sensitive inputs are validated and remote content is treated as untrusted data.
Review and commits
Use Conventional Commits. Keep changes atomic. Never weaken tests, annotations, source verification, or security checks to make CI pass. Do not push, publish, or change repository settings unless the user explicitly authorized it.
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.
- 5d ago First seen · 58 lines · 445 tokens per session scan A ffddeac070be
fivem-enhanced-mcp AGENTS.md is an instructions file published in the GitHub repository ghost-maxi/fivem-enhanced-mcp (2 stars, last pushed 5d ago), licensed MIT. It adds 445 tokens to every session, about $0.0022 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
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
netdata AGENTS.md
AGENTS.md instructions for netdata/netdata, covering agents.md, goals, requirement language, working with the user and development principles.
meme-search CLAUDE.md
Instructions for neonwatty/meme-search, covering claude.md, 📁 file organization guidelines, 🤖 task agent usage guidelines, when to use task agents and documentation lookup pattern.
selfhost-ai CLAUDE.md
Claude Code instructions for kossakovsky/selfhost-ai, covering claude.md, project overview, core architecture, key files and installation flow.
SForum AGENTS.md
AGENTS.md instructions for zhuchunshu/SForum, covering agent guide, project intent, working principles, stack and directory map and commands.
redd-archiver CLAUDE.md
Instructions for 19-84/redd-archiver, covering claude.md, project overview, deviations from global standards, build & run commands and docker development (primary method).