llm-guard: Instructions file for Codex

AGENTS.md

llm-guard AGENTS.md is an instructions file for Codex, OpenCode from HendrikReh/llm-guard. It costs 3,941 tokens per session, scanned B, original, MIT.

Project guidance for AI coding agents working on LLM-Guard, a Rust tool that detects prompt injection and jailbreak indicators. It explains the hackathon context, project goals, key documents, and collaboration expectations.

In plain words
What is it for?
Use it when working on LLM-Guard features such as prompt scanning, transparent risk scoring, CLI or JSON output, and optional language-model analysis.
Why use it?
It gives an agent the project background and priorities needed to contribute safely and consistently to a fast-moving prototype.

Instructions file for CodexOpenCode

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

This is HendrikReh/llm-guard's own configuration. It tells Codex and OpenCode how to work on llm-guard 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 llm-guard configures →

Reuse

Borrowing it

Nothing to install: this file belongs to HendrikReh/llm-guard. 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/HendrikReh/llm-guard/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/HendrikReh/llm-guard

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 llm-guard AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hendrikreh/llm-guard/agents-md.svg)](https://agentmods.dev/instructions/hendrikreh/llm-guard/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/hendrikreh/llm-guard/agents-md"><img src="https://agentmods.dev/badge/instructions/hendrikreh/llm-guard/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,941 This file is loaded in full into every session.
When invoked 3,941 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.03941 $0.03941
Opus 5 $0.01971 $0.01971
Sonnet 5 $0.00788 $0.00788
Haiku 4.5 $0.00394 $0.00394

Measured 8d ago against content hash 6767ef0d37ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

llm-guard AGENTS.md scanned grade B with 1 finding 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 8d 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

- [ ] Code compiles without warnings
AGENTS.md · 590 lines

How it starts

The opening of the file, as written. The whole thing — 590 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Coding Assistant Onboarding Guide

Welcome to the AI Coding Hackathon!

This document provides essential context, conventions, and collaboration guidelines for AI coding assistants participating in hackathon projects. Follow these practices to contribute effectively and maintain code quality during rapid development.


1. Hackathon Context

1.1 Event Overview

You are assisting in the AI Coding Accelerator Hackathon organized by Maven.

Instructors: Vignesh Mohankumar and Jason Liu

Key Characteristics:

  • Fast-paced development (typically 1-day sprints)
  • Focus on working prototypes over perfect architecture
  • Balance between speed and code quality
  • Emphasis on demonstrable results

1.2 Current Project: LLM-Guard

Project Goal: Build a fast, explainable prompt injection detection tool in Rust

Core Objectives:

  • Scan prompts for injection/jailbreak indicators
  • Provide transparent risk scoring (0-100)
  • Support multiple output formats (CLI, JSON)
  • Optional LLM-powered analysis

Key Documents:

  • PRD.md - Product Requirements Document
  • PLAN.md - Implementation roadmap and progress tracking
  • README.md - User-facing documentation

2. Collaboration Philosophy

2.1 Speed vs Quality Balance

DO:

  • ✅ Implement features incrementally
  • ✅ Write tests for core logic
  • ✅ Use simple, explicit designs
  • ✅ Prioritize working code over perfect abstractions
  • ✅ Document non-obvious decisions in comments

DON'T:

  • ❌ Over-engineer solutions
  • ❌ Add unnecessary abstractions prematurely
  • ❌ Skip error handling entirely
  • ❌ Ignore the PRD requirements
  • ❌ Create features not explicitly requested

2.2 Communication Style

  • Be concise: Explain what you're doing and why, briefly
  • Ask when uncertain: Clarify requirements before implementing
  • Show progress: Use comments to indicate WIP sections
  • Acknowledge constraints: Call out hackathon trade-offs explicitly

Read the full file on GitHub · 590 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. 8d ago First seen · 590 lines · 3,941 tokens per session scan B 6767ef0d37ce

Subscribe to this mod's changes

llm-guard AGENTS.md is an instructions file published in the GitHub repository HendrikReh/llm-guard (3 stars, last pushed 10mo ago), licensed MIT. It adds 3,941 tokens to every session, about $0.0197 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens