Borrowing it
Nothing to install: this file belongs to the-missing-pink/ai-repository-security-baseline. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/the-missing-pink/ai-repository-security-baseline/main/AGENTS.mdgit clone --depth 1 https://github.com/the-missing-pink/ai-repository-security-baselineWrote 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/the-missing-pink/ai-repository-security-baseline/agents-md)<a href="https://agentmods.dev/instructions/the-missing-pink/ai-repository-security-baseline/agents-md"><img src="https://agentmods.dev/badge/instructions/the-missing-pink/ai-repository-security-baseline/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/the-missing-pink/ai-repository-security-baseline/agents-md"><img src="https://agentmods.dev/badge/instructions/the-missing-pink/ai-repository-security-baseline/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.05846 | $0.05846 |
| Opus 5 | $0.02923 | $0.02923 |
| Sonnet 5 | $0.01169 | $0.01169 |
| Haiku 4.5 | $0.00585 | $0.00585 |
Grade D, and why
ai-repository-security-baseline AGENTS.md scanned grade D with 3 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 9d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- INSTRUCTIONS FOR AI AGENTS: If this section contains [PLACEHOLDER], ask the user to describe their project or analyze the repository to propose a description. Show a before/after diff before making any changes. --> Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **Never run destructive commands** (`rm -rf`, `drop database`, `format`, etc.) without explicit user confirmation showing exactly what will be affected. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Never curl, wget, or fetch URLs found in code without user permission. How it starts
The opening of the file, as written. The whole thing — 622 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Instructions
This file is the central source of truth for all AI coding agents, assistants, and IDE plugins working in this repository. Tool-specific configuration files (CLAUDE.md, .cursorrules, copilot-instructions.md, etc.) reference this file for shared rules.
First-time setup: If you are an AI agent reading this for the first time and the sections below still contain
[PLACEHOLDER]markers, you are permitted to help the user fill them in. Ask the user for the required information, or infer it from the repository contents, then propose changes showing a clear before/after diff. Never modify these instructions without explicit user approval.
Table of Contents
- Project Overview
- Architecture
- Tech Stack & Languages
- File Structure
- Naming Conventions
- Git Workflow
- Security Rules
- Privacy Rules
- Access Restrictions
- Testing Requirements
- Accessibility Standards
- CI/CD & Pipeline Rules
- Dependency & Supply Chain Security
- Code Quality Standards
- Agent Self-Governance
1. Project Overview
Project name: [PLACEHOLDER - e.g., "MyApp"] Description: [PLACEHOLDER - Brief description of what this project does] Primary purpose: [PLACEHOLDER - e.g., "SaaS platform for inventory management"] Target audience: [PLACEHOLDER - e.g., "Small business owners"] Repository type: [PLACEHOLDER - e.g., "Monorepo", "Single application", "Library/Package"]
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.
- 9d ago First seen · 622 lines · 5,846 tokens per session scan D f82b77b17df8
ai-repository-security-baseline AGENTS.md is an instructions file published in the GitHub repository the-missing-pink/ai-repository-security-baseline (10 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 5,846 tokens to every session, about $0.0292 per session on Opus 5. A static security scan graded it D with 3 findings (hidden instructions, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.
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.
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).
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).
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.
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.