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/hangboss1761/rule-link/agents-mdgit clone --depth 1 https://github.com/hangboss1761/rule-linkWrote 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/hangboss1761/rule-link/agents-md)<a href="https://agentmods.dev/instructions/hangboss1761/rule-link/agents-md"><img src="https://agentmods.dev/badge/instructions/hangboss1761/rule-link/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 5.1 | $0.00696 | $0.00696 |
| Opus 5 | $0.00348 | $0.00348 |
| Sonnet 5 | $0.00139 | $0.00139 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
rule-link 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to coding agents when working with code in this repository.
Project Overview
rule-link is a CLI tool for managing AI programming tool rule files through symbolic links. It helps developers maintain consistency across different AI assistants (Cursor, Claude Code, Gemini CLI, etc.) by creating symlinks from a single source file (typically AGENTS.md).
Development Commands
pnpm install- Install dependenciespnpm build- Build the project using tsdownpnpm dev- Build in watch modepnpm test- Run tests with Vitestpnpm typecheck- Run TypeScript type checkingpnpm release- Bump version and publish to npm
Architecture
The codebase follows a modular architecture with clear separation of concerns:
Core Modules
src/config.ts- AI tool configurations and constants. DefinesSUPPORTED_AI_TOOLSarray with tool-specific settings for file paths, native support, and configurability.src/types.ts- Core type definitions includingAIToolinterface andCreateOptions.src/utils.ts- Utility functions for symlink creation, file validation, and path operations.src/interactive.ts- Interactive CLI prompts and user selection logic using @inquirer/prompts.src/cli.ts- Command-line interface built with Commander.js, handles argument parsing and command routing.src/index.ts- Main entry point that re-exports all public APIs.
Key Concepts
- Source File: Default is
AGENTS.md(changed fromrule.mdfor better AI tool compatibility) - Target File: Default is
coding-standards.mdfor configurable tools - Native Support: Some tools (Cursor, Gemini CLI, Roo Code) natively read
AGENTS.mdfrom project root - Symbolic Links: Created for tools without native support to maintain consistency
AI Tool Configuration
Each AI tool in SUPPORTED_AI_TOOLS has:
name: Display namefileName/directoryTemplate: Target file pathisConfigurable: Whether tool supports custom target file namesnativeSupport: Whether tool natively supportsAGENTS.md
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 · 73 lines · 696 tokens per session scan A 8493a0f1c87f
rule-link AGENTS.md is an instructions file published in the GitHub repository hangboss1761/rule-link (1 stars, last pushed 11mo ago), licensed MIT. It adds 696 tokens to every session, about $0.0035 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
syncai AGENTS.md
Instructions for dmtrkzntsv/syncai, covering claude.md, build & run, architecture, lifecycle and identify is the routing decision.
syncai CLAUDE.md
Instructions for dmtrkzntsv/syncai, covering claude.md, build & run, architecture, lifecycle and identify is the routing decision.
aix GEMINI.md
Instructions for thoreinstein/aix, covering aix project context, tech stack, architecture, key concepts and development workflow.
matcha GEMINI.md
Gemini CLI instructions for plumpslabs/matcha, covering 🍵 matcha — antigravity cli convention, core rules, intensity, agents and session memory.
vivagents CLAUDE.md
Instructions for n0an/vivagents, covering claude.md, project overview, build & run, architecture and key files.
just-mcp CLAUDE.md
Instructions for toolprint/just-mcp, covering claude.md, project overview, essential development commands, quick start & setup and core development workflow.