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/enuno/tailscale-acl/claude-mdgit clone --depth 1 https://github.com/enuno/tailscale-aclWrote 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/enuno/tailscale-acl/claude-md)<a href="https://agentmods.dev/instructions/enuno/tailscale-acl/claude-md"><img src="https://agentmods.dev/badge/instructions/enuno/tailscale-acl/claude-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 | $0.01421 | $0.01421 |
| Opus 5 | $0.00711 | $0.00711 |
| Sonnet 5 | $0.00284 | $0.00284 |
| Haiku 4.5 | $0.00142 | $0.00142 |
Grade A, and why
tailscale-acl CLAUDE.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 4d 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude AI Instructions for Tailscale ACL Repository
Project Context
This repository implements GitOps for Tailscale Access Control Lists, managing network security policies through infrastructure-as-code principles. You are an expert in Tailscale networking, zero-trust security, and GitOps workflows.
Core Competencies Required
- Tailscale Expertise: Deep understanding of ACL policies, device tags, user groups, and networking concepts
- Security Architecture: Zero-trust networking principles, least privilege access, and defense-in-depth strategies
- GitOps Proficiency: Infrastructure-as-code, automated deployment pipelines, and version-controlled configuration
- HuJSON Mastery: Human-readable JSON with comments, trailing commas, and proper formatting
Repository Architecture
Critical Files
policy.hujson: Main ACL policy file - NEVER rename this file as it breaks GitHub Actions integration.github/workflows/tailscale.yml: GitHub Actions workflow for ACL synchronization with TailscaleREADME.md: Project documentation and setup instructions- Various AI agent configuration files for development tool integration
ACL Policy Structure
{
"groups": {
// User groups for simplified access management
"group:engineering": ["[email protected]", "[email protected]"]
},
"tagOwners": {
// Define who can assign tags to devices
"tag:server": ["group:devops"]
},
"acls": [
// Network access control rules
{
"action": "accept",
"src": ["group:engineering"],
"dst": ["tag:server:22"]
}
],
"tests": [
// Automated validation of policy behavior
{
"src": "[email protected]",
"accept": ["tag:server:22"]
}
]
}
Development Workflow Standards
1. Policy Modification Process
- Create feature branch for all ACL changes
- Edit
policy.hujsonwith proper HuJSON formatting - Include descriptive comments explaining access decisions
- Add comprehensive test cases for new rules
- Create pull request with detailed change description
- Review security implications before merging
- Monitor GitHub Actions for successful deployment
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.
- 4d ago First seen · 205 lines · 1,421 tokens per session scan A d68c3a6c78fd
tailscale-acl CLAUDE.md is an instructions file published in the GitHub repository enuno/tailscale-acl (5 stars, last pushed 9mo ago), licensed Apache-2.0. It adds 1,421 tokens to every session, about $0.0071 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
agent-rules testing.instructions.md
Instructions for lirantal/agent-rules, covering testing guidelines for node.js applications, general testing principles, guiding principles, descriptive test naming (three-part structure) and structure tests by the aaa pattern.
yoloai CLAUDE.md
Instructions for kstenerud/yoloai, covering claude code specifics and the quality gate runs itself here.
cursor-handbook CLAUDE.md
Claude Code instructions for girijashankarj/cursor-handbook, covering claude.md — instructions for claude, project, critical rules, token efficiency (most important) and security (critical).
agent-rules child-process.instructions.md
Instructions for lirantal/agent-rules, covering system processes secure coding guidelines, your mission and spawning system processes.
agentforge CLAUDE.md
Instructions for mrzroot/agentforge, covering claude.md - project directives for claude code, project overview: agentforge, commands & environment, code architecture & philosophy and architectural conventions.
backend-pro-max-skill CLAUDE.md
Instructions for shashankswe2020-ux/backend-pro-max-skill, covering claude.md, project overview, search command, useful flags and domains.