agentmods.dev

unifly AGENTS.md

Repository instructions for AI coding assistants working on Unifly, a Rust command-line and terminal interface tool for managing Ubiquiti UniFi networks.

In plain words
What is it for?
Use it when an agent needs to understand the Unifly codebase, run its commands, or follow the required checks before committing changes.
Why use it?
It gives agents one shared source for repository rules, commands, and checks before code is committed, reducing incorrect changes and missed validation.

Instructions file for CodexOpenCode

250 +1 26d ago A scan 9,275 tokens original Apache-2.0
View the source file hyperb1iss/unifly
Install

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.

agentmods
npx agentmods add instructions/hyperb1iss/unifly/agents-md
Clone the repo
git clone --depth 1 https://github.com/hyperb1iss/unifly

Made for: Codex, OpenCode.

Per session 9,275 This file is loaded in full into every session.
When invoked 9,275 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.09275 $0.09275
Opus 5 $0.04637 $0.04637
Sonnet 5 $0.01855 $0.01855
Haiku 4.5 $0.00928 $0.00928

Measured 2d ago against content hash 8a41e3ab7b0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

unifly 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 2d 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.

AGENTS.md · 847 lines

How it starts

The opening of the file, as written. The whole thing — 847 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Instructions for AI agents working on the unifly codebase. This file is the single source of truth for repository conventions. CLAUDE.md is a symlink to this file. Cursor, Codex, Aider, Cline, and Claude Code all read from here.

For end-user documentation see README.md. For contributor workflow see CONTRIBUTING.md. For how agents should use the unifly CLI at runtime see skills/unifly/SKILL.md (a separate audience from this file).

What This Repository Is

unifly is a Rust CLI and TUI for managing Ubiquiti UniFi network infrastructure. A single unifly binary ships three user-facing surfaces:

  • CLI commands (unifly devices list, etc.): 28 top-level commands (27 without the tui feature) covering devices and switch port management (ports / ports-export / port-set), clients, networks, WiFi, firewall (policies, zones, and groups), NAT, DNS, ACL, traffic-lists, hotspot, events, stats, DPI, VPN (servers, tunnels, site-to-site, remote-access, clients, connections, peers, magic-site-to-site, settings), Wi-Fi observability (neighbors, channels, roams, experience), site settings (settings), cloud fleet queries, and a raw api escape hatch.
  • TUI dashboard (unifly tui) -- 11-screen Ratatui interface for real-time monitoring and interactive management.
  • Agent skill at skills/unifly/SKILL.md: bundled documentation that teaches AI agents to drive the CLI.

The binary is powered by the unifly-api library crate, which is also published independently on crates.io for Rust developers building custom integrations.

The moat is triple-path coverage: unifly speaks the modern Integration API (REST, API key), the Session API (cookie + CSRF), and Site Manager cloud fleet/connector APIs. Most competing tools are one path or two; unifly can mix local and cloud workflows in one binary.

Quick Command Reference

The project uses just for task orchestration. All recipes live in the justfile at the repo root.

Read the full file on GitHub · 847 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. 2d ago First seen · 847 lines · 9,275 tokens per session scan A 8a41e3ab7b0e

Subscribe to this mod's changes

unifly AGENTS.md is an instructions file published in the GitHub repository hyperb1iss/unifly (250 stars, last pushed 26d ago), licensed Apache-2.0. It adds 9,275 tokens to every session, about $0.0464 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 2026-08-30.

Git and workflowLanguagesclinetworkingratatuiterminaltui
Related

Other instructions, from other repositories

longbridge-terminal CLAUDE.md

Instructions for longbridge/longbridge-terminal, covering claude.md, project overview, core architecture, tech stack and key modules.

longbridge/longbridge-terminal · 3,071 tokens

VTCode AGENTS.md

Instructions for vinhnx/VTCode, covering agents.md, rules, detailed guides, workspace and per-module guidance.

vinhnx/VTCode · 3,954 tokens

terminal AGENTS.md

Instructions for browser-use/terminal, covering agent notes, rust rewrite verification loop and terminal ui testing standard.

browser-use/terminal · 739 tokens

hex1b AGENTS.md

Instructions for mitchdenny/hex1b, covering ai coding agent guidelines for hex1b, 🛠️ available skills, 📋 project overview, key technologies and repository layout.

mitchdenny/hex1b · 3,232 tokens

waveloom AGENTS.md

Instructions for Menfre01/waveloom, covering waveloom, 项目概要, 编码规范, 代码审查 and 开发流程.

Menfre01/waveloom · 3,069 tokens

lazyazure AGENTS.md

AGENTS.md instructions for matsest/lazyazure, covering lazyazure - agent guidelines, project overview, critical guidelines, 1. tui development with gocui and 2. mutex best practices.

matsest/lazyazure · 9,566 tokens