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/unoplatform/uno/agents-mdgit clone --depth 1 https://github.com/unoplatform/unoWhat 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 | $0.05074 | $0.05074 |
| Opus 5 | $0.02537 | $0.02537 |
| Sonnet 5 | $0.01015 | $0.01015 |
| Haiku 4.5 | $0.00507 | $0.00507 |
Grade A, and why
uno 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 3d 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 — 409 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI Agents when working with code in this repository.
Project Overview
Uno Platform is an open-source .NET UI cross-platform framework for building .NET applications from a single codebase using the WinUI 3 API. It targets Web (WebAssembly), Desktop (Windows, macOS, Linux via Skia), and Mobile (iOS, tvOS, Android).
Reference these instructions first, then lean on skills (workflows) and the path-scoped rules below.
Claude Code Skills (invoke via /skill-name)
| Skill | Command | Use For |
|---|---|---|
| Add Sample | /add-sample |
Creating SamplesApp sample pages with correct registration |
| Runtime Tests | /runtime-tests |
Building and running Uno runtime tests (Skia Desktop/WASM) |
| WinUI Runtime Tests | /winui-runtime-tests |
Running runtime tests against native WinUI on Windows |
| WinUI Porting | /winui-port |
Porting WinUI C++ code to Uno Platform C# (full deep reference) |
| DevServer | /devserver |
DevServer CLI/Host build, test, MCP proxy, add-in discovery |
| Docs Build | /docs-build |
Building, previewing & validating the docs website (DocFX), incl. external-doc commit bumps in import_external_docs.ps1 |
Pre-commit review (invoke via /review-panel)
/review-panel [scope] runs an eight-lens reviewer panel (architect, contract, skeptic, performance, operability, quality, security, jerome) in parallel and synthesizes one report with a ship / fix-first / block-merge verdict. Run it before you commit or open a PR — pass a scope (master..HEAD, a #PR, HEAD~1) or omit it to auto-detect uncommitted changes / branch-vs-master. The panel learns from corrections recorded in specs/lessons.md. Lenses, scopes, and loop recipes: .claude/review-panel-cheatsheet.md.
Path-scoped rules (.claude/rules/)
These load automatically when you touch matching files — you don't invoke them. They hold the non-obvious, subsystem-specific conventions so this always-loaded file stays lean:
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.
- 3d ago First seen · 409 lines · 5,074 tokens per session scan A fb0490a3778d
uno AGENTS.md is an instructions file published in the GitHub repository unoplatform/uno (10,030 stars, last pushed yesterday), licensed Apache-2.0. It adds 5,074 tokens to every session, about $0.0254 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.
Other instructions, from other repositories
web-to-app AGENTS.md
AGENTS.md instructions for shiaho777/web-to-app, covering agents.md, code style, project layout, how the main pieces connect and i18n.
Amarok-Hider AGENTS.md
Instructions for deltazefiro/Amarok-Hider, covering amarok, project overview, build, e2e test and agent rules.
OpenTagViewer AGENTS.md
Instructions for parawanderer/OpenTagViewer, covering agents.md, what this project is, rules, 1. never ship a room schema change without a migration and 2. do not claim something works if you have not run it.
sceneview AGENTS.md
Instructions for sceneview/sceneview, covering agents.md — conventions for delegated coding agents, your role, git — you do not own it, secrets and hard technical rules.
AppClaw CLAUDE.md
Instructions for appclawhq/AppClaw, covering claude.md, what is appclaw?, build & run commands, architecture and entry point & cli modes (src/index.ts).
scrcpy-mcp AGENTS.md
Instructions for JuanCF/scrcpy-mcp, covering agents.md, project overview, project documentation, build/lint/test commands and build the project.