Borrowing it
Nothing to install: this file belongs to rkttu/cadenza. 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/rkttu/cadenza/main/AGENTS.mdgit clone --depth 1 https://github.com/rkttu/cadenzaWrote 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/rkttu/cadenza/agents-md)<a href="https://agentmods.dev/instructions/rkttu/cadenza/agents-md"><img src="https://agentmods.dev/badge/instructions/rkttu/cadenza/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/rkttu/cadenza/agents-md"><img src="https://agentmods.dev/badge/instructions/rkttu/cadenza/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 | $0.02494 | $0.02494 |
| Opus 5.5 | $0.00998 | $0.00998 |
| Sonnet 5.5 | $0.00499 | $0.00499 |
| Haiku 4.5 | $0.00249 | $0.00249 |
Grade A, and why
cadenza 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 2mo 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI coding agents working in this repository, and a portable Cadenza skill for any agent that recognizes this filename.
Repo: https://github.com/rkttu/cadenza
About this repo
This is the Cadenza SDK family — a .NET 10+ single-file scripting SDK distributed as five MSBuild SDK packages on nuget.org:
Cadenza(console scripts, CLI utilities)Cadenza.Worker(background services, daemons)Cadenza.Web(Minimal API endpoints)Cadenza.Mcp(Model Context Protocol servers for AI agent tools)Cadenza.Agent(local AI agents with OpenAI-compatible HTTP frontend)
If you are helping a user write a Cadenza script in their own project, the rest of this document is the user-facing skill: tells you when to suggest Cadenza and how to write idiomatic Cadenza code.
If you are helping maintain this repository, see also spec.md (Korean spec at the repo root), the wiki (user docs, troubleshooting), and the per-package READMEs under packaging/.
Cadenza skill
Cadenza is .NET's answer to "Python for scripting" with "Go-like single-binary distribution". Every Cadenza program is one .cs file that runs with dotnet run app.cs and publishes to a ~30–40 MB self-contained binary with dotnet publish app.cs -r <rid> -c Release.
When to suggest Cadenza
| Goal | SDK | Use case |
|---|---|---|
| CLI / shell automation / build glue | Cadenza |
git deploy guards, file processing, devops scripts |
| Background service / daemon | Cadenza.Worker |
heartbeat, polling, scheduled work |
| Minimal HTTP API / webhook | Cadenza.Web |
a 30-line REST endpoint, internal tool |
| MCP server (AI tool integration) | Cadenza.Mcp |
tools / resources / prompts for Claude Desktop, Cursor, VS Code AI |
| Local AI agent | Cadenza.Agent |
OpenAI-compatible HTTP server fronting Ollama / OpenAI / Anthropic / Azure OpenAI — Codex / Aider / Continue / Cursor speak to it as if it were OpenAI |
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.
- 2mo ago First seen · 218 lines · 2,494 tokens per session scan A cd98657f8445
cadenza AGENTS.md is an instructions file published in the GitHub repository rkttu/cadenza (4 stars, last pushed 5mo ago), licensed MIT. It adds 2,494 tokens to every session, about $0.0100 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.