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/.github/copilot-instructions.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/copilot-instructions)<a href="https://agentmods.dev/instructions/rkttu/cadenza/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/rkttu/cadenza/copilot-instructions.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 | $0.02248 | $0.02248 |
| Opus 5 | $0.01124 | $0.01124 |
| Sonnet 5 | $0.00450 | $0.00450 |
| Haiku 4.5 | $0.00225 | $0.00225 |
Grade A, and why
cadenza copilot-instructions.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 7d 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot instructions for Cadenza
This repository is the Cadenza SDK family — a .NET 10+ single-file scripting SDK distributed as five MSBuild SDK packages (Cadenza, Cadenza.Worker, Cadenza.Web, Cadenza.Mcp, Cadenza.Agent). The skill content below also applies when you (Copilot) help users write Cadenza scripts in other projects.
Repo: https://github.com/rkttu/cadenza
When to suggest Cadenza
Pick Cadenza when the user wants:
| 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 |
Skip Cadenza for multi-project solutions, libraries that ship as DLLs, or anything that needs a full csproj.
Critical: exact version pinning
MSBuild SDK references do NOT support wildcards (1.*). Always pin an exact SemVer version. Latest: 1.0.15.
#:sdk [email protected] // console
#:sdk [email protected] // worker
#:sdk [email protected] // web
#:sdk [email protected] // MCP server
#:sdk [email protected] // AI agent (OpenAI-compatible HTTP)
Tier 1 — bare names per variant (no namespace prefix needed)
Cadenza(console):Run(cmd),Capture(cmd),ReadText(path),WriteText(path, content),Glob(pattern),TempDir(), plusWriteLine/Write/ReadLine.Cadenza.Worker:Run(Func<CT, Task>),Config<T>(key).Log.Info/Warn/Error/Debugvia ILogger.Cadenza.Web:Get/Post/Put/Delete/Map(path, handler),Run().Web.App/Web.Servicesfor raw access.Cadenza.Mcp:Tool(name, desc, handler),Resource(uri, name, handler),Prompt(name, desc, handler),Run().Log.*→ stderr (never useWriteLinehere).Cadenza.Agent:Tool(name, desc, handler),SystemPrompt(text),UseOllama/UseOpenAi/UseAnthropic/UseAzureOpenAi/UseChatClient,Run()(HTTP server onlocalhost:8080— servesPOST /v1/chat/completionsANDPOST /v1/responses),ChatLoop()(REPL),Reply(prompt)(one-shot). Server-sideTool(...)auto-invokes on Chat Completion only; Codex CLI requires the Responses path and brings its own toolset.
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.
- 7d ago First seen · 200 lines · 2,248 tokens per session scan A cd2eff0fde00
cadenza copilot-instructions.md is an instructions file published in the GitHub repository rkttu/cadenza (4 stars, last pushed 3mo ago), licensed MIT. It adds 2,248 tokens to every session, about $0.0112 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
graftcode graftcode-dotnet.instructions.md
Instructions for grft-dev/graftcode, covering graftcode — .net backend services, when this applies (always), authoritative docs (source of truth), golden rules and service = .net class library.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).