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/microsoft/tinytroupe/copilot-instructionsgit clone --depth 1 https://github.com/microsoft/TinyTroupeWhat 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 | $0.02629 | $0.02629 |
| Opus 5 | $0.01314 | $0.01314 |
| Sonnet 5 | $0.00526 | $0.00526 |
| Haiku 4.5 | $0.00263 | $0.00263 |
Grade A, and why
TinyTroupe 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 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.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guidelines for Code Generation in TinyTroupe
This document provides the primary guidelines for generating programs in the TinyTroupe project. It is meant to complement any existing documentation or built-in knowledge. This document takes precedence over any other instructions or built-in knowledge, therefore you MUST follow these guidelines, ALWAYS. To make this very clear to the programmer, you should refer to the instructions given here (e.g.," ... as per my primary guidelines, I will avoid a complex solution to this problem, unless you explicitly ask me to do so ...").
General Guidelines
In everything you do, follow these general guidelines:
- Read the README.md: Always read the README.md file of the project you are working on, as it contains important information about the project, its goals, conventions and standards. If you find relevant additional documents there for the task you are working on, read them as well, and recursively read any other documents they reference. Only then you can start working on the task.
- Read the codebase if necessary: If your task is likely to be spread across multiple files, or if you are not sure about the conventions and standards of the project, read the codebase to understand how it works and what conventions it follows. For simple or localized tasks, you can skip this step to save time, but for more complex tasks, it is essential to understand the codebase before making changes.
- Elegance: Be elegant in your solutions. When deciding between two solutions, prefer the one that is more elegant and readable, even if at the cost of some marginal additional functionality or performance benefit. Avoid unnecessary complexity.
- Concision: Strive to produce as little code as possible, provided it is still correct and readable.
- Ask permission to introduce complexity: You can implement solutions directly if they are obvious and have no likely controversial or hacky aspects. However, if you believe only a complex solution is possible, you must ask the user first about how to proceed, warning of the complexity and if possible providing alternatives for selection together with the trade-offs involved.
- Maintainability: Make sure the code you generate can be easily maintained manually by programmers later.
- Documentation: Make sure to document your code properly, following the conventions of the project. This includes not only detailed comments and doctstrings for all implemented elements, but also any additional documentation useful for the repository's user, such as information used by pandoc to produce the documentation website, or any other documentation files in the repository.
- Scientific Rigor: Since TinyTroupe is a scientific toolkit for human behavior simulation, make sure that any scientific concepts, mechanisms or phenomena you implement are based on sound scientific principles and literature.
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.
- 2d ago First seen · 113 lines · 2,629 tokens per session scan A 570dc0f643b4
TinyTroupe copilot-instructions.md is an instructions file published in the GitHub repository microsoft/TinyTroupe (7,558 stars, last pushed 2mo ago), licensed MIT. It adds 2,629 tokens to every session, about $0.0131 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
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.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain 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.