TinyTroupe is a Python library that uses large language models to simulate people with defined personalities, interests, and goals in artificial environments. It is used to explore human behavior, consumer types, and business scenarios through configurable multi-agent simulations. The catalogue entry provides an instruction for working with it.
Borrowing it
Nothing to install: this file belongs to microsoft/TinyTroupe. 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/microsoft/TinyTroupe/main/.github/prompts/improve.prompt.mdgit clone --depth 1 https://github.com/microsoft/TinyTroupeWrote 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/commands/microsoft/tinytroupe/improve)<a href="https://agentmods.dev/commands/microsoft/tinytroupe/improve"><img src="https://agentmods.dev/badge/commands/microsoft/tinytroupe/improve/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/commands/microsoft/tinytroupe/improve"><img src="https://agentmods.dev/badge/commands/microsoft/tinytroupe/improve.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 | $0.00010 | $0.00301 |
| Opus 5.5 | $0.00004 | $0.00120 |
| Sonnet 5.5 | $0.00002 | $0.00060 |
| Haiku 4.5 | $0.00001 | $0.00030 |
Grade A, and why
improve 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.
What it actually says
Examine the attached files in order to find ways to improve the programs, documentation, or any other aspect of the project.
Among other things you might consider, please also look for:
- Potential errors and bugs: think carefully about how the program could fail. Consider both common and corner cases, and how the program might behave in unexpected situations.
- Performance issues: identify any potential performance bottlenecks or inefficiencies in the code.
- Code quality: look for ways to improve the code quality, such as simplifying complex logic, removing redundant code, or improving readability.
- Formatting and style: check if the code follows the project's formatting and style guidelines. If not, suggest improvements to make it more consistent.
- More clear names: suggest more descriptive names for variables, functions, classes, or any other identifiers that could be improved for clarity or adherence to the project's goals and conventions.
- Testing coverage: ensure that the code is adequately tested, and suggest additional tests. You can look for in the
tests/directory to determine existing tests. - Complexity reduction: determine whether there are ways to reduce the complexity of the code without losing too much functionality or performance.
- Documentation: check if the documentation is clear, complete, and up-to-date. Suggest improvements if necessary.
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 · 17 lines · 10 tokens per session scan A 9d8e246a8108
improve is a command published in the GitHub repository microsoft/TinyTroupe (7,626 stars, last pushed 6d ago), licensed MIT. It adds 10 tokens to every session and 301 once invoked, about $0.0000 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 2026-10-22.
Other commands, from other repositories
dart-review-pr
review a PR or address review feedback.
dart-mechanical-refactor
perform a behavior-preserving mechanical refactor.
pr
Automated PR code quality review with language-aware analysis and project-specific profiles.
code-improve
Launch autonomous code improvement loop — detects opportunities, applies improvements, creates PRs for review.
pr-enhance
Command "pr-enhance" from ruvnet/ruflo, covering pr-enhance, usage, options, examples and enhance pr.
refactor-sprint
Parallel refactor sprint — fires refactor-cleaner + code-simplifier + type-design-analyzer + tdd-guide simultaneously. Full cleanup in one pass.