Visual Studio Code is a code editor that supports editing, navigating, understanding, debugging, and extending software projects. Developers use it for the edit-build-debug cycle, and the catalogue add-ons provide skills, instructions, and agents for working within the editor.
Borrowing it
Nothing to install: this file belongs to microsoft/vscode. 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/vscode/main/.github/prompts/micro-perf.prompt.mdgit clone --depth 1 https://github.com/microsoft/vscodeWrote 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/vscode/micro-perf)<a href="https://agentmods.dev/commands/microsoft/vscode/micro-perf"><img src="https://agentmods.dev/badge/commands/microsoft/vscode/micro-perf.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 | $0.00003 | $0.00421 |
| Opus 5 | $0.00002 | $0.00211 |
| Sonnet 5 | $0.00001 | $0.00084 |
| Haiku 4.5 | $0.00000 | $0.00042 |
Grade A, and why
micro-perf 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 today.
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
Role
You are an expert performance engineer.
Instructions
Review the attached file and find all publicly exported class or functions. Optimize performance of all exported definitions. If the user provided explicit list of classes or functions to optimize, scope your work only to those definitions.
Guidelines
- Make sure to analyze usage and calling patterns for each function you optimize.
- When you need to change a function or a class, add optimized version of it immediately below the existing definition instead of changing the original.
- Optimized function or class name should have the same name as original with '_new' suffix.
- Create a file with '..perf.js' suffix with perf tests. For example if you are using model 'Foo' and optimizing file name utils.ts, you will create file named 'utils.foo.perf.js'.
- IMPORTANT: You should use ESM format for the perf test files (i.e. use 'import' instead of 'require').
- The perf tests should contain comprehensive perf tests covering identified scenarios and common cases, and comparing old and new implementations.
- The results of perf tests and your summary should be placed in another file with '..perf.md' suffix, for example 'utils.foo.perf.md'.
- The results file must include section per optimized definition with a table with comparison of old vs new implementations with speedup ratios and analysis of results.
- At the end ask the user if they want to apply the changes and if the answer is yes, replace original implementations with optimized versions but only in cases where there are significant perf gains and no serious regressions. Revert any other changes to the original code.
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.
- today First seen · 27 lines · 3 tokens per session scan A 99fe2bc2ac05
micro-perf is a command published in the GitHub repository microsoft/vscode (190,932 stars, last pushed today), licensed MIT. It adds 3 tokens to every session and 421 once invoked, about $0.0000 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 2026-09-06.
Other commands, from other repositories
plugin-commands
:::info This document covers all build, test, and smoke commands for eIsland native plugins. Each plugin lives under plugins/ and has its own package.json with independent scripts. ::.
cloud-sdk-ai-chat-template
Generate or review a JavaScript or TypeScript chat template for SAP Cloud SDK for AI with safe configuration boundaries.
package-commands
:::info This document covers the packaging and lifecycle commands for building distributable installers and managing native modules. For development commands (dev, build, preview), see Development Commands. ::.
quality-commands
:::info This document covers the code quality commands for validating comment standards and i18n completeness in the eIsland frontend. ::.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.