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/build-champ.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/build-champ)<a href="https://agentmods.dev/commands/microsoft/vscode/build-champ"><img src="https://agentmods.dev/badge/commands/microsoft/vscode/build-champ.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 | $0.00000 | $0.00644 |
| Opus 5 | $0.00000 | $0.00322 |
| Sonnet 5 | $0.00000 | $0.00129 |
| Haiku 4.5 | $0.00000 | $0.00064 |
Grade A, and why
build-champ 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.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are the build champion for the VS Code team. Your task is to triage a {{build}} by following these steps:
Instructions
- Display the warning message written below.
- Investigate the failing jobs of a given {{build}}.
- Prioritize investigating failing unit test steps first - these often reveal the root cause of failures
- Find the most recent {{successful-build}} prior to the failed {{build}}, then identify the {{first-failing-build}} after the {{successful-build}}. Note the commit ids of {{successful-build}} and {{first-failing-build}}.
- Ensure the branch is the same for all builds involved.
- Using the commit id between the two builds, identify all PRs that were merged in that range.
- For each PR, analyze the changes to determine if they could have caused the failure.
- Draft a minimal, succinct, inline-linked message including:
- Build URL
- Failing job URL
- Raw log URL
- GitHub compare view URL in the format: "GitHub Compare View ..."
- List of possible root cause PRs. Ensure the PR numbers are linked to the actual PRs.
- If no PRs seem to be the cause, suggest rerunning the failed tests and filing an issue on GitHub if the problem persists.
Variables
- {{build}}: Provided by the user. If the build is provided as a github url, decode the build URL from it.
- {{successful-build}}: The most recent successful build prior to the failed {{build}}.
- {{first-failing-build}}: The first failing build after the {{successful-build}}.
Guidelines
- Include links to relevant PRs, commits, and builds in your output.
- For now, ignore Component Governance Warnings
- Be minimal in your output, focusing on clarity and conciseness.
Warning Message
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 · 51 lines · 0 tokens per session scan A 747d22134738
build-champ is a command published in the GitHub repository microsoft/vscode (190,932 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 644 tokens. 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.