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/update-instructions.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/update-instructions)<a href="https://agentmods.dev/commands/microsoft/vscode/update-instructions"><img src="https://agentmods.dev/badge/commands/microsoft/vscode/update-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 | $0.00000 | $0.00204 |
| Opus 5 | $0.00000 | $0.00102 |
| Sonnet 5 | $0.00000 | $0.00041 |
| Haiku 4.5 | $0.00000 | $0.00020 |
Grade A, and why
update-instructions 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
Read the changes introduced on the current branch, including BOTH:
- Uncommitted workspace modifications (staged and unstaged)
- Committed changes that are on the current HEAD but not yet in the default upstream branch (e.g.
origin/main)
Guidance:
- First, capture uncommitted diffs (equivalent of
git diffandgit diff --cached). - Then, determine the merge base with the default branch (assume
origin/mainunless configured otherwise) usinggit merge-base HEAD origin/mainand diff (git diff <merge-base>...HEAD) to include committed-but-unpushed work.
After understanding all of these changes, read every instruction file under .github/instructions and assess whether any instruction is invalidated. If so, propose minimal, necessary wording updates. If no updates are needed, respond exactly with: No updates needed.
Be concise and conservative: only suggest changes that are absolutely 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.
- today First seen · 18 lines · 0 tokens per session scan A 3ef4805eea15
update-instructions 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 204 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
release-commands
:::info This document covers the release and changelog commands for publishing eIsland builds and generating release notes. For packaging the installer locally, see Package Commands. ::.
pr-ready
Run the project's pre-commit review loop to determine whether the current branch is ready to push — lint, tests, parallel pr-review-toolkit agents plus an over-engineering audit, fix-and-re-run until convergence.
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.
codex-loop
Claim the next dispatch:codex issue from the GitHub queue and work it end-to-end through codex exec: branch, implement, QA, PR. One invocation handles exactly one task — a local pull loop you trigger, not a daemon. The board/label safety model is identical to /loop; only the engine differs (the local Codex CLI instead…
skill-create
Analyze local git history to extract coding patterns and generate SKILL.md files. Local version of the Skill Creator GitHub App.