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/skills/code-review/SKILL.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/skills/microsoft/vscode/code-review)<a href="https://agentmods.dev/skills/microsoft/vscode/code-review"><img src="https://agentmods.dev/badge/skills/microsoft/vscode/code-review/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/skills/microsoft/vscode/code-review"><img src="https://agentmods.dev/badge/skills/microsoft/vscode/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00041 | $0.00532 |
| Opus 5.5 | $0.00016 | $0.00213 |
| Sonnet 5.5 | $0.00008 | $0.00106 |
| Haiku 4.5 | $0.00004 | $0.00053 |
Grade A, and why
code-review 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 27d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Review the proposed changes as a senior maintainer. Focus on actionable defects introduced by the changes, especially correctness issues, regressions, and changes that are not necessary for the stated goal.
Establish the Review Scope
Before reviewing:
- Determine the intended change from the request, pull request description, linked issue, and maintainer comments.
- Identify the complete diff against the appropriate base.
- Account for every changed file and subsystem.
Do not infer the purpose solely from the implementation. If the intended behavior is unclear, state the assumption used for the review.
Review the Changes
Trace the changed behavior through its callers, dependencies, and tests. Check for:
- Incorrect logic, broken edge cases, or behavior that contradicts the stated goal.
- Regressions in existing behavior, including platform-specific and lifecycle behavior.
- Missing or incorrect error handling.
- Unsafe assumptions about data, ordering, concurrency, or object lifetime.
- Tests that do not cover the changed behavior or that would pass without the fix.
- Changes whose connection to the stated goal is unclear.
Keep fixes tied to the underlying cause. Do not accept unrelated changes to behavior, state management, or architecture merely because they make the reported symptom disappear.
Treat prerequisite or tightly coupled changes as in scope only when their necessity is clear from the implementation or pull request description. A changed file should be necessary for the stated goal or be a directly related test, documentation update, generated artifact, or required refactor. Independent cleanup and speculative improvements belong in a separate change.
Report Findings
Report only findings that are:
- Introduced or made materially worse by the changes under review.
- Specific and actionable.
- Supported by the code or by a concrete missing validation.
For each finding:
- State the user-visible or engineering impact.
- Explain the conditions that trigger it.
- Point to the smallest relevant changed line or range.
- Explain why the current implementation is incorrect.
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.
- 27d ago Changed · +27 lines · +8 tokens per session 7ee471b53487
- 1mo ago First seen · 26 lines · 33 tokens per session scan A c2a0feb2dc49
code-review is a skill published in the GitHub repository microsoft/vscode (194,219 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 532 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
open-code-review
Use Alibaba Open Code Review (ocr) to review git diffs, staged changes, branches, or scan a workspace, then summarize findings and optionally fix high-confidence issues.
Release Readiness
Review a change against release gates, rollback safety, validation evidence, and operational risk.
performance-lint-rules
Performance review guidance for Oxc linter rule implementations. Use only when reviewing Rust rule code under crates/oxclinter/src/rules/ or when explicitly auditing those rules for performance improvements.
output-eval-error-analysis
Systematically review workflow traces to identify failure modes before building evaluators. Use when starting an eval project, after significant pipeline changes, or when production quality drops.
qa-frontend
Internal PostHog developer frontend/browser QA skill. Use only when a PostHog developer explicitly asks to run frontend QA, browser-test a PR, verify a UI flow against the local PostHog stack, use qa-frontend, or QA current frontend changes with browser/runtime evidence, or to make a feature reel (see reel mode…
agent-dependencies
Perform one conservative dependency or toolchain upgrade in the Elements monorepo and open a validated pull request. Use for nightly or unattended dependency maintenance, outdated package checks, first-party actions/ GitHub Actions updates, and pinned mise tool updates. Use the github-dependabot skill instead when the…