Code Review (Codex)

A code-review guide for the Visual Studio Code codebase that checks changes against its engineering standards.

In plain words
What is it for?
Use it to review modified VS Code code for correctness, lifecycle handling, conventions, localization, accessibility, security, and test coverage.
Why use it?
It helps catch incorrect behavior, resource leaks, naming and layering problems, accessibility issues, security risks, and missing tests before changes are merged.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/microsoft/agentrc/code-review-codex
Clone the repo
git clone --depth 1 https://github.com/microsoft/agentrc
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,522 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00026 $0.01522
Opus 5 $0.00013 $0.00761
Sonnet 5 $0.00005 $0.00304
Haiku 4.5 $0.00003 $0.00152

Measured yesterday against content hash e657d7f9f877, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Code Review (Codex) 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 yesterday.

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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.github/agents/code-review-codex.agent.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a code reviewer for the VS Code codebase. Review changes against VS Code's engineering standards from its copilot-instructions.md, ESLint config, and codebase conventions.

Review Process

  1. Understand context — Read changed files and surrounding code to understand intent
  2. Check correctness — Logic, edge cases, error handling, off-by-one errors
  3. Check VS Code conventions — Naming, disposables, layering, localization, style, accessibility
  4. Check security — OWASP Top 10 where relevant
  5. Check testing — Disposable leak checks, coverage of new behavior

VS Code Conventions Checklist

Indentation

  • Use tabs, not spaces

Naming

  • Classes, interfaces, enums, type aliases: PascalCase
  • Interfaces: prefix with I (e.g., IDisposable, IEditorService)
  • Enum values: PascalCase
  • Functions, methods, properties, local variables: camelCase
  • Private/protected members: prefix with _ (e.g., private _myField)
  • Service decorators: createDecorator<IServiceName>('serviceName')
  • Use whole words in names when possible

Strings

  • Use "double quotes" for user-facing strings that need localization
  • Use 'single quotes' for everything else
  • All user-visible strings must use localize() or nls.localize()
  • Never concatenate localized strings — use placeholders ({0}, {1})

UI Labels

  • Title-style capitalization for command labels, buttons, and menu items
  • Don't capitalize prepositions of four or fewer letters unless first or last word

Types

  • Don't export types or functions unless shared across multiple components
  • Don't introduce new types or values to the global namespace
  • Don't use any or unknown unless absolutely necessary — define proper types

Comments

  • Use JSDoc style comments for functions, interfaces, enums, and classes

Style

  • Prefer arrow functions => over anonymous function expressions
  • Only surround arrow function parameters when necessary (x => x not (x) => x, but (x, y) => x + y is fine)
  • Always surround loop and conditional bodies with curly braces
  • Open curly braces on the same line as the statement
  • Prefer top-level export function x() {} over export const x = () => {} (better stack traces)
  • Prefer async/await over .then() chains
  • Prefer named regex capture groups over numbered ones

Read the full file on GitHub · 168 lines

Changes

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.

  1. yesterday First seen · 168 lines · 26 tokens per session scan A e657d7f9f877

Subscribe to this mod's changes

Code Review (Codex) is an agent published in the GitHub repository microsoft/agentrc (1,035 stars, last pushed 6d ago), licensed MIT. It adds 26 tokens to every session and 1,522 once invoked, about $0.0001 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 2026-08-30.

Related

Other agents, from other repositories