apex-code-review

A structured review tool for Apex code, the programming language used to customize Salesforce. It checks classes, triggers, and test classes against Salesforce coding, security, and design practices.

In plain words
What is it for?
Use it to review Salesforce classes, triggers, or tests and organize findings by severity. The source can be provided from local files or fetched from a Salesforce organization.
Why use it?
It gives you a consistent way to find security problems, inefficient use of Salesforce limits, and design issues before code is deployed. It first establishes where the source code will come from.

Skill for Claude CodeCodex

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 skills/tsmztech/claude-code-plugins/apex-code-review
Any agent
npx skills add tsmztech/claude-code-plugins --skill apex-code-review
Clone the repo
git clone --depth 1 https://github.com/tsmztech/claude-code-plugins

Made for: Claude Code, Codex.

Per session 149 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,663 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 $0.00149 $0.02663
Opus 5 $0.00075 $0.01332
Sonnet 5 $0.00030 $0.00533
Haiku 4.5 $0.00015 $0.00266

Measured yesterday against content hash c48b396e83c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

apex-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 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.

salesforce-dev/skills/apex-code-review/SKILL.md · 331 lines

How it starts

The opening of the file, as written. The whole thing — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Apex Code Review

Perform a structured, severity-categorized code review of Apex classes, triggers, and test classes against Salesforce best practices, security guidelines, governor limit awareness, and design patterns.

Phase 1: Your FIRST action -- ask where to get the source code

Before doing ANYTHING else -- before searching, before reading files, before any Glob calls -- you must ask the user where the Apex source code is located. This is your first action every time because class names alone don't tell you whether the files exist locally or need to be fetched from a Salesforce org.

What NOT to do (common failure)

❌ WRONG: User says "review AccountService" → you immediately run Glob to search
   for the file → file not found → you ask user to paste code or give a path.
   This wastes time and misses the Salesforce org fetch entirely.

What to do instead

✅ RIGHT: User says "review AccountService" → you FIRST ask where to get the file
   → user says "Salesforce org" → you run fetch-apex.js → you have the code.

Step 1: Collect file/class names

Determine which files to review from the request:

  • $ARGUMENTS contains file paths or class names → use those
  • User has an IDE selection → review that code directly (skip Step 2)
  • Neither → ask the user which files to review

Step 2: Ask source preference using AskUserQuestion

Use AskUserQuestion to ask where to get the source code. Here is the exact question to ask -- do not skip this, do not try to find the files first:

question: "Where should I get the Apex source code?"
options:
  - label: "Search locally"
    description: "I'll search for the files in the current project directory"
  - label: "Fetch from Salesforce org"
    description: "I'll retrieve the source code from your connected Salesforce org"

Skip this question ONLY if one of these is true:

  • The user gave full file paths (e.g., force-app/.../AccountService.cls)
  • The user has code selected in their IDE
  • The user explicitly said "from org" or "from salesforce" in their message

Read the full file on GitHub · 331 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 331 lines · 149 tokens per session scan A c48b396e83c5

Subscribe to this mod's changes

apex-code-review is a skill published in the GitHub repository tsmztech/claude-code-plugins (2 stars, last pushed 6mo ago), licensed MIT. It adds 149 tokens to every session and 2,663 once invoked, about $0.0007 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens