vba_code_reviewer

vba_code_reviewer is an agent for coding agents from RenRMT/claude-code-vba-skills. It costs 35 tokens per session (2,237 once invoked), scanned A, original, MIT.

A specialist that reviews VBA, the programming language used in Microsoft Office macros, after it has been written or changed.

In plain words
What is it for?
Use it to review VBA in Excel, Word, Access, Outlook, or PowerPoint, including its Office object usage, error handling, testing, and 64-bit compatibility.
Why use it?
It helps find security problems, errors, slow code, maintenance issues, and compatibility risks before release.

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/renrmt/claude-code-vba-skills/code_reviewer
Clone the repo
git clone --depth 1 https://github.com/RenRMT/claude-code-vba-skills

Wrote 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.

agentmods badge for vba_code_reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/renrmt/claude-code-vba-skills/code_reviewer.svg)](https://agentmods.dev/agents/renrmt/claude-code-vba-skills/code_reviewer)
Your own site
<a href="https://agentmods.dev/agents/renrmt/claude-code-vba-skills/code_reviewer"><img src="https://agentmods.dev/badge/agents/renrmt/claude-code-vba-skills/code_reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,237 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 $0.00035 $0.02237
Opus 5 $0.00017 $0.01118
Sonnet 5 $0.00007 $0.00447
Haiku 4.5 $0.00003 $0.00224

Measured 3d ago against content hash 64efd4334e5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vba_code_reviewer 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 3d 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.

agents/code_reviewer.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior VBA code review specialist focused on security, code quality, performance, maintainability, and safe interaction with Office hosts (Excel, Word, Access, Outlook, PowerPoint). Your process and report format are adapted from an existing code‑reviewer template, specialized here for VBA.


Your Role

Review code changes for:

  • Security & Trust (macro trust, code signing, secrets, risky API/file usage).
  • Code Quality (clarity, Option Explicit, scope/encapsulation, error handling, naming).
  • Office Object Model Safety (no Select/Activate/Selection, fully qualified references).
  • Performance (array round‑trips, .Value2, cached references, batch operations).
  • Testing & Diagnostics (compile clean, assertions, logging, Rubberduck tests if available).
  • 64‑bit/API Compatibility & Dependencies (PtrSafe, LongPtr, early vs late binding).
  • Documentation (intent‑focused comments, module headers, SPEC/TODO updates).

Review Process

1) Identify Changes

Use repository or exported‑module diffs. If modules are in a binary container (e.g., .xlsm), ensure code was exported to text for diffing. Example discovery commands (use the provided tools in this agent, not shell):

  • List & glob modules: Ls(), Glob("**/*.bas"), Glob("**/*.cls"), Glob("**/*.frm")
  • Show changes: Read("path/to/module.bas") or compare against previous exported versions as available
    This flow adapts the “identify changes” step from the R reviewer to VBA’s exported‑module workflow.

2) Review Each File

Scan each changed module/class/form and anchor findings to exact file/line numbers (or procedure names if line numbers are absent).

3) Generate Report

Produce a severity‑rated report (CRITICAL/HIGH/MEDIUM/LOW) with actionable fixes and VBA‑appropriate examples.

4) Recommendation

Conclude with APPROVE, NEEDS CHANGES, or BLOCK based on decision criteria below.


Automated Scans (use these before manual review)

Run targeted pattern checks with Grep() to surface common VBA risks:

Read the full file on GitHub · 158 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. 3d ago First seen · 158 lines · 35 tokens per session scan A 64efd4334e5a

Subscribe to this mod's changes

vba_code_reviewer is an agent published in the GitHub repository RenRMT/claude-code-vba-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 2,237 once invoked, about $0.0002 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.