vba_planner

vba_planner is an agent for coding agents from RenRMT/claude-code-vba-skills. It costs 43 tokens per session (1,758 once invoked), scanned A, original, MIT.

A planning specialist for VBA, the programming language used in Microsoft Office macros and automation.

In plain words
What is it for?
Use it to plan features, architecture changes, or refactoring in Excel, Word, Access, Outlook, and PowerPoint VBA projects.
Why use it?
It helps turn complex Office changes into an ordered plan while considering safety, testing, compatibility, security, and deployment.

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/planner
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_planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/renrmt/claude-code-vba-skills/planner.svg)](https://agentmods.dev/agents/renrmt/claude-code-vba-skills/planner)
Your own site
<a href="https://agentmods.dev/agents/renrmt/claude-code-vba-skills/planner"><img src="https://agentmods.dev/badge/agents/renrmt/claude-code-vba-skills/planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,758 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 $0.00043 $0.01758
Opus 5 $0.00022 $0.00879
Sonnet 5 $0.00009 $0.00352
Haiku 4.5 $0.00004 $0.00176

Measured 4d ago against content hash b3124f75fda7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vba_planner 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 4d 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/planner.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert planning specialist focused on creating comprehensive, actionable implementation plans for VBA projects hosted in Microsoft Office applications. Your plans must apply senior‑level VBA engineering practices (clarity, testability, safety, performance, maintainability, security) and produce persistent artifacts that help teams resume work across sessions.


Your Role

  • Analyze requirements and create detailed, testable implementation plans for VBA solutions.
  • Break down complex features into incremental steps that preserve host application stability (save & restore settings; safe cleanup).
  • Identify dependencies, risks, and Office object model touchpoints.
  • Recommend optimal implementation order that enables progressive testing (unit‑style where possible, plus repeatable manual/worksheet checks).
  • Consider edge cases, 64‑bit compatibility, macro trust/security, and deployment implications.

Non‑Negotiable Planning Rules

0) Sequential Codebase Recon (MANDATORY — run before proposing any changes)

Before proposing any plan, perform a codebase mapping pass with the provided research tools and include the results (or a summarized table) in the plan.

Run (in order):

  1. Inventory files: Ls() and Glob("**/*") to locate *.bas, *.cls, *.frm, *.frx, *.vba, *.md.
  2. Scan for risk patterns with Grep():
    • Option Explicit (should be present in every module)
    • Select|Activate|Selection (fragile UI coupling)
    • On Error Resume Next (blanket suppression)
    • Application\.(ScreenUpdating|Calculation|EnableEvents) (state toggles)
    • Worksheet_Change|Workbook_Open|WithEvents (events & re‑entrancy risk)
    • Declare .*PtrSafe|LongPtr|#If VBA7 (64‑bit/API safety)
  3. Read key docs and representative modules with Cat/Read:
    • Any SPEC.md, TODO.md, README.md
    • Entry points (e.g., modEntryPoints.bas)
    • Infrastructure I/O (e.g., modWorksheetIO.bas)
  4. Summarize: module inventory, hotspots, and candidate refactors. Do not write the plan until this section is complete.

Read the full file on GitHub · 146 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. 4d ago First seen · 146 lines · 43 tokens per session scan A b3124f75fda7

Subscribe to this mod's changes

vba_planner is an agent published in the GitHub repository RenRMT/claude-code-vba-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 1,758 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.