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.
npx agentmods add commands/renrmt/claude-code-vba-skills/verifygit clone --depth 1 https://github.com/RenRMT/claude-code-vba-skillsWrote 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/commands/renrmt/claude-code-vba-skills/verify)<a href="https://agentmods.dev/commands/renrmt/claude-code-vba-skills/verify"><img src="https://agentmods.dev/badge/commands/renrmt/claude-code-vba-skills/verify.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00025 | $0.00479 |
| Opus 5 | $0.00013 | $0.00239 |
| Sonnet 5 | $0.00005 | $0.00096 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
verify 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.
What it actually says
/verify - VBA Verification Loop
Run all quality gates before committing code. Produces a READY or NOT READY verdict.
When to Use
- Before every commit
- After implementing a feature or fix
- Before distributing a workbook or add-in
Verification Phases
Run each phase in order. A failure in any phase blocks the verdict.
Phase 1: Option Explicit Check
Scan all modules for Option Explicit. Every module must have it.
Phase 2: Anti-Pattern Scan
Search for known anti-patterns:
Select/Activate/Selection/ActiveSheet/ActiveWorkbook- Blanket
On Error Resume Next(without targeted scope) - Unqualified
Range()/Cells()references Integerdeclarations (should beLong)
Phase 3: Error Handling & State Restoration
Verify that:
- Public procedures use structured error handling (
CleanExit/CleanFail) Application.ScreenUpdating,.Calculation,.EnableEventsare restored on exit and error- No procedures leave application state modified on failure
Phase 4: Code Review
Invoke /code-review to check all uncommitted changes.
Phase 5: Diff Review
git diff --stat HEAD
git diff HEAD
Confirm:
- No unintended files changed
- No debug code left in (
Debug.Print,Stop,MsgBoxfor debugging) - No hardcoded paths or credentials
- Commit message ready
Verdict Format
## Verification Report
| Phase | Status | Notes |
|----------------------|---------|------------------------------|
| Option Explicit | PASS | All 12 modules |
| Anti-pattern scan | PASS | 0 findings |
| Error handling | PASS | All public procedures covered |
| Code review | PASS | No CRITICAL/HIGH issues |
| Diff review | PASS | Changes look correct |
## Verdict: READY TO COMMIT
Related Commands
/plan— plan before implementing/code-review— standalone code review
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.
- 4d ago First seen · 76 lines · 25 tokens per session scan A db84030af92e
verify is a command published in the GitHub repository RenRMT/claude-code-vba-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 479 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 2026-08-31.
Other commands, from other repositories
gen-gtests
Generate unit Googletests for a diff from trunk.
gaze-fix
Generate tests and documentation fixes for functions identified by gaze quality analysis, or auto-detect and run the active implementation workflow (Speckit/OpenSpec). With arguments: batch remediation. Without arguments: detects active workflow and runs /speckit.implement or /opsx-apply.
golang-test-review
Use when reviewing Go test code (new or changed test.go files, test harnesses, fixtures, or test tooling) for a Go-test-expert pass — behavior-over-surface, determinism, parallel-safety, build-tag correctness, and harness reuse. Complements the general code-reviewer with test-specific rigor.
testing
Command "testing" from Awesome-Embedded-Learning-Studio/CFDesktop, covering /testing — 测试覆盖建议, 触发方式, 工作流程, step 1: 分析目标代码 and step 2: 检查现有测试覆盖.
comprehensive-unit-testing-with-pytest
Aims for high test coverage using pytest, testing both common and edge cases.
test-rust
Run Rust tests for Solana programs and backend services.