vmcp-review

A code-review guide for the vMCP Go codebase, focused on patterns that make code harder to understand, more fragile, or harder to test.

In plain words
What is it for?
Use it when reviewing pull requests, planning features, auditing packages, or refactoring files under `pkg/vmcp/` and `cmd/vmcp/`.
Why use it?
It helps reviewers spot problems consistently in changed or existing vMCP code, and separates issues that must be fixed from those worth addressing or simply noting.

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/stacklok/toolhive/vmcp-review
Any agent
npx skills add stacklok/toolhive --skill vmcp-review
Clone the repo
git clone --depth 1 https://github.com/stacklok/toolhive

Made for: Claude Code, Codex.

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 571 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 $0.00044 $0.00571
Opus 5 $0.00022 $0.00285
Sonnet 5 $0.00009 $0.00114
Haiku 4.5 $0.00004 $0.00057

Measured 3d ago against content hash 50ec95eb2343, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vmcp-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 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.

.claude/skills/vmcp-review/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vMCP Code Review

Purpose

Review code in pkg/vmcp/ and cmd/vmcp/ for known anti-patterns that increase cognitive load, create brittle dependencies, or undermine testability. This skill is used both for reviewing proposed changes and for auditing existing code.

Instructions

1. Determine Scope

Identify the files to review:

  • If reviewing a PR or diff, examine only the changed files under pkg/vmcp/ and cmd/vmcp/
  • If auditing a package, examine all .go files in the target package
  • Skip files outside the vMCP codebase — this skill is vMCP-specific

2. Anti-Pattern Detection

For each file under review, check against the anti-patterns defined in .claude/rules/vmcp-anti-patterns.md (which is auto-loaded when vMCP files are read). Not every anti-pattern applies to every file — use judgment about which checks are relevant based on what the code does.

For each finding, classify severity:

  • Must fix: The anti-pattern is being introduced or significantly expanded by this change
  • Should fix: The anti-pattern exists in touched code and the change is a good opportunity to address it
  • Note: The anti-pattern exists in nearby code but is not directly related to this change — flag for awareness only

3. Present Findings

Structure your report as:

## vMCP Review: [scope description]

### Must Fix
- **[Anti-pattern name]** in `path/to/file.go:line`: [What's wrong and what to do instead]

### Should Fix
- **[Anti-pattern name]** in `path/to/file.go:line`: [What's wrong and what to do instead]

### Notes
- **[Anti-pattern name]** in `path/to/file.go:line`: [Brief description, for awareness]

### Clean
No issues found for: [list anti-patterns that were checked and passed]

If no issues are found, say so explicitly — a clean review is valuable signal.

What This Skill Does NOT Cover

  • General Go style issues (use golangci-lint for that)
  • Security vulnerabilities (use the security-advisor agent)
  • Test quality (use the unit-test-writer agent)
  • Non-vMCP code (use the general code-reviewer agent)
  • Performance issues (unless they stem from an anti-pattern like repeated body parsing)

Read the full file on GitHub · 61 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 · 61 lines · 44 tokens per session scan A 50ec95eb2343

Subscribe to this mod's changes

vmcp-review is a skill published in the GitHub repository stacklok/toolhive (2,065 stars, last pushed yesterday), licensed Apache-2.0. It adds 44 tokens to every session and 571 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 2026-08-30.