inspecto: Skill for Claude Code

.claude/skills/review-code/SKILL.md

review-code is a skill for Claude Code from inspecto-dev/inspecto. It costs 159 tokens per session (1,479 once invoked), scanned A, original, MIT.

A code-review guide for the Inspecto monorepo, a single repository containing several related packages. It checks code against that project's architecture and rules.

In plain words
What is it for?
Use it to review an Inspecto file or package for code quality, architecture compliance, and implementation issues.
Why use it?
It helps identify broken package dependencies, misplaced logic, framework coupling, and other project-specific design problems.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is inspecto-dev/inspecto's own configuration. It tells Claude Code how to work on inspecto itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything inspecto configures →

Reuse

Borrowing it

Nothing to install: this file belongs to inspecto-dev/inspecto. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/inspecto-dev/inspecto/main/.claude/skills/review-code/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/inspecto-dev/inspecto

Made for: Claude Code.

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 review-code

README.md
[![agentmods](https://agentmods.dev/badge/skills/inspecto-dev/inspecto/review-code/github.svg)](https://agentmods.dev/skills/inspecto-dev/inspecto/review-code)
Your own site
<a href="https://agentmods.dev/skills/inspecto-dev/inspecto/review-code"><img src="https://agentmods.dev/badge/skills/inspecto-dev/inspecto/review-code/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for review-code

Your own site · 80×15
<a href="https://agentmods.dev/skills/inspecto-dev/inspecto/review-code"><img src="https://agentmods.dev/badge/skills/inspecto-dev/inspecto/review-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 159 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,479 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00159 $0.01479
Opus 5.5 $0.00064 $0.00592
Sonnet 5.5 $0.00032 $0.00296
Haiku 4.5 $0.00016 $0.00148

Measured 2mo ago against content hash 40b06f3d93d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

review-code scanned grade A with 1 finding 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 2mo 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- Server uses `portfinder` + `launch-ide` (not custom child_process port scanning)
.claude/skills/review-code/SKILL.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

review-code — Inspecto Code Quality Review

You are performing a deep code quality review of a file or package in the inspecto monorepo. Your goal is to give the developer honest, specific, actionable feedback — not a rubber-stamp.

Project Architecture (reference model)

The intended dependency direction is strictly one-way:

@inspecto-dev/types          ← leaf, no internal deps
        ↓
@inspecto-dev/unplugin       ← build-time only, Node.js
        ↓
@inspecto-dev/core           ← browser runtime + server utils
        ↓
@inspecto-dev/react          ← thin React wrapper (peer: react)
@inspecto-dev/vue            ← thin Vue wrapper (peer: vue)
        ↓
@inspecto-dev/ide                    ← IDE extension (VS Code, Cursor, Trae) (CommonJS, Node.js)

Key architectural invariants to enforce:

  • core must never import from react, vue, or ide
  • types must never import from any other internal package
  • react and vue are thin wrappers — no inspector logic, just prop-passing
  • Web Component UI lives entirely in core/src/client/ — zero framework dependency
  • Transform layer uses MagicString (not @babel/generator) for source maps
  • Server uses portfinder + launch-ide (not custom child_process port scanning)
  • Attributes injected only when NODE_ENV !== 'production'

Review Dimensions

For the given file or package, evaluate each dimension thoroughly:

1. Architecture & Module Boundaries

  • Does the file import from packages it shouldn't depend on?
  • Is the file in the right package given its responsibility?
  • Does it introduce coupling between layers that should be independent?
  • Are side effects (server startup, DOM mutation, customElements.define) isolated correctly?

2. Implementation Quality

  • Are edge cases handled? (file not found, parse errors, empty input, Windows paths)
  • Are error paths explicit with structured error codes (not raw throw new Error('string'))?
  • No hardcoded magic values — ports, timeouts, attribute names should be constants/config
  • Is async/await used correctly? No floating Promises, no unhandled rejections
  • Are cleanup paths present? (event listeners removed, servers stopped, DOM elements removed)

Read the full file on GitHub · 176 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. 2mo ago First seen · 176 lines · 159 tokens per session scan A 40b06f3d93d3

Subscribe to this mod's changes

review-code is a skill published in the GitHub repository inspecto-dev/inspecto (22 stars, last pushed 1mo ago), licensed MIT. It adds 159 tokens to every session and 1,479 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.