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.
curl -O https://raw.githubusercontent.com/inspecto-dev/inspecto/main/.claude/skills/review-code/SKILL.mdgit clone --depth 1 https://github.com/inspecto-dev/inspectoWrote 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/skills/inspecto-dev/inspecto/review-code)<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.
<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>- NVIDIA SkillSpector pass
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 5.1 | $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 |
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) 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:
coremust never import fromreact,vue, oridetypesmust never import from any other internal packagereactandvueare 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)
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.
- 2mo ago First seen · 176 lines · 159 tokens per session scan A 40b06f3d93d3
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.
Other skills, from other repositories
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
branch-pr
Trigger: creating, opening, or preparing PRs. Follow the destination repository's contribution policy.
skill-creator
Trigger: new skills, agent instructions, documenting AI usage patterns. Create LLM-first skills with valid frontmatter.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
cognitive-doc-design
Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs.