wasp: Skill for Claude Code

.agents/skills/wasp-review/SKILL.md

wasp-review is a skill for Claude Code, Codex from wasp-lang/wasp. It costs 40 tokens per session (620 once invoked), scanned A, original, MIT.

A code-review guide for checking code changes, files, and pull requests, which are proposed changes submitted for review. It focuses on correctness, clarity, naming, interfaces, and readability.

In plain words
What is it for?
Use it to review a diff, file, or pull request and provide feedback on behavior, naming, contracts, structure, and maintainability.
Why use it?
It helps identify misleading names, unclear responsibilities, and code that is difficult to understand before changes are accepted.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is wasp-lang/wasp's own configuration. It tells Claude Code and Codex how to work on wasp 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 wasp configures →

About the project

Wasp is a full-stack web framework for building React and Node.js applications with declarative code, while Prisma handles database access. It is for developers who want built-in features such as authentication, background jobs, email, RPC, type safety, and deployment in one application framework.

wasp-lang/wasp · 18,726 stars · on GitHub · wasp.sh

Reuse

Borrowing it

Nothing to install: this file belongs to wasp-lang/wasp. 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/wasp-lang/wasp/main/.agents/skills/wasp-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/wasp-lang/wasp

Made for: Claude Code, Codex.

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 wasp-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/wasp-lang/wasp/wasp-review/github.svg)](https://agentmods.dev/skills/wasp-lang/wasp/wasp-review)
Your own site
<a href="https://agentmods.dev/skills/wasp-lang/wasp/wasp-review"><img src="https://agentmods.dev/badge/skills/wasp-lang/wasp/wasp-review/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 wasp-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/wasp-lang/wasp/wasp-review"><img src="https://agentmods.dev/badge/skills/wasp-lang/wasp/wasp-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 620 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00040 $0.00620
Opus 5 $0.00020 $0.00310
Sonnet 5 $0.00008 $0.00124
Haiku 4.5 $0.00004 $0.00062

Measured 10d ago against content hash a6e83486ba7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

wasp-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 10d 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/skills/wasp-review/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rules

Naming And Vocabulary

  • Demand precise, informative names. Names must not misdirect, omit relevant behavior, or assume unavailable context.
  • Make names accurately reflect what their declarations represent.
  • Context is king: evaluate names within their scope and surrounding vocabulary.
  • Use established codebase terminology consistently.
  • Follow established naming conventions e.g. is... for booleans and ensure... for idempotent setup operations.
  • Treat awkward names as evidence of design problems. If an accurate name becomes excessively long or complicated, inspect whether the declaration has too many responsibilities.
  • Avoid vague names such as data, info, or unexplained single letters.

Contracts And Interfaces

  • Review names before implementation details. Poor names often expose deeper problems in decomposition and architecture.
  • Declaration should be enough to understand, without the implementation. A function’s name, arguments, types, and contract should explain its behavior.

Readability And Context

  • Demand code to be easy to read. Understanding one section should not require reading the entire file.
  • Review from the perspective of a developer with minimal reasonable context.

Design And Architecture

  • Treat and or then in a function name as a possible responsibility smell.
  • Treat groups of similarly prefixed parameters as possible missing abstractions.
  • Make sure the code is DRY. Introduce helpers for commonly repeated concepts.
  • Identify hidden assumptions. Require assumptions to be enforced through types, runtime checks, or comments, in that order.
  • Check for Effective TypeScript defined problems.
  • Avoid NIH: check existing code and dependencies before introducing abstractions or helpers, share code once it has multiple consumers.

Comments And Writing

  • Prefer improving design or naming; use comments only when code cannot communicate enough.
  • Remove comments that preserve session-specific context unnecessary to a fresh reader.
  • Use comments only for information that names, arguments, and types cannot express.
  • Remove comments that merely narrate obvious code or exhibit generated filler.
  • Suggest pruning fluff and no-op sentences from prose.

Read the full file on GitHub · 62 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. 10d ago First seen · 62 lines · 40 tokens per session scan A a6e83486ba7a

Subscribe to this mod's changes

wasp-review is a skill published in the GitHub repository wasp-lang/wasp (18,726 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 620 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.

Related

Other skills, from other repositories