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.
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.
curl -O https://raw.githubusercontent.com/wasp-lang/wasp/main/.agents/skills/wasp-review/SKILL.mdgit clone --depth 1 https://github.com/wasp-lang/waspWrote 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/wasp-lang/wasp/wasp-review)<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.
<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>- 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 | $0.00040 | $0.00620 |
| Opus 5 | $0.00020 | $0.00310 |
| Sonnet 5 | $0.00008 | $0.00124 |
| Haiku 4.5 | $0.00004 | $0.00062 |
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.
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 andensure...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
andorthenin 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.
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.
- 10d ago First seen · 62 lines · 40 tokens per session scan A a6e83486ba7a
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.
Other skills, from other repositories
triage-contributor-pr
Triage open pull requests from external contributors to prisma/prisma and produce a per-PR verdict with evidence. Use when a maintainer asks to triage, evaluate, assess, or review the queue of incoming contributor PRs, to decide whether a fork PR is safe to run CI on, to check whether a PR is in scope for its version…
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
review-triage-phase
Produces canonical review actions from fetched review state and renders action markdown. Use when the user wants only triage/action-planning for the review-framework workflow.
no-bare-casts
Writing as in TypeScript or TSX production code, modifying a file that contains a bare as cast, silencing a type error with a cast, encountering as unknown as, or reviewing a cast site.
compiler-commit
Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits with the [compiler] or [rust-compiler] prefix.
compiler-verify
Use when you need to run all compiler checks (tests, lint, format) before committing. Detects whether TS or Rust code changed and runs the appropriate checks.