Skip to content
Back to search

jevlint

MarketplaceWorks with Claude CodeGitHub

A model-based linter that tells you what to refactor first.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/INDXDev/jevlint with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/INDXDev/jevlint'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/indxdev--jevlint/badge.svg)](/listings/indxdev--jevlint)

HTML

<a href="/listings/indxdev--jevlint"><img src="/api/listings/indxdev--jevlint/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

npm install -g @indxjp/jevlint     # or: pnpm add -g @indxjp/jevlint
jevlint --version

Requires Node.js 24.22.1 or later (or 22.23.4, or 26.12.1, on those lines).

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 14 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. {
  2. "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  3. "name": "jevlint",
  4. "description": "A model-based linter that tells you what to refactor first.",
  5. "owner": { "name": "INDX", "url": "https://github.com/INDXDev" },
  6. "plugins": [
  7. {
  8. "name": "jevlint",
  9. "description": "Rank what to refactor first with jevlint, and review what a change made worse.",
  10. "source": "./",
  11. "category": "development"
  12. }
  13. ]
  14. }
README.md · README · 346 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <p align="center">
  2. <a href="README.ja.md">日本語</a> · <a href="README.zh-CN.md">简体中文</a> · <b>English</b>
  3. </p>
  4. <p align="center">
  5. <a href="#try-it-now"><img src="docs/assets/hero.svg" alt="jevlint: know what to refactor first" width="820"></a>
  6. </p>
  7. <p align="center">
  8. <a href="https://www.npmjs.com/package/@indxjp/jevlint"><img src="https://img.shields.io/npm/v/@indxjp/jevlint?color=cb3837&logo=npm" alt="npm version"></a>
  9. <a href="https://github.com/INDXDev/jevlint/actions/workflows/ci.yml"><img src="https://github.com/INDXDev/jevlint/actions/workflows/ci.yml/badge.svg?branch=main" alt="CI status"></a>
  10. <img src="https://img.shields.io/badge/node-%E2%89%A524.22.1-339933?logo=nodedotjs&logoColor=white" alt="Node.js 24.22.1 or later">
  11. <img src="https://img.shields.io/badge/languages-TS%20%7C%20JS%20%7C%20Python%20%7C%20Go%20%7C%20Rust%20%7C%20more-89b4fa" alt="Languages: TypeScript, JavaScript, Python, Go, Rust and more">
  12. <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-a6e3a1" alt="MIT license"></a>
  13. </p>
  14. <p align="center">
  15. <a href="docs/getting-started.md"><b>Get started</b></a> &nbsp;·&nbsp;
  16. <a href="docs/cli.md"><b>CLI</b></a> &nbsp;·&nbsp;
  17. <a href="docs/presets.md"><b>Presets</b></a> &nbsp;·&nbsp;
  18. <a href="docs/agents.md"><b>Coding agents</b></a> &nbsp;·&nbsp;
  19. <a href="docs/README.md"><b>Docs</b></a>
  20. </p>
  21. # jevlint
  22. **A model-based linter that tells you what to refactor first.**
  23. ESLint tells you a line broke a rule. jevlint reads every file in your repository, scores how
  24. clean it is against principles you choose, and hands you a ranked list: messiest and most-changed
  25. files first. Then it writes the prompt that gets Claude Code or Codex to fix them.
  26. <p align="center">
  27. <img src="docs/assets/before-after.svg" alt="A diff of a fictional file, src/orders/total.ts. A deeply nested function named proc, with one-letter names, an any type and a magic number 0.9, becomes orderTotal, which uses filter, reduce and a named MEMBER_DISCOUNT constant. Its score rises from 18 to 92, nesting from 4 to 1 and complexity from 5 to 2." width="820">
  28. </p>
  29. <p align="center"><sub>Illustrative example on a fictional file.</sub></p>
  30. ## Try it now
  31. No install, no API key, and your code stays on your machine:
  32. ```sh
  33. npx @indxjp/jevlint --ast-only
  34. ```
  35. ## Install
  36. ```sh
  37. npm install -g @indxjp/jevlint # or: pnpm add -g @indxjp/jevlint
  38. jevlint --version
  39. ```
  40. Requires Node.js 24.22.1 or later (or 22.23.4, or 26.12.1, on those lines).
  41. ## See it work
  42. A team inherits `shop-api` and has one afternoon for cleanup. jevlint picks the file, explains why,
  43. hands it to Claude Code, and confirms the score went up.
  44. <p align="center">
  45. <img src="docs/assets/demo.gif" alt="Terminal recording: jevlint audit ranks src/orders/process.ts worst at 21 out of 100, jevlint explain lists its findings, jevlint fix runs Claude Code on it and the score rises to 84, and a second audit shows the repository score rise from 58 to 63." width="820">
  46. </p>
  47. <p align="center"><sub>Simulated run on a fictional project. <a href="docs/assets/demo/demo.tape">Recording script</a>.</sub></p>
  48. ## Why it is different
  49. - **Two kinds of judgement.** AST analysis measures what is measurable, such as complexity and
  50. nesting. A [decision model](docs/concepts.md#decision-models) answers what needs judgement, such
  51. as "do these names carry meaning?"
  52. - **Decision models, not chatbots.** Models like [TypeSafe AI's Jev](https://typesafe.ai) return
  53. calibrated scores and probabilities rather than prose. That makes them fast and cheap, and it means results can be ranked and cached.
  54. - **A ranking, not a wall of warnings.** Files are ordered by mess, git churn and size, so the
  55. first item is the one worth your time.
  56. - **Reviews of a change, not only a repository.** `jevlint pr` and `jevlint commits` show a file's
  57. score before and after, and only what the change made worse. `--intent` also holds a change
  58. against its message and your `AGENTS.md`, and `pr --acceptance` against the acceptance criteria
  59. of the issues it closes.
  60. - **Your own rules, in one sentence.** An ast-grep pattern picks the code and a yes/no question
  61. judges each match, so a model's verdict gets a line number.
  62. - **Most source languages.** TypeScript, JavaScript, Python, Go and Rust get exact metrics. Other
  63. languages get [approximate ones](docs/scoring.md#languages-without-a-grammar), with no extra install.
  64. - **Principles as presets.** Audit against ideas from well-known software books, or write your own
  65. in a few lines of TOML.
  66. - **Scores you can settle.** A `jevlint-score` comment fixes an accepted score with a reason, so
  67. nobody chases points. See [Pinning scores](docs/scoring.md#pinning-scores).
  68. - **Ready for coding agents.** `jevlint prompt | claude -p`, or let `jevlint fix` run the agent.
  69. A [Claude Code plugin](#fix-it-with-a-coding-agent) and an edit hook are included.
  70. - **Pay for an answer once.** Results are cached by content, and an
  71. [S3-compatible bucket](docs/caching.md#share-the-cache-through-object-storage) shares them across CI
  72. and your team.
  73. ## What it is not
  74. - **Not a replacement for your linter.** Keep ESLint, Ruff, Clippy and your type checker for what
  75. they can decide exactly. jevlint ranks what they cannot judge.
  76. - **Not a verdict.** Model scores are calibrated opinions. They vary between models and can move
  77. between model versions, so treat them as candidates for a person to review, pin a model version
  78. in CI, and use [`jevlint test`](docs/presets.md#testing-a-question) to see when a question drifts.
  79. - **Not private by default, once a provider is on.** Everything except `--ast-only` sends code to
  80. the provider you configure. See [Before you run it](#before-you-run-it).
  81. ## Quick start
  82. ```sh
  83. jevlint auth set typesafe # store a key once, per user
  84. jevlint init # create jevlint.toml in this repository
  85. jevlint audit --dry-run # see what would be sent, with no provider requests
  86. jevlint audit # rank the whole codebase
  87. ```
  88. No TypeSafe access? [Use another provider](docs/providers.md), such as `openai`, `cloudflare` or
  89. `gateway`.
  90. ## Fix it with a coding agent
  91. ```sh
  92. jevlint prompt --top 3 --copy # paste into any agent
  93. jevlint prompt | claude -p # or pipe it
  94. jevlint fix --agent claude # or run the agent, then re-score
  95. jevlint quickfix --agent claude # or let it only edit, then see the diff, new score and commit
  96. ```
  97. In Claude Code, install the plugin for a skill and `/jevlint:audit`, `/jevlint:explain` and
  98. `/jevlint:review`. Its edit hook is off until you turn it on:
  99. ```text
  100. /plugin marketplace add INDXDev/jevlint
  101. /plugin install jevlint@jevlint
  102. ```
  103. See [Coding agents](docs/agents.md).
  104. ## Keep documents and code in agreement
  105. `jevlint spec` turns your documents into a checklist, then checks code and documents against it:
  106. ```sh
  107. jevlint spec compile --copy # a prompt for your agent: write .jevlint/spec from the docs
  108. jevlint spec check # which files violate an item, and which items nothing implements
  109. jevlint spec drift # where the docs and the checklist disagree
  110. ```
  111. The checklist is YAML with two levels: a project checklist, and one per feature. Each file is first
  112. routed to its feature, then judged against that feature's items only. See
  113. [Spec-driven development](docs/spec-driven-development.md).
  114. ## Write your own rule
  115. An ast-grep pattern decides which code is looked at. One question decides whether it is a problem,
  116. and yes means a violation. Each hit is reported on its line:
  117. ```toml
  118. # jevlint.toml
  119. [[rules]]
  120. id = "catch-hides-failure"
  121. language = "typescript"
  122. pattern = "try { $$$ } catch ($E) { $$$ }"
  123. question = "Does this catch block swallow a failure the caller needed to know about?"
  124. message = "This catch hides a failure"
  125. fix = "Rethrow it, or return an error the caller must handle."
  126. threshold = 0.8 # optional: report at or above this probability
  127. ```
  128. Each match is one provider request, up to `max_rule_matches` per rule and file, and `--ast-only` skips
  129. rules. See [Semantic rules](docs/presets.md#semantic-rules).
  130. Prove a preset question works with `good-*` and `bad-*` fixtures, and catch a model update that
  131. moves it:
  132. ```sh
  133. jevlint test # every fixture must land on the right side
  134. jevlint test --record # save today's answers
  135. jevlint test --drift # ask again, and list what moved
  136. ```
  137. ## Review a change
  138. ```sh
  139. jevlint pr --ast-only # what this branch's pull request made worse
  140. jevlint pr 42 --ast-only # the same, by number
  141. jevlint commits --count 5 --ast-only # the same, commit by commit
  142. jevlint commits --count 5 --intent # also check each message and AGENTS.md against the diff
  143. jevlint pr 42 --acceptance # does it meet the criteria of the issues it closes?
  144. ```
  145. Your working tree stays as it is, and your own config applies, not the change's. `--intent` reads
  146. the repository's instructions from the base commit, so a change cannot rewrite what it is judged by.
  147. See the [CLI reference](docs/cli.md#jevlint-pr-number), and
  148. [Continuous integration](docs/ci.md#review-what-a-pull-request-changes) to run it on every pull request.
  149. Catch a regression before it is committed, with no key and no network:
  150. ```sh
  151. jevlint init --pre-commit # stops a commit that makes a file worse than HEAD
  152. ```
  153. ## Fail CI on a low score
  154. ```toml
  155. # jevlint.toml
  156. [scoring]
  157. fail_under = 60 # exit 1 below this
  158. ```
  159. On a legacy codebase, gate on what is new instead of on the score:
  160. ```sh
  161. jevlint baseline --ast-only # commit .jevlint/baseline.json
  162. jevlint audit --new --ast-only --format github # exit 1 on anything new, as PR annotations
  163. jevlint audit --ast-only --format sarif > jevlint.sarif # for code scanning
  164. ```
  165. See [CI](docs/ci.md).
  166. ## Related projects
  167. Jev made a linter an obvious thing to build, and several people built one independently. None of
  168. these is affiliated with this project. They answer different questions, so pick by what you need:
  169. | Project | Unit of judgement | Use it when you want |
  170. | --- | --- | --- |
  171. | **@indxjp/jevlint** (this one) | Whole files, ranked. Optional per-match rules | To know what to refactor first, across a repository, against named principles |
  172. | [jev-lint](https://github.com/mizchi/jev-lint) | One ast-grep match, one sentence | A large catalogue of shipped rules with fitted cutoffs, for code that contradicts its own comments and names |
  173. | [@hazymoon/jevlint](https://github.com/Ice-Hazymoon/jevlint) | A rule per question, in a TypeScript config | Hand-written review rules with exemptions, and mutation tests that measure recall |
  174. | [@phox-js/jevlint](https://github.com/Fox-Islam/jevlint) | A Jev query | To lint the queries you send to Jev, not your code. Also for PHP and Python |
  175. | [@diffpal/jevlint](https://www.npmjs.com/package/@diffpal/jevlint), now [LintPal](https://github.com/diffpal/lintpal) | Changed lines in a Git comparison | Your team's Markdown rules as pull request checks |
  176. Baselines, SARIF output, fixtures, drift checks and message checks here follow the lead of the
  177. first two projects above. jevlint, jev-lint and @hazymoon/jevlint all use
  178. [ast-grep](https://ast-grep.github.io) to read code.
  179. ## Reference
  180. <details>
  181. <summary><b>Commands</b></summary>
  182. | Command | What it does |
  183. | --- | --- |
  184. | `jevlint audit [paths...]` | Score files and rank them. Also the default command. |
  185. | `jevlint explain <file>` | Show every finding and score for one file. |
  186. | `jevlint architecture [paths...]` | Review the codebase, directories and classes, and rank them worst to best. |
  187. | `jevlint architecture compile\|show\|check\|drift\|plan` | Compile an architecture SSOT from the code with a coding agent, draw it, check code against it with no model, and keep it current. |
  188. | `jevlint pr [number]` | Review what a GitHub pull request changes: scores before and after, and what got worse. |
  189. | `jevlint commits [revision]` | Review commits the same way, one by one, from `HEAD` backwards. |
  190. | `jevlint baseline [paths...]` | Record today's issues, so `audit --new` reports only what is new. |
  191. | `jevlint test [questions...]` | Run preset fixtures, record their answers, and detect drift. |
  192. | `jevlint hook` | Report what an edit or a staged change made worse, for agents and pre-commit. |
  193. | `jevlint spec compile\|check\|drift\|list` | Spec-driven development: compile documents into a checklist, then check code and documents against it. |
  194. | `jevlint prompt [files...]` | Print or copy a fix prompt for a coding agent. |
  195. | `jevlint fix [files...] --agent <name>` | Run an agent on the worst files, then re-score them. |
  196. | `jevlint quickfix [files...] --agent <name>` | Have an agent only edit the worst files, one at a time, then show the diff side by side, re-score and commit each. |
  197. | `jevlint init` | Create a repository or user config. |
  198. | `jevlint auth set\|list\|remove\|env` | Manage API keys. |
  199. | `jevlint preset [list\|show\|default\|new\|edit\|add\|remove]` | Choose, view, write and manage principle presets. Alone, it opens a menu. |
  200. | `jevlint cache info\|clear` | Inspect or empty the result cache. |
  201. | `jevlint config show\|path` | Show the merged config and where it came from. |
  202. </details>
  203. <details>
  204. <summary><b>Configuration</b></summary>
  205. ```toml
  206. # jevlint.toml
  207. presets = ["readable-code", "solid"]
  208. include = ["src/**"]
  209. exclude = ["**/*.generated.ts"]
  210. [provider]
  211. name = "typesafe"
  212. model = "jev-latest"
  213. [scoring]
  214. scale = 100 # use 1 for scores from 0 to 1
  215. fail_under = 60 # exit 1 below this, for CI
  216. [weights]
  217. "readable-code.naming" = 3 # care about this more
  218. "solid.dependency-inversion" = 0 # turn this off
  219. ```
  220. </details>
  221. <details>
  222. <summary><b>Built-in presets</b></summary>
  223. | Preset | Focus |
  224. | --- | --- |
  225. | `full` | The default: every preset below, 97 questions in one request per file |
  226. | `readable-code` | Names, comments, control flow, time to understand |
  227. | `clean-code` | Small functions, one level of abstraction, honest error handling |
  228. | `solid` | The five object-oriented design principles |
  229. | `software-design` | Deep modules, information hiding, complexity management |
  230. | `code-smells` | Classic refactoring smells |
  231. | `clean-architecture` | Dependency direction, boundaries, framework independence |
  232. | `kiss-dry-yagni` | Simplicity, duplication, speculative code |
  233. | `security` | Input validation, injection, secrets, access checks, safe failure |
  234. | `documentation` | File purpose, doc comments on public code, stated contracts, accurate docs |
  235. | `bug-hunt` | 43 known defect classes, from CWE and other taxonomies, to rank where bugs hide |
  236. Presets paraphrase publicly discussed principles in our own words. They are not affiliated with or
  237. endorsed by the original authors or publishers. See [docs/presets.md](docs/presets.md).
  238. </details>
  239. ## Documentation
  240. Start with the [documentation index](docs/README.md).
  241. - [Getting started](docs/getting-started.md)
  242. - [Concepts](docs/concepts.md)
  243. - [CLI reference](docs/cli.md)
  244. - [Configuration](docs/configuration.md)
  245. - [Providers](docs/providers.md)
  246. - [Presets](docs/presets.md)
  247. - [Scoring](docs/scoring.md)
  248. - [Architecture review](docs/architecture-review.md)
  249. - [Architecture-driven development](docs/architecture-driven-development.md) and the [SSOT reference](docs/architecture-reference.md)
  250. - [Spec-driven development](docs/spec-driven-development.md) and the [spec reference](docs/spec-reference.md)
  251. - [Coding agents](docs/agents.md)
  252. - [Caching](docs/caching.md)
  253. - [Continuous integration](docs/ci.md)
  254. - [JSON output](docs/json-output.md)
  255. - [Security and privacy](docs/security.md)
  256. - [Troubleshooting](docs/troubleshooting.md)
  257. - [Architecture](docs/architecture.md) and [code reference](docs/code-reference.md)
  258. ## Before you run it
  259. An audit sends the contents of your source files to the provider you configure. Read
  260. [Security and privacy](docs/security.md) first if your code is confidential. `audit --ast-only`
  261. never touches the network.
  262. ## Contributing
  263. See [CONTRIBUTING.md](CONTRIBUTING.md). To report a vulnerability, see [SECURITY.md](SECURITY.md).
  264. ## License
  265. [MIT](LICENSE)
  266. jevlint is an independent open-source project. It is not affiliated with or endorsed by TypeSafe
  267. AI, Cloudflare, Microsoft, OpenAI, Vercel or Anthropic. All product names are the property of their
  268. respective owners.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.