Agent skill

Jev Lint Repo

by mizchi in mizchi/jev-lint

A skill your agent uses when changing jev-lint ITSELF — editing src/, shipped rule suites under rules/<language/<id/, or recorded runs in docs/data/.

MITAuto-check passedDevelopment

Install Jev Lint Repo

skills CLI
$ npx skills add mizchi/jev-lint --skill jev-lint-repo -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mizchi/jev-lint jev-lint-repo --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mizchi/jev-lint.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/jev-lint-repo .claude/skills/jev-lint-repo && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
jev-lint-repo
GitHub stars
119
Token cost
~942 tokens
SKILL.md length
434 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when changing jev-lint ITSELF — editing src/, shipped rule suites under rules/<language/<id/, or recorded runs in docs/data/.

  • Changing jev-lint ITSELF — editing src/
  • SKILL.md covers The loop, Rules and their evals and Plugin
  • Calls npm, node and just
  • Shipped rule suites under rules/<language/<id/

What it does

Jev Lint Repo is an agent skill from mizchi/jev-lint. Use when changing jev-lint ITSELF — editing src/, shipped rule suites under rules/<language/<id/, or recorded runs in docs/data/. Complements the user-facing jev-lint skill with the maintainer loop: fixtures, labels, calibration, CI, replay. Not for using jev-lint on another project.

Its SKILL.md is about 940 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Linting and formatting and Performance reviews. It works with npm. The repository describes itself as: lint text in code by jev scorerer. The licence is MIT.

When your agent uses it

  • Changing jev-lint ITSELF — editing src/
  • Shipped rule suites under rules/<language/<id/
  • Recorded runs in docs/data/

Example prompts

  • “/jev-lint-repo”

What it can do on your machine

Read from SKILL.md and the folder at commit af58a3b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm
    • node
    • just

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Jev Lint Repo loads about 942 tokens when it runs. Until then it costs about 76 tokens; SKILL.md has 434 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~76
When it runs · the whole SKILL.md, loaded when a task matches
~942

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mizchi/jev-lint at commit af58a3b, republished under its MIT licence (© mizchi). 434 words, ~942 tokens.

Download SKILL.mdSave it as .claude/skills/jev-lint-repo/SKILL.md (or your agent's skills folder).
name
jev-lint-repo
description
Use when changing jev-lint ITSELF — editing src/, shipped rule suites under rules/<language>/<id>/, or recorded runs in docs/data/. Complements the user-facing `jev-lint` skill with the maintainer loop: fixtures, labels, calibration, CI, replay. Not for using jev-lint on another project.

Maintaining jev-lint

The user-facing skill (skills/jev-lint/, symlinked into .claude/skills/) is the contract; this file is what is different when the repository is jev-lint's own. Read docs/internal.md before editing src/. The symlink is checked by npm run ci; run just skills-sync if it is missing.

The loop

bash
npm test                                   # no key, no network
npm run ci                                 # typecheck, test, build, eval --replay
node --experimental-strip-types src/cli.ts eval rules/<language>/<id> --repeat 3   # one suite, then --accept
node --experimental-strip-types src/cli.ts check --dry-run    # self-lint plan, via .jev-lint.yaml
node --experimental-strip-types src/cli.ts review --base main --retry 3

.jev-lint.yaml here points at source, tests, docs, and package.json, and excludes test/fixtures/, which holds planted defects for the cookbook.

Rules and their evals

  • A rule is rules/<language>/<id>/rule.yml with fixtures/, expect.yml (labelled defects and cleans), and an accepted baseline.json beside it. last.json is untracked. jev-lint eval rules/<language>/<id> --repeat 3 runs it; --accept promotes the run; npm run ci ends in jev-lint eval --replay, which fails on a case that was right when accepted and is wrong now, or on a rule whose question changed since its baseline. The case files carry NO // DEFECT / // CLEAN markers: those sat inside the file the model was shown, and the fits they produced were better than the rules (six fell when they came out). Editing a case file means shifting the labels below the edit; the test suite fails on a label no subject sits on.
  • Each suite labels only its own rule. tools/arms.ts and tools/grouping.ts run every rule over every suite's cases (evalCorpus), where another rule's answer on a suite's file is clean by default -- a defect for rule A in rule B's cases is B's false positive until labelled.
  • A fixture file named for the rule it exercises carries // jev-lint-ignore-file module-name-describes-contents on line 1, above its imports, so the module rule does not judge a name that was never a claim about the exports.
  • A new shipped rule needs its own fixtures with hard cleans, gaps, repeated eval, a report with a verdict, and a pass over unseen code before it enters rules/<language>/<id>/ with an accepted baseline.
  • Any change to a shipped rule's ask, criteria, note, matcher, subject or state is a new question: jev-lint eval --replay refuses the old baseline until you run jev-lint eval rules/<language>/<id> --repeat 3, read the result, and --accept it. Commit the baseline with the rule.
  • tools/arms.ts measures every arm per rule over every suite's cases (five arms, two passes, about twenty cents). Re-run it after changing a matcher or splitting a rule; the shipped state: choices are measurements, not preferences.
  • Figures quoted in README.md, docs/reference.md and docs/deepdive.md are measured. Change the measurement and the figure together, or neither.
Show full SKILL.md (37 more words)Show less

Plugin

The repository root is a Claude Code plugin (.claude-plugin/plugin.json, skills/, commands/). Every YAML block in skills/jev-lint/references/cookbook.md must load and match test/fixtures/cookbook/; npm test asserts it. A new recipe needs its code shape added to the fixture.

© mizchi, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/jev-lint-repo of mizchi/jev-lint.

Open the folder on GitHubat commit af58a3b

Compare with similar skills

Jev Lint Repo next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Jev Lint Repo compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Jev Lint Repo this skillmizchi/jev-lint119—~942Automated safety check: PassMIT
Install Anti-Slop Oxlint Rulesdmmulroy/anti-slop5.4k—~2.2kAutomated safety check: PassMIT
Setup Pre Commitfossasia/eventyay-interpretation1.6k12 repos~565Automated safety check: PassApache-2.0
Releasehyhmrright/brooks-lint1.5k—~1.2kAutomated safety check: PassMIT
Prepare Rslint npm Releaseweb-infra-dev/rslint461—~1.5kAutomated safety check: PassMIT
Create Saleor Packagesaleor/apps162—~608Automated safety check: PassCustom licence

Similar skills

  • Installs, updates or migrates the vendored anti-slop Oxlint plugin in a repository, keeping local rule changes and the plugin's license and provenance files.

    5.4k GitHub stars~2.2k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Setup Pre Commit

    fossasia/eventyay-interpretation

    Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo.

    1.6k GitHub starsUsed in 12 repos~565 tokens
    DevelopmentAuto-check passed
  • Release

    hyhmrright/brooks-lint

    Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG…

    1.5k GitHub stars~1.2k tokensUpdated 6 days ago
    DevelopmentAuto-check passed
  • Prepare Rslint npm Release

    web-infra-dev/rslint

    Prepare a stable release PR for the unified rslint npm packages by updating package versions and rule/TypeScript release metadata.

    461 GitHub stars~1.5k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Scaffold a new shared package in the saleor-apps monorepo under ./packages/.

    162 GitHub stars~608 tokensUpdated 4 days ago
    DevelopmentAuto-check passed
  • Dev

    Automattic/wordpress-activitypub

    Development workflows for WordPress ActivityPub plugin including wp-env setup, testing commands, linting, and build processes.

    582 GitHub stars~1.1k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from mizchi/jev-lint

  • Jev Lint

    mizchi/jev-lint

    A skill your agent uses when running jev-lint, adding it to a repository or its CI, choosing which of its shipped rule packs to use, writing a new jev-lint rule (an ast-grep matcher plus one…

    119 GitHub stars~2.6k tokensUpdated 9 days ago
    Auto-check passed

Works with

Categories

Questions about Jev Lint Repo

What does Jev Lint Repo do?

A skill your agent uses when changing jev-lint ITSELF — editing src/, shipped rule suites under rules/<language/<id/, or recorded runs in docs/data/. Jev Lint Repo is an agent skill from mizchi/jev-lint. Use when changing jev-lint ITSELF — editing src/, shipped rule suites under rules/<language/<id/, or recorded runs in docs/data/.

When should I use Jev Lint Repo?

Jev Lint Repo fits situations like: changing jev-lint ITSELF — editing src/; shipped rule suites under rules/<language/<id/; recorded runs in docs/data/.

How do I install Jev Lint Repo in Claude Code?

Run `npx skills add mizchi/jev-lint --skill jev-lint-repo -a claude-code`. Or copy the skill folder (.claude/skills/jev-lint-repo in mizchi/jev-lint) into .claude/skills/jev-lint-repo in your project. Claude Code loads it when a task matches its description.

How do I install Jev Lint Repo in Codex?

Run `npx skills add mizchi/jev-lint --skill jev-lint-repo -a codex`. Or copy the skill folder (.claude/skills/jev-lint-repo in mizchi/jev-lint) into .agents/skills/jev-lint-repo in your project. Codex loads it when a task matches its description.

Can I use Jev Lint Repo in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mizchi/jev-lint --skill jev-lint-repo -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/jev-lint-repo, .gemini/skills/jev-lint-repo, .github/skills/jev-lint-repo and .opencode/skills/jev-lint-repo in your project.

What does Jev Lint Repo need to run?

Going by SKILL.md and its folder, Jev Lint Repo needs the command-line tools its instructions call (npm, node and just).

Does Jev Lint Repo access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Jev Lint Repo safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Jev Lint Repo use?

Jev Lint Repo is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Jev Lint Repo use?

About 942 tokens (SKILL.md is roughly 3.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Jev Lint Repo?

Skills that share tags, products or a category with Jev Lint Repo: Install Anti-Slop Oxlint Rules (dmmulroy/anti-slop, 5.4k stars), Setup Pre Commit (fossasia/eventyay-interpretation, 1.6k stars), Release (hyhmrright/brooks-lint, 1.5k stars) and Prepare Rslint npm Release (web-infra-dev/rslint, 461 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Jev Lint Repo?

mizchi (a GitHub user) maintains it in mizchi/jev-lint, which has 119 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 2, 2026.

Source: mizchi/jev-lint on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.