Jev directory
CommunityJev Tools & CLIs
Jev Test Filter — npmjs.com
Command-line tool that reads a git diff, asks Jev how much the change can alter each test's outcome, and prints filter arguments for vitest, jest, node --test, bun test, Playwright, cargo test, or go test.
- Reading time
- 2 min
- Published by
- Community
- Added
- Nov 2026
This is one of several Jev listings for the same project. The canonical entry is Jev Test Filter — mizchi.
Highlights
- Supports vitest, jest, node --test, bun test, Playwright, cargo test, and go test.
- Uses one shared state (the diff) and one question per test, with no agent loop and no file reading by the model.
- Requires Node 24 or newer, git, and a TypeSafe API key; rust and go formats also need cargo and go on PATH.
- --exec appends selection arguments to your command through spawn, with no shell in between.
- --verify-snapshots labels changed .snap files plausible, review, or unknown without editing snapshots or running tests.
Questions about this entry
Short answers drawn from the linked project or page.
Install with pnpm add -D jev-test-filter, or run it without installing via npx jev-test-filter --base main --exec -- vitest run. It requires Node 24 or newer, git, and a TypeSafe API key. The rust and go formats additionally need cargo and go on the PATH.
It emits filter arguments for vitest, jest, node --test, bun test, Playwright, cargo test, and go test, so the run covers the tests the change could plausibly break instead of all of them.
Everything after --exec -- is your command, and the selection arguments are appended to it. They go straight to spawn with no shell in between, so nothing can be re-split or re-quoted, and the command's exit code becomes the tool's exit code.
It reports framework, mode, argv, fallback, selected and total counts, and spend (calls, input and output tokens, milliseconds, retries, rate limits, and usd), plus every test with its file, name, line, selected flag, reason, score, and confidence.
It sends one shared state (the diff) and one question per test in a single round trip. Tests whose own body sits inside the diff are marked touched and cost no tokens; others are kept or dropped by score and confidence.
No. Installing the skill does not install the command, and you want both. Add the skill with npx skills add mizchi/jev-test-filter for Claude Code, Codex, Cursor and similar agents; the Claude Code plugin adds the same skill plus a /filter-tests command.
It is advisory and does not fail CI on a suspicious update. It reads the working-tree diff by default, does not edit snapshots or run tests, ignores image snapshots, and treats each .snap file as one question, so a suspicious entry marks the whole file for review.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
YouTube: Ray Amjad puts Jev inside an agentic coding loop and looks at what it costs to run.
YouTube: RoboNuggets puts Jev to work inside Claude Code.
X: Decision outputs in Grep
Hacker News: jevmem keeps Claude Code project memory by asking Jev which turns are worth saving.
avinashjetwani61 pointsJevmem – automatic project memory for Claude Code, built on JevRead the thread on Hacker NewsMore Jev resources like this
A local-first MCP server that gives Claude Code, Codex, Cursor, and OpenCode structured quality scores from Jev across correctness, complexity, tests, security, and other dimensions while the agent writes code.
Jev Tools & CLIs#community#typescript#mcp
Community
NiazMorshed2007/jev-reviewTypeScript
NiazMorshed2007/jev-reviewTypeScriptA local gateway for coding agents that asks Jev which tool to call each turn and steers the LLM when Jev is confident, while every other request goes to your usual provider untouched.
Jev Tools & CLIs#community#typescript#gateway
Community
vinilana/jev-gatewayTypeScript
vinilana/jev-gatewayTypeScriptA local-first Herdr CLI that filters your agent subscriptions with fixed eligibility rules, then asks TypeSafe Jev to rank the remaining Cursor, Claude Code, Codex, or OpenCode options and pick a reasoning effort.
Jev Tools & CLIs#community#typescript#cli
Community
nidhi-singh02/agent-routerTypeScript
nidhi-singh02/agent-routerTypeScriptA Jev-guided context compaction library for coding agents: instead of summarizing old context, Jev decides which tool calls and results still matter while user and assistant text is kept verbatim.
Jev Tools & CLIs#community#typescript#compaction
An experimental local context-pruning proxy for Claude Code and Codex that asks Jev, through the Vercel AI Gateway, which history spans to omit, then forwards a rewritten request with omission markers.
Jev Tools & CLIs#community#typescript#compaction
Community
compozy/yoshiTypeScript
compozy/yoshiTypeScriptA CLI that compiles natural-language agent rules into Jev programs: a few narrow typed questions answered by TypeSafe's System One model plus a reducer that computes the verdict in ordinary code, so a markdown rule becomes an invariant you can read, diff and unit-test.
Jev Tools & CLIs#cli#coding-agent#claude-code
Community
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.