jev-use skillA
jev-use is agent-read markdown (skill) from shitianfang/jev-use: Use before ANY step that is a decision rather than writing: labelling, filtering or triaging MANY items; checking whether a command, test or build succeeded; picking the next action from options you can list; judging safety, quality or severity; or risk-checking each command of a checklist or pipeline before it runs. Route by where the facts already are: facts already in your context go to the jev_judge tool with ALL questions batched into ONE call; items sitting in a file or in tool output go t.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Handing off to Jev Jev answers a typed judgment in ~250 ms at a judgment-model rate ($0.042/Mtok in, $0 out) instead of LLM reasoning. It is a RATE win, not a token win: Jev spends *more* tokens per decision, not fewer. So the saving is real only when the decision **leaves the conversation** — which is what the routing below is for. You stay the planner and the writer. ## Route each decision: where are the facts × does it block? | Where the facts are | **Nothing is blocked** — you can keep working | **Blocked** — nothing proceeds until this is decided | | --- | --- | --- | | **Already in your context** | `jev_judge`, every question about that state batched into **ONE** call (`noul` yes/no, `choice` next action, `score` quality) | `jev_gate` on that one action before you run it — and if it is *every* tool call, wire `jev-use hook gate` as a PreToolUse hook **once** and the decision leaves the conversation for good: 24 gated commands, 17.1 s, **zero LLM tokens**, vs 46.9 s / $0.2366 through a supervisor LLM | …
Read the whole file at its exact version.
How to install
mdr add shitianfang/jev-use/jev-use@git:20260920.d26bee2mdr add shitianfang/jev-use/jev-use@sha256:75716b01e211c4e8Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_6nq5tnrwo47yy722)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260920.d26bee2 latest | 2026-09-20 | d26bee2 | 3,377 B | A | view · diff |
| git:20260920.e18181a | 2026-09-20 | e18181a | 3,511 B | A | view · diff |
| git:20260919.07c09fd | 2026-09-19 | 07c09fd | 2,099 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3377 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
shitianfang/jev-use · 25 stars · license MIT · pushed 2026-09-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_6nq5tnrwo47yy722 GET https://markdownregistry.com/api/v1/resolve?ref=shitianfang/jev-use/jev-use GET https://markdownregistry.com/api/v1/blob/75716b01e211c4e8c9170d1d68cbdd32756fc924b3274e8917c88212d0677001
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.