jevaluate-harness SKILL.md skillA

jevaluate-harness from tiffygk/jev-mode is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add tiffygk/jev-mode/jevaluate-harness@git:20261105.e7931dc

Pins git:20261105.e7931dc in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
tiffygk/jev-mode
Path
jevaluate-harness/SKILL.md
Versions recorded
7
Latest version
git:20261105.e7931dc, committed Nov 5, 2026
First version recorded
Sep 29, 2026
Size
3,073 bytes
Repository stars
15
License
a license file GitHub does not identify

Use when running a jevaluate rating round, re-rating after a rubric change, changing the jevaluate rubric, or publishing ratings to the jev-mode ratings folder.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Jevaluate Harness

The maintainer's process for `jevaluate-publish`. One rating is `jevaluate/read.md`; testing the rubric is the `jevaluate-eval` skill. If `$JEVALUATE_OVERLAY` is set, read that file first; its rules override the defaults here.

## Settings (yours, not in this skill)
- `$JEVALUATE_LIBRARY`: the private ratings library (default `~/.claude/jevaluate-library` if it exists, else `~/.jevaluate-library`).
- `$PRIVATE_TERMS`: your never-publish regexes, one per line. `library.py export` reads only `$JEVALUATE_LIBRARY/private-terms.txt`, so keep the file there (or symlink it) and have your pre-push hook read the same file.
- `$JEVALUATE_OVERLAY`: a markdown note of your own rules for these workflows, read first; no required format.

## Two principles
- **Code checks, text explains:** every rule has a row in `jevaluate/enforcement.md` naming the check that refuses a wrong answer, or why it stays judgment.
- **Ask for what is observed:** raters record type, the calls-Jev line, each decision's stakes as read and the verdict; `library.py add` derives kind and every n.a.

## Workflows
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add tiffygk/jev-mode/jevaluate-harness@sha256:c45ca1006183ff8c

The line at the top of this page pins the label git:20261105.e7931dc, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_jvlhsl7vx6w7xjzr.svg)](https://markdownregistry.com/a/art_jvlhsl7vx6w7xjzr)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 7 versions of this file, between Sep 29, 2026 and Nov 5, 2026, about one every 6 days.

versioncommittedcommitsizeaudit
git:20261105.e7931dc latest2026-11-05 e7931dc 3,073 BA view · diff
git:20261105.67806b32026-11-05 67806b3 3,044 BA view · diff
git:20261009.47b18012026-10-09 47b1801 2,460 BA view · diff
git:20261002.a0d26972026-10-02 a0d2697 2,427 BA view · diff
git:20260930.b83c6d42026-09-30 b83c6d4 2,385 BA view · diff
git:20260929.7f3447e2026-09-29 7f3447e 3,654 BA view · diff
git:20260929.27b1a5c2026-09-29 27b1a5c 3,502 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (3073 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

GitHub

tiffygk/jev-mode · 15 stars · license a license file GitHub does not identify · pushed 2026-11-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_jvlhsl7vx6w7xjzr
GET https://markdownregistry.com/api/v1/resolve?ref=tiffygk/jev-mode/jevaluate-harness
GET https://markdownregistry.com/api/v1/blob/c45ca1006183ff8ceb47f5cf52f63917dbaaac1313625d10df60fbbc92c1bde7

Your AI assistant 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.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from tiffygk/jev-mode

CLAUDE.md CLAUDE.md file
tiffygk/jev-mode · CLAUDE.md
git:20261105.edd8be1 · audit A · 15 stars
jev-lens SKILL.md skill
tiffygk/jev-mode · archive/jev-lens/SKILL.md · Legacy. Use only when images (photos, illustrations, screenshots) must reach TypeSafe's Jev (System One) model as text…
git:20261104.6316c85 · audit A · 15 stars
jev-sources SKILL.md skill
tiffygk/jev-mode · jev-sources/SKILL.md · Finds and cites TypeSafe's docs on Jev, including Noul, Choice, Score and Box questions, models and limits. Use when a…
git:20261105.5f5542d · audit A · 15 stars
jevaluate-eval SKILL.md skill
tiffygk/jev-mode · jevaluate-eval/SKILL.md · Use when testing whether the jevaluate rubric and instructions lead graders to the right answers: after a rubric or…
git:20261008.f2310f0 · audit A · 15 stars
jevaluate-private SKILL.md skill
tiffygk/jev-mode · jevaluate-private/SKILL.md · Rates a Jev project and keeps the rating private, with the same rubric and checks as Jevaluate, a verdict and fixes, a…
git:20261105.67806b3 · audit A · 15 stars
jevaluate-report SKILL.md skill
tiffygk/jev-mode · jevaluate-report/SKILL.md · Turns a Jevaluate rating a team agrees with into one Markdown report its coding agents can work from before a pull…
git:20261105.186f16a · audit A · 15 stars
jevaluate-publish SKILL.md skill
tiffygk/jev-mode · jevaluate/SKILL.md · Use when rating whether a project, repo, skill, workflow, plugin, agent product or post uses TypeSafe's Jev (System…
git:20261105.67806b3 · audit A · 15 stars

Every file in tiffygk/jev-mode

Browse by kind, by grade A, or by owner.