New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Jev Guard

by autonomous-ai in autonomous-ai/openharness

Fix a broken module under the live eye of Jev Guard, where Jev (TypeSafe's System One model) scores your own edits for progress, risk and trust.

MITAuto-check passed

Install Jev Guard

skills CLI
$ npx skills add autonomous-ai/openharness --skill jev-guard -a claude-code

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

GitHub CLI
$ gh skill install autonomous-ai/openharness jev-guard --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/autonomous-ai/openharness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/store/agents/jev-guard/skills/guard .claude/skills/jev-guard && 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-guard
GitHub stars
1.2k
Token cost
~590 tokens
SKILL.md length
268 words
Files
1
Skills in repo
99
Repo updated
First seen
Licence
MIT

At a glance

Fix a broken module under the live eye of Jev Guard, where Jev (TypeSafe's System One model) scores your own edits for progress, risk and trust.

  • Works in 3 steps: Edit project/score.js (that's the work).… → Watch the meters: toward (progress),… → Iterate until node project/test.js…
  • SKILL.md covers The loop, Reading Jev, Verifying and Driving Jev yourself
  • Calls node; needs TYPESAFE_API_KEY

What it does

Jev Guard is an agent skill from autonomous-ai/openharness. Fix a broken module under the live eye of Jev Guard, where Jev (TypeSafe's System One model) scores your own edits for progress, risk and trust.

Its SKILL.md is about 590 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across… The licence is MIT.

Example prompts

  • “/jev-guard”

Requirements

  • A credential in TYPESAFE_API_KEY

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Edit project/score.js (that's the work). Jev Guard auto-judges on each edit, or step it with
  2. Watch the meters: toward (progress), trust (Jev's confidence in the exact change), risk
  3. Iterate until node project/test.js prints ALL TESTS PASS and the viewer verdict reads as

What it can do on your machine

Read from SKILL.md and the folder at commit 74c2733. 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:

    • node

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

  • Network

    No URLs in SKILL.md.

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

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • TYPESAFE_API_KEY

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

Context cost

Jev Guard loads about 590 tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 268 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~39
When it runs · the whole SKILL.md, loaded when a task matches
~590

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 autonomous-ai/openharness at commit 74c2733, republished under its MIT licence (© autonomous-ai). 268 words, ~590 tokens.

Download SKILL.mdSave it as .claude/skills/jev-guard/SKILL.md (or your agent's skills folder).
name
jev-guard
description
Fix a broken module under the live eye of Jev Guard, where Jev (TypeSafe's System One model) scores your own edits for progress, risk and trust.

Jev Guard fix-under-watch

Jev Guard runs the test suite in project/ on every edit and asks Jev (TypeSafe's System One model) to judge each change: how much closer to the goal, how risky, how confident. The pane draws those as meters, a history chart and a run log. The goal is to make the tests pass and the verdict go green with a fix Jev trusts.

The loop

  1. Edit project/score.js (that's the work). Jev Guard auto-judges on each edit, or step it with "Judge now" / node "$JEV_DSH/toolchain/check.mjs".
  2. Watch the meters: toward (progress), trust (Jev's confidence in the exact change), risk (a red flag on a shaky edit). The run log shows PASS/FAIL per test run with what changed.
  3. Iterate until node project/test.js prints ALL TESTS PASS and the viewer verdict reads as a passing/green judgment.

Reading Jev

Jev's scores are layered on real test results: the suite is the ground truth, Jev is the overlay. A focused, honest fix — correct logic, nothing special-cased, nothing extra — is what reads as high trust / low risk. A hack that greps the test names or returns constants will pass the tests but Jev's risk meter will go red.

Verifying

  • node "$JEV_DSH/toolchain/check.mjs" validates the workspace (goal.json + project/test.js present and runnable).
  • node project/test.js is the real check: exit 0 + ALL TESTS PASS is done.
  • Watch the viewer verdict flip to a green/god-met judgment, not just the tests passing.

Driving Jev yourself

toolchain/jev.mjs exports a small client. Example (from the workspace) — ask Jev's opinion on an implementation choice:

bash
node --input-type=module -e '
import { evaluate, jev } from "$JEV_DSH/toolchain/jev.mjs";
const res = await evaluate({
  state: "Implement sumTo(5) by looping, vs a closed-form n*(n+1)/2. Which is more likely a correct, maintainable fix for a tiny module?",
  questions: {
    risky: jev.score({0:"safe",1:"risky",2:"reckless"}, "How risky is switching to the closed-form?"),
  },
});
console.log(JSON.stringify(res.answers, null, 2));
'

Without TYPESAFE_API_KEY this uses the deterministic mock; set the key to hit live Jev.

© autonomous-ai, 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 store/agents/jev-guard/skills/guard of autonomous-ai/openharness.

Open the folder on GitHubat commit 74c2733

Compare with similar skills

Jev Guard 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 Guard compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Jev Guard this skillautonomous-ai/openharness1.2k—~590Automated safety check: PassMIT
Safety Guardaffaan-m/ECC276k2 repos~554Automated safety check: NotesMIT
Guard Modegarrytan/gstack136k—~1kAutomated safety check: NotesMIT
Broken Imagesthedaviddias/Front-End-Checklist74k—~728Automated safety check: PassMIT
Broken Linksthedaviddias/Front-End-Checklist74k—~412Automated safety check: PassMIT
Es Modulesthedaviddias/Front-End-Checklist74k—~482Automated safety check: PassMIT

Similar skills

  • Safety Guard

    affaan-m/ECC

    Guard against destructive operations with three modes: Careful intercepts dangerous commands (rm -rf, git push --force, DROP TABLE) for confirmation, Freeze locks writes to one directory, and Guard…

    276k GitHub starsUsed in 2 repos~554 tokens
    DevelopmentAuto-check: notes

  • Guard Mode

    garrytan/gstack

    Switches on full safety by combining warnings before destructive commands with a block on edits outside one directory you choose, for work on production or live systems.

    136k GitHub stars~1k tokensUpdated today
    Agent WorkflowsAuto-check: notes

  • Broken Images

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing image assets, markup, and CDN or build transforms related to Fix broken images.

    74k GitHub stars~728 tokensUpdated 3 days ago
    Frontend & DesignAuto-check passed

  • Broken Links

    thedaviddias/Front-End-Checklist

    A skill your agent uses when auditing metadata, crawlability, structured data, or indexability related to Resolve internal broken links.

    74k GitHub stars~412 tokensUpdated 3 days ago
    Marketing & SEOAuto-check passed

  • Es Modules

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing scripts, client components, bundles, or runtime behavior related to Use ES modules (import/export).

    74k GitHub stars~482 tokensUpdated 3 days ago
    Auto-check passed

  • Safety Guard

    affaan-m/ECC

    本番システムでの作業時や、エージェントを自律的に実行する際に破壊的な操作を防ぐためにこのスキルを使用してください. An agent skill from affaan-m/ECC.

    276k GitHub stars~323 tokensUpdated 4 days ago
    Auto-check: notes

More from autonomous-ai/openharness

All 99 skills in this repo

  • G-code Slicer Tool

    autonomous-ai/openharness

    Slices 3D mesh files into printer-profiled plain G-code through real slicer CLIs, with backend discovery, input inspection, dry runs and static validation.

    1.2k GitHub stars~1.5k tokensUpdated today
    Auto-check passed

  • Home Assistant Automation Builder

    autonomous-ai/openharness

    Turns a home-automation request into standard, testable automations.yaml, run against Home Assistant Core's real triggers and verified with its own trace tool.

    1.2k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Score Music Composer

    autonomous-ai/openharness

    Turns a musical brief into LilyPond concert-pitch music, checked parts for each instrument and a playable practice pack.

    1.2k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • OrcaSlicer 3MF and G-code Workflow

    autonomous-ai/openharness

    Turns an STL and explicit printer and material requirements into compared OrcaSlicer plans, an editable 3MF project, checked G-code and a portable handoff.

    1.2k GitHub stars~1.5k tokensUpdated today
    Auto-check passed

  • Sheets and Docs Report Builder

    autonomous-ai/openharness

    Builds an editable DOCX report, a formula-driven XLSX workbook and a fresh LibreOffice PDF preview from one structured source file, then checks them together.

    1.2k GitHub stars~708 tokensUpdated today
    Auto-check passed

  • Bambu Labs

    autonomous-ai/openharness

    Dry-run, upload, and cautiously initiate local Bambu Lab print jobs from validated plain .gcode, using Bambu LAN FTPS/MQTT handoffs.

    1.2k GitHub starsUsed in 1 repo~2.1k tokens
    Auto-check: warnings

Questions about Jev Guard

What does Jev Guard do?

Fix a broken module under the live eye of Jev Guard, where Jev (TypeSafe's System One model) scores your own edits for progress, risk and trust. Jev Guard is an agent skill from autonomous-ai/openharness. Fix a broken module under the live eye of Jev Guard, where Jev (TypeSafe's System One model) scores your own edits for progress, risk and trust.

How do I install Jev Guard in Claude Code?

Run `npx skills add autonomous-ai/openharness --skill jev-guard -a claude-code`. Or copy the skill folder (store/agents/jev-guard/skills/guard in autonomous-ai/openharness) into .claude/skills/jev-guard in your project. Claude Code loads it when a task matches its description.

How do I install Jev Guard in Codex?

Run `npx skills add autonomous-ai/openharness --skill jev-guard -a codex`. Or copy the skill folder (store/agents/jev-guard/skills/guard in autonomous-ai/openharness) into .agents/skills/jev-guard in your project. Codex loads it when a task matches its description.

Can I use Jev Guard 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 autonomous-ai/openharness --skill jev-guard -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-guard, .gemini/skills/jev-guard, .github/skills/jev-guard and .opencode/skills/jev-guard in your project.

What does Jev Guard need to run?

Going by SKILL.md and its folder, Jev Guard needs the command-line tools its instructions call (node) and credentials named TYPESAFE_API_KEY. Our summary lists: A credential in TYPESAFE_API_KEY.

Does Jev Guard access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Jev Guard 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 Guard use?

Jev Guard 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 Guard use?

About 590 tokens (SKILL.md is roughly 2.4k 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 Guard?

Skills that share tags, products or a category with Jev Guard: Safety Guard (affaan-m/ECC, 276k stars), Guard Mode (garrytan/gstack, 136k stars), Broken Images (thedaviddias/Front-End-Checklist, 74k stars) and Broken Links (thedaviddias/Front-End-Checklist, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Jev Guard?

autonomous-ai (a GitHub organization) maintains it in autonomous-ai/openharness, which has 1,194 GitHub stars. The repository holds 99 skills in this directory. The repository was last updated on October 9, 2026.

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