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 Pendulum

by autonomous-ai in autonomous-ai/openharness

Design and verify Jev's balancing rigs in OpenHarness's viewer, where Jev keeps an inverted pendulum upright and loses it at high gravity.

MITAuto-check passed

Install Jev Pendulum

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

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

GitHub CLI
$ gh skill install autonomous-ai/openharness jev-pendulum --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-pendulum/skills/pendulum .claude/skills/jev-pendulum && 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-pendulum
GitHub stars
1.1k
Token cost
~782 tokens
SKILL.md length
363 words
Files
1
Skills in repo
100
Repo updated
First seen
Licence
MIT

At a glance

Design and verify Jev's balancing rigs in OpenHarness's viewer, where Jev keeps an inverted pendulum upright and loses it at high gravity.

  • Works in 3 steps: Update pendulum.json (title, gravity,… → node "$JEV_DSH/toolchain/check.mjs"… → Watch the rod. Does it stand, wobble,…
  • SKILL.md covers The loop, Reading the rig, Verifying a rig and Driving Jev yourself
  • Calls node; needs TYPESAFE_API_KEY

What it does

Jev Pendulum is an agent skill from autonomous-ai/openharness. Design and verify Jev's balancing rigs in OpenHarness's viewer, where Jev keeps an inverted pendulum upright and loses it at high gravity.

Its SKILL.md is about 780 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

  • “s balancing rigs in OpenHarness”
  • “/jev-pendulum”

Requirements

  • A credential in TYPESAFE_API_KEY

Workflow steps

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

  1. Update pendulum.json (title, gravity, maxTorque, gustEvery/gustStrength, and a style line that
  2. node "$JEV_DSH/toolchain/check.mjs" verifies the workspace's pendulum.json is valid. Run it
  3. Watch the rod. Does it stand, wobble, and sometimes drop on a hard rig — or always stand like a

What it can do on your machine

Read from SKILL.md and the folder at commit 50da5db. 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 Pendulum loads about 782 tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 363 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~38
When it runs · the whole SKILL.md, loaded when a task matches
~782

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 50da5db, republished under its MIT licence (© autonomous-ai). 363 words, ~782 tokens.

Download SKILL.mdSave it as .claude/skills/jev-pendulum/SKILL.md (or your agent's skills folder).
name
jev-pendulum
description
Design and verify Jev's balancing rigs in OpenHarness's viewer, where Jev keeps an inverted pendulum upright and loses it at high gravity.

Jev Pendulum rig design

Jev Pendulum simulates a rod hinged on a cart: Jev (TypeSafe's System One model) reads the rod's angle and swing every tick and picks a push on the cart to keep it up. The agent shapes pendulum.json — the rig (gravity, rod length, push authority, gusts) and the style line Jev balances by.

The loop

  1. Update pendulum.json (title, gravity, maxTorque, gustEvery/gustStrength, and a style line that tells Jev a strategy). The viewer watches it and Jev adapts live — no restart, no second server.
  2. node "$JEV_DSH/toolchain/check.mjs" verifies the workspace's pendulum.json is valid. Run it before you call a rig done.
  3. Watch the rod. Does it stand, wobble, and sometimes drop on a hard rig — or always stand like a statue (too easy) or always fall (too hard)? That observation is the finding.

Reading the rig

The viewer shows the cart and rod, five force arrows on the cart sized by the probability of each push, the "no return" lines where gravity beats the hardest shove, a lean budget meter, a run timer against the best run, and a tilt trace with every gust marked. Good rigs produce drama: a gust throws the rod toward the no return line, Jev's "under control?" answer dips, it recovers — and at high gravity it drops. gravity is the difficulty dial: 4–5 never falls, 7 is tense, 10+ topples every few seconds. A shorter length is harder too. gustStrength and gustEvery push it toward the edge without tipping it by themselves.

Show full SKILL.md (112 more words)Show less

Verifying a rig

node "$JEV_DSH/toolchain/check.mjs" returns non-zero when pendulum.json is invalid (no title, or a value outside its range, for example gravity 0.5..30, length 0.2..3, stepMs 30..2000). It also prints the lean past which the rod cannot be saved. It does not replace watching the motion: confirm Jev holds a mid gravity steady, that raising gravity or gusts makes it visibly struggle and fall, and that the style line shifts how decisively it recovers.

Driving Jev yourself

toolchain/jev.mjs exports a small client. Example (from the workspace) — ask Jev's read on a state before you commit to a rig:

bash
node --input-type=module -e '
import { evaluate, jev } from "$JEV_DSH/toolchain/jev.mjs";
const res = await evaluate({
  state: "Keep the rod upright.\nA stiff rod of length 1.00 stands hinged on a cart. You push the cart left or right along a rail.\nangle: +8.0°  velocity: +0.30 rad/s   (positive = leaning right, it falls at ±60°)\ncart: velocity +0.00 m/s   rail drag 0.2 per s\ngravity: 7.0   damping: 0.50\npush: LEFT_HARD -1.60, LEFT -0.80, CENTER +0.00, RIGHT +0.80, RIGHT_HARD +1.60 m/s²",
  questions: {
    action: jev.choice(["LEFT_HARD", "LEFT", "CENTER", "RIGHT", "RIGHT_HARD"], "Which push steadies the rod right now?"),
  },
});
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-pendulum/skills/pendulum of autonomous-ai/openharness.

Open the folder on GitHubat commit 50da5db

Compare with similar skills

Jev Pendulum 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 Pendulum compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Jev Pendulum this skillautonomous-ai/openharness1.1k—~782Automated safety check: PassMIT
Character Riggingcalesthio/OpenMontage65k—~460Automated safety check: PassMIT
Agent Load Balancerruvnet/ruflo74k2 repos~3.1kAutomated safety check: PassMIT
Rigsmvschwarz/openrig5.9k—~2.6kAutomated safety check: PassApache-2.0
Load Balancingsickn33/agentic-awesome-skills47k2 repos~2.9kAutomated safety check: NotesMIT
Developing PDF ViewerTriliumNext/Trilium38k—~1.8kAutomated safety check: PassAGPL-3.0

Similar skills

  • Character Rigging

    calesthio/OpenMontage

    Build data-driven 2D character rigs for local animation: parts, pivots, layers, constraints, views, and reusable rig packages.

    65k GitHub stars~460 tokensUpdated 4 days ago
    Media & CreativeAuto-check passed

  • Agent Load Balancer

    ruvnet/ruflo

    Agent skill for load-balancer - invoke with $agent-load-balancer

    74k GitHub starsUsed in 2 repos~3.1k tokens
    DevOps & CloudAuto-check passed

  • Rigs

    mvschwarz/openrig

    A skill your agent uses when the user types /rigs, or asks to install OpenRig, to see their OpenRig agents ("show me my agents", "show me the terminals", the welcome screen or the OpenRig view), to…

    5.9k GitHub stars~2.6k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Load Balancing

    sickn33/agentic-awesome-skills

    Configure load balancers and traffic distribution. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 2 repos~2.9k tokens
    DevOps & CloudAuto-check: notes

  • Developing PDF Viewer

    TriliumNext/Trilium

    A skill your agent uses when changing Trilium's built-in PDF viewer — anything under packages/pdfjs-viewer (the code injected into Mozilla's PDF.js viewer: bootstrap.ts, annotations.ts, pages.ts…

    38k GitHub stars~1.8k tokensUpdated today
    Documents & OfficeAuto-check passed

  • Jev Social

    sickn33/agentic-awesome-skills

    Run read-only, browser-grounded Instagram, TikTok, or LinkedIn research through Jev routing and socai CLI, returning source-linked evidence and reports.

    47k GitHub starsUsed in 1 repo~3.4k tokens
    Auto-check passed

More from autonomous-ai/openharness

All 100 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.

    1.1k 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.

    1.1k 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.

    1.1k 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.

    1.1k 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.

    1.1k 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.

    1.1k GitHub starsUsed in 1 repo~2.1k tokens
    Auto-check: warnings

Questions about Jev Pendulum

What does Jev Pendulum do?

Design and verify Jev's balancing rigs in OpenHarness's viewer, where Jev keeps an inverted pendulum upright and loses it at high gravity. Jev Pendulum is an agent skill from autonomous-ai/openharness. Design and verify Jev's balancing rigs in OpenHarness's viewer, where Jev keeps an inverted pendulum upright and loses it at high gravity.

How do I install Jev Pendulum in Claude Code?

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

How do I install Jev Pendulum in Codex?

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

Can I use Jev Pendulum 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-pendulum -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-pendulum, .gemini/skills/jev-pendulum, .github/skills/jev-pendulum and .opencode/skills/jev-pendulum in your project.

What does Jev Pendulum need to run?

Going by SKILL.md and its folder, Jev Pendulum 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 Pendulum 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 Pendulum 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 Pendulum use?

Jev Pendulum 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 Pendulum use?

About 782 tokens (SKILL.md is roughly 3.1k 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 Pendulum?

Skills that share tags, products or a category with Jev Pendulum: Character Rigging (calesthio/OpenMontage, 65k stars), Agent Load Balancer (ruvnet/ruflo, 74k stars), Rigs (mvschwarz/openrig, 5.9k stars) and Load Balancing (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Jev Pendulum?

autonomous-ai (a GitHub organization) maintains it in autonomous-ai/openharness, which has 1,149 GitHub stars. The repository holds 100 skills in this directory. The repository was last updated on October 8, 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.