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 Pong

by autonomous-ai in autonomous-ai/openharness

Design and verify Jev's paddle-defense courts in OpenHarness's viewer, where Jev keeps a rally alive and loses it as the ball accelerates.

MITAuto-check passed

Install Jev Pong

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

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

GitHub CLI
$ gh skill install autonomous-ai/openharness jev-pong --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-pong/skills/pong .claude/skills/jev-pong && 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-pong
GitHub stars
1.2k
Token cost
~770 tokens
SKILL.md length
360 words
Files
1
Skills in repo
100
Repo updated
First seen
Licence
MIT

At a glance

Design and verify Jev's paddle-defense courts in OpenHarness's viewer, where Jev keeps a rally alive and loses it as the ball accelerates.

  • Works in 3 steps: Update pong.json (title, courtW/courtH,… → node "$JEV_DSH/toolchain/check.mjs"… → Watch the rally. Does Jev return a few…
  • SKILL.md covers The loop, Reading the court, Verifying a court and Driving Jev yourself
  • Calls node; needs TYPESAFE_API_KEY

What it does

Jev Pong is an agent skill from autonomous-ai/openharness. Design and verify Jev's paddle-defense courts in OpenHarness's viewer, where Jev keeps a rally alive and loses it as the ball accelerates.

Its SKILL.md is about 770 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 paddle-defense courts in OpenHarness”
  • “/jev-pong”

Requirements

  • A credential in TYPESAFE_API_KEY

Workflow steps

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

  1. Update pong.json (title, courtW/courtH, speed, maxSpeed, accel, and a style line that tells
  2. node "$JEV_DSH/toolchain/check.mjs" verifies the workspace's pong.json is valid. Run it
  3. Watch the rally. Does Jev return a few balls, speed the ball up, and sometimes drop it — or

What it can do on your machine

Read from SKILL.md and the folder at commit cc4983e. 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 Pong loads about 770 tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 360 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~37
When it runs · the whole SKILL.md, loaded when a task matches
~770

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 cc4983e, republished under its MIT licence (© autonomous-ai). 360 words, ~770 tokens.

Download SKILL.mdSave it as .claude/skills/jev-pong/SKILL.md (or your agent's skills folder).
name
jev-pong
description
Design and verify Jev's paddle-defense courts in OpenHarness's viewer, where Jev keeps a rally alive and loses it as the ball accelerates.

Jev Pong court design

Jev Pong simulates a paddle-defense rally: Jev (TypeSafe's System One model) reads the ball's position and velocity every tick and moves the paddle to meet the return. Each hit speeds the ball up, so a long rally outruns the paddle. The agent shapes pong.json — the court, the paddle's authority, and the starting ball speed.

The loop

  1. Update pong.json (title, courtW/courtH, speed, maxSpeed, accel, 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 pong.json is valid. Run it before you call a court done.
  3. Watch the rally. Does Jev return a few balls, speed the ball up, and sometimes drop it — or never miss (too easy) / always drop (too hard)? That observation is the finding.

Reading the court

The viewer shows the court, five ghost paddles lit by the probability of each move, a ring where the ball will cross Jev's wall, the paddle's remaining reach, a pace meter with the pace where the paddle is outrun, the text Jev reads, and a bar for every finished rally. Good courts produce a natural arc: Jev holds a few returns, the ball accelerates, Jev scrambles harder, and it finally slips past. speed sets the serve pace; accel controls how fast each rally runs away; maxSpeed is how far a plain paddle move goes per decision (a FAST move goes twice as far).

Show full SKILL.md (115 more words)Show less

Verifying a court

node "$JEV_DSH/toolchain/check.mjs" returns non-zero when pong.json is invalid (no title, or a value outside its range, for example speed 1..60 or stepMs 30..2000). It also prints the pace past which a far ball is out of the paddle's reach. It doesn't replace watching the motion: confirm Jev holds a low speed comfortably, that raising speed or accel shortens rallies and raises the miss count, and that the style line shifts how decisively it moves.

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 court:

bash
node --input-type=module -e '
import { evaluate, jev } from "$JEV_DSH/toolchain/jev.mjs";
const res = await evaluate({
  state: "Keep the rally alive.\nYou are the paddle on the left wall of a 200x120 court. y 0 is the top, y grows downward.\npaddle: centre y 50.0, half-height 13.0, face at x 8\npaddle speed: a plain move shifts it 2.0 per decision, a FAST move 4.0 per decision\nball: x 40.0  y 70.0  vx -6.0  vy 2.0  radius 3  (toward you)\nspeed: 6.0 per decision   rally: 0",
  questions: {
    move: jev.choice(["MOVE_UP_FAST", "MOVE_UP", "HOLD", "MOVE_DOWN", "MOVE_DOWN_FAST"], "Which paddle move keeps the rally alive?"),
  },
});
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-pong/skills/pong of autonomous-ai/openharness.

Open the folder on GitHubat commit cc4983e

Compare with similar skills

Jev Pong 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 Pong compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Jev Pong this skillautonomous-ai/openharness1.2k—~770Automated safety check: PassMIT
Courtsickn33/agentic-awesome-skills47k—~1.5kAutomated safety check: PassMIT
Paddle DebugPaddlePaddle/Paddle24k—~1.4kAutomated safety check: PassApache-2.0
Jev Socialsickn33/agentic-awesome-skills47k1 repos~3.4kAutomated safety check: PassMIT
Jev Usesickn33/agentic-awesome-skills47k1 repos~2.5kAutomated safety check: PassMIT
Paddle BuildPaddlePaddle/Paddle24k—~1kAutomated safety check: PassApache-2.0

Similar skills

  • Court

    sickn33/agentic-awesome-skills

    Put an idea on trial: a prosecutor and a defense Claude argue, 12 juror sub-agents vote independently, and a judge reads the verdict and the changes that would flip it.

    47k GitHub stars~1.5k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Paddle Debug

    PaddlePaddle/Paddle

    在 Paddle 代码库中定位问题并输出高质量调试报告的专用技能。当遇到以下场景时优先使用：(1) Paddle 框架 bug 调试，(2) 算子实现问题排查，(3) 训练脚本异常诊断，(4) 分布式训练故障定位，(5) CUDA/GPU 相关错误处理，(6) 需要生成结构化调试报告。

    24k GitHub stars~1.4k tokensUpdated today
    AI & LLM EngineeringAuto-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

  • Jev Use

    sickn33/agentic-awesome-skills

    Route enumerable judgment steps - did it work, which option, how risky, is this safe to run - to the Jev judgment model through the jevjudge and jevgate MCP tools, batched into one call per state.

    47k GitHub starsUsed in 1 repo~2.5k tokens
    Agent WorkflowsAuto-check passed

  • Paddle Build

    PaddlePaddle/Paddle

    A skill your agent uses when needing to compile, rebuild, or install Paddle from source after code changes.

    24k GitHub stars~1k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Paddle Design Compiler

    PaddlePaddle/Paddle

    A skill your agent uses when working with Paddle 3.0 compiler full pipeline: SOT (Symbolic Opcode Translator) for bytecode-level dy2st graph capture, PIR (Paddle IR) for SSA-based intermediate…

    24k GitHub stars~3.6k tokensUpdated today
    AI & LLM EngineeringAuto-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.

    1.2k 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 Pong

What does Jev Pong do?

Design and verify Jev's paddle-defense courts in OpenHarness's viewer, where Jev keeps a rally alive and loses it as the ball accelerates. Jev Pong is an agent skill from autonomous-ai/openharness. Design and verify Jev's paddle-defense courts in OpenHarness's viewer, where Jev keeps a rally alive and loses it as the ball accelerates.

How do I install Jev Pong in Claude Code?

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

How do I install Jev Pong in Codex?

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

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

What does Jev Pong need to run?

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

Jev Pong 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 Pong use?

About 770 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 Pong?

Skills that share tags, products or a category with Jev Pong: Court (sickn33/agentic-awesome-skills, 47k stars), Paddle Debug (PaddlePaddle/Paddle, 24k stars), Jev Social (sickn33/agentic-awesome-skills, 47k stars) and Jev Use (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 Pong?

autonomous-ai (a GitHub organization) maintains it in autonomous-ai/openharness, which has 1,210 GitHub stars. The repository holds 100 skills in this directory. The repository was last updated on October 10, 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.