Agent skill

Kid Agents

by elophanto in elophanto/EloPhanto

A skill your agent uses when running dangerous shell commands, installing untrusted packages, or testing untrusted code that could damage the host.

Custom licenceAuto-check passed

Install Kid Agents

skills CLI
$ npx skills add elophanto/EloPhanto --skill kid-agents -a claude-code

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

GitHub CLI
$ gh skill install elophanto/EloPhanto kid-agents --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/elophanto/EloPhanto.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/kid-agents .claude/skills/kid-agents && 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
kid-agents
GitHub stars
106
Token cost
~1.6k tokens
SKILL.md length
832 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
Custom licence

At a glance

A skill your agent uses when running dangerous shell commands, installing untrusted packages, or testing untrusted code that could damage the host.

  • Works in 5 steps: decide if a kid is the right tool → spawn → execute → …
  • Running dangerous shell commands
  • SKILL.md covers Triggers, Overview, Iron rules and Phase 1 — decide if a kid is…, plus 8 more sections
  • Calls docker

What it does

Kid Agents is an agent skill from elophanto/EloPhanto. Use when running dangerous shell commands, installing untrusted packages, or testing untrusted code that could damage the host. Spawns a sandboxed kid (a child EloPhanto inside a hardened container) where rm -rf, fork bombs, kernel-touching ops, and similar are safely contained. Default vault scope is empty; default network is outbound-only. Distinct from organization specialists — kids are ephemeral, identity-less, and disposable.

Its SKILL.md is about 1.6k 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: Source-available autonomous AI agent with a self-model that actually changes as it runs - ego, affect and identity grounded in real psychology (Higgins, PAD/OCC). Writes its own…

When your agent uses it

  • Running dangerous shell commands
  • Installing untrusted packages
  • Testing untrusted code that could damage the host

Example prompts

  • “/kid-agents”

Requirements

  • Docker

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. decide if a kid is the right tool
  2. spawn
  3. execute
  4. read outputs (optional)
  5. destroy

What it can do on your machine

Read from SKILL.md and the folder at commit 7bfc65d. 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:

    • docker

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

  • Network

    No URLs in SKILL.md. Its commands use docker, which can reach the network depending on how they are called.

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

  • Credentials

    Names no API keys, tokens, secrets or passwords.

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

Context cost

Kid Agents loads about 1.6k tokens when it runs. Until then it costs about 112 tokens; SKILL.md has 832 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~112
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 832 words (~1,620 tokens).

“A kid is a child EloPhanto running inside a hardened Docker container. It exists to do things that are too dangerous to run on the host: package installs, untrusted scripts, fork bombs, kernel-poking, code you don't fully trust. The container's…”

— opening of SKILL.md by elophanto, Custom licence
name
kid-agents

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/kid-agents of elophanto/EloPhanto.

Open the folder on GitHubat commit 7bfc65d

Compare with similar skills

Kid Agents 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.

Kid Agents compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Kid Agents this skillelophanto/EloPhanto106—~1.6kAutomated safety check: PassCustom licence
Packaging Static Installernetdata/netdata81k—~4.5kAutomated safety check: NotesGPL-3.0
Generating Python Installeraffaan-m/ECC276k1 repos~6.1kAutomated safety check: PassMIT
Shell ScriptingRightNow-AI/openfang18k—~827Automated safety check: PassApache-2.0
Crush Shell Builtinscharmbracelet/crush29k—~790Automated safety check: PassCustom licence
Add Packageremix-run/remix33k—~2kAutomated safety check: PassMIT

Similar skills

  • Build, test, review or troubleshoot Netdata static makeself installers and packaging/makeself changes.

    81k GitHub stars~4.5k tokensUpdated today
    DevOps & CloudAuto-check: notes
  • Commercial-grade Python installer expert for Windows: Nuitka extreme compilation, dist slimming, DLL footprint analysis, and Inno Setup packaging to ship the smallest, fastest installers.

    276k GitHub starsUsed in 1 repo~6.1k tokens
    Testing & QAAuto-check passed
  • Shell Scripting

    RightNow-AI/openfang

    Shell scripting expert for Bash, POSIX compliance, error handling, and automation

    18k GitHub stars~827 tokensUpdated 3 mo ago
    DevelopmentAuto-check passed
  • Crush Shell Builtins

    charmbracelet/crush

    Explains how to add a new in-process builtin command to Crush's embedded POSIX shell, so it is intercepted before reaching the OS, with context polling and exit-status rules.

    29k GitHub stars~790 tokensUpdated today
    DevelopmentAuto-check passed
  • Add Package

    remix-run/remix

    Create or align a package in the Remix monorepo to match existing package conventions.

    33k GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check passed
  • Kubeshark Installer

    kubeshark/kubeshark

    Installs and configures Kubeshark on a Kubernetes cluster, choosing between the quick CLI path and a Helm install with custom values.

    12k GitHub stars~3.6k tokensUpdated today
    DevOps & CloudAuto-check: notes

More from elophanto/EloPhanto

All 11 skills in this repo
  • Pikastream Video Meeting

    elophanto/EloPhanto

    Join a Google Meet or Zoom call as a video meeting agent via PikaStreaming.

    106 GitHub stars~1.5k tokensUpdated 9 days ago
    Auto-check passed
  • Metaplex

    elophanto/EloPhanto

    Metaplex development on Solana — NFTs, tokens, compressed NFTs, candy machines, token launches.

    106 GitHub stars~1.6k tokensUpdated 9 days ago
    Auto-check passed
  • 12 Principles Of Animation

    elophanto/EloPhanto

    Audit animation code against Disney's 12 principles adapted for web.

    106 GitHub stars~1.5k tokensUpdated 9 days ago
    Auto-check passed
  • Deep Research

    elophanto/EloPhanto

    A skill your agent uses when investigating any claim, question, or topic where the easy first answer is likely insufficient.

    106 GitHub stars~2.4k tokensUpdated 9 days ago
    Auto-check passed
  • Nextjs16 Skills

    elophanto/EloPhanto

    Key facts and links for Next.js 16. An agent skill from elophanto/EloPhanto.

    106 GitHub stars~1.4k tokensUpdated 9 days ago
    Auto-check passed
  • Pumpfun Livestream

    elophanto/EloPhanto

    Stream a local video file to Pump.fun's livestream UI for the agent's coin.

    106 GitHub stars~3.2k tokensUpdated 9 days ago
    Auto-check passed

Questions about Kid Agents

What does Kid Agents do?

A skill your agent uses when running dangerous shell commands, installing untrusted packages, or testing untrusted code that could damage the host. Kid Agents is an agent skill from elophanto/EloPhanto. Use when running dangerous shell commands, installing untrusted packages, or testing untrusted code that could damage the host.

When should I use Kid Agents?

Kid Agents fits situations like: running dangerous shell commands; installing untrusted packages; testing untrusted code that could damage the host.

How do I install Kid Agents in Claude Code?

Run `npx skills add elophanto/EloPhanto --skill kid-agents -a claude-code`. Or copy the skill folder (skills/kid-agents in elophanto/EloPhanto) into .claude/skills/kid-agents in your project. Claude Code loads it when a task matches its description.

How do I install Kid Agents in Codex?

Run `npx skills add elophanto/EloPhanto --skill kid-agents -a codex`. Or copy the skill folder (skills/kid-agents in elophanto/EloPhanto) into .agents/skills/kid-agents in your project. Codex loads it when a task matches its description.

Can I use Kid Agents 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 elophanto/EloPhanto --skill kid-agents -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/kid-agents, .gemini/skills/kid-agents, .github/skills/kid-agents and .opencode/skills/kid-agents in your project.

What does Kid Agents need to run?

Going by SKILL.md and its folder, Kid Agents needs the command-line tools its instructions call (docker). Our summary lists: Docker.

Does Kid Agents access the network?

SKILL.md contains no URLs. Its commands use docker, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Kid Agents 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 Kid Agents use?

Kid Agents has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Kid Agents use?

About 1.6k tokens (SKILL.md is roughly 6.5k 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 Kid Agents?

Skills that share tags, products or a category with Kid Agents: Packaging Static Installer (netdata/netdata, 81k stars), Generating Python Installer (affaan-m/ECC, 276k stars), Shell Scripting (RightNow-AI/openfang, 18k stars) and Crush Shell Builtins (charmbracelet/crush, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Kid Agents?

elophanto (a GitHub user) maintains it in elophanto/EloPhanto, which has 106 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 1, 2026.

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