app_creator

app_creator is a skill for Claude Code, Codex from espressif/esp-claw. It costs 35 tokens per session (638 once invoked), scanned A, original, Apache-2.0.

A workflow for creating, updating, publishing, or removing launcher-visible Lua applications on a device. These are packaged apps opened from the device's system launcher, not conversational skills or ordinary scripts.

In plain words
What is it for?
Use it for explicit requests to manage a launcher app, including its package, manifest, update, publication, or removal.
Why use it?
It prevents app packages from being confused with other extension types and ensures they are stored and changed in the correct writable area.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for explicit requests to manage a launcher app, including its package, manifest, update, publication, or removal.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/espressif/esp-claw/app_creator
About the project

ESP-Claw is an AI agent framework that runs on Espressif IoT chips and lets people define device behavior through conversation. It handles local sensing, decision-making, and execution for connected devices, with support for event-driven actions, structured memory, and MCP communication.

espressif/esp-claw · 2,260 stars · on GitHub · esp-claw.com

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add espressif/esp-claw --skill app_creator
Clone the repo
git clone --depth 1 https://github.com/espressif/esp-claw

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for app_creator

README.md
[![agentmods](https://agentmods.dev/badge/skills/espressif/esp-claw/app_creator/github.svg)](https://agentmods.dev/skills/espressif/esp-claw/app_creator)
Your own site
<a href="https://agentmods.dev/skills/espressif/esp-claw/app_creator"><img src="https://agentmods.dev/badge/skills/espressif/esp-claw/app_creator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for app_creator

Your own site · 80×15
<a href="https://agentmods.dev/skills/espressif/esp-claw/app_creator"><img src="https://agentmods.dev/badge/skills/espressif/esp-claw/app_creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 638 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.00638
Opus 5.5 $0.00014 $0.00255
Sonnet 5.5 $0.00007 $0.00128
Haiku 4.5 $0.00003 $0.00064

Measured today against content hash 6ecfbc7bd9e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

app_creator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

components/claw_capabilities/cap_app_mgr/skills/app_creator/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

App Creator

Use this skill only when the user explicitly requests creation, update, or removal of a launcher-visible runtime App. Apps are independent packages consumed by the System UI Launcher; they are not Skills. Use skill_creator when the requested behavior should be invoked conversationally by the model instead of launched from the UI.

This workflow manages runtime Apps under the writable DATA root. It does not edit firmware-baked SYSTEM Apps or create native capabilities.

Resolve The Runtime Apps Root

Before reading or writing a runtime App, run:

{"path":"{CUR_SKILL_DIR}/scripts/resolve_apps_root.lua","args":{}}

Treat the returned absolute path as <APPS_ROOT>. Do not assume /fatfs; DATA may be mounted on an SD card. If the path cannot be resolved, report the error and stop.

App Contract

Before creating or updating an App, read {CUR_SKILL_DIR}/references/app-package-spec.md and follow the complete package contract. Do not load the reference for removal-only requests.

Store each runtime App under <APPS_ROOT>/<app_id>/. Do not overwrite an existing App unless the user explicitly requested an update to that id.

Minimal manifest:

{
  "schema_version": 1,
  "id": "example_app",
  "display_name": "Example App",
  "entry": "scripts/main.lua",
  "visible": true
}

Create Or Update

  1. Resolve <APPS_ROOT> and inspect the exact target package before changing it.
  2. Read the package spec, then activate lua_package_authoring and follow its App-script rules.
  3. Write scripts and existing accessible assets first, then write launcher.json last. Do not fabricate binary JPEG data through a text file tool; omit the icon when no valid asset is available.
  4. Read the completed text files back and verify the manifest types, id, relative paths, entry existence, Lua imports, and packaged asset references.
  5. Call publish_app with only the final id:
{"app_id":"example_app"}
  1. Treat the tool result as authoritative. Report publication errors directly and do not claim success when publication fails.

Read the full file on GitHub · 68 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. today First seen · 68 lines · 35 tokens per session scan A 6ecfbc7bd9e4

Subscribe to this mod's changes

app_creator is a skill published in the GitHub repository espressif/esp-claw (2,260 stars, last pushed yesterday), licensed Apache-2.0. It adds 35 tokens to every session and 638 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-20.

Related

Other skills, from other repositories

app-ui-design

Mobile app UI design expert for iOS and Android. Use when designing app interfaces, creating design systems, ensuring accessibility, or following platform guidelines. Covers Material Design 3, Human Interface Guidelines, color theory, typography, and 2025 trends.

majiayu000/spellbook · 54 tokens

codex-expo-run-actions

Wire Expo projects into the Codex app with project-local run scripts and .codex/environments/environment.toml actions. Use when the user wants the Codex app Run button, build/run actions, action buttons, or a stable Expo start/run workflow from Codex.

openai/plugins · 61 tokens

mobile

A mobile handoff skill that sends the current coding task to a phone-review service and waits for feedback. It also explains how to retrieve and apply review comments or stop an active watcher.

minorun365/html-share · 61 tokens

quick-win-session

Generates guided first-action flows that help users achieve a meaningful result within 60 seconds to boost retention. Use when user wants quick win onboarding, time-to-value optimization, or first success moments.

rshankras/claude-code-apple-skills · 43 tokens

happy-handoff

A workflow for moving an unfinished Codex Desktop task to Happy on Android at a safe checkpoint. It records the workspace state and next step before starting the resumed session.

markoblogo/abvx-agent-skills · 38 tokens

apple-featuring

Use when preparing an Apple platform app for App Store featuring or the Apple Design Awards — readiness reviews before a launch or major update, featuring nominations in App Store Connect, nomination timing and pitch, choosing an ADA category, or asking how to get an app noticed by Apple. Covers iOS, iPadOS, macOS…

tartinerlabs/skills · 94 tokens