PalmClaw is an AI agent framework that runs directly on Android phones, keeping sessions, memory, skills, tools, and the agent loop on the device while using a configured LLM API for inference. It is for users who want an agent to access mobile capabilities and perform controlled tasks through permissions, confirmations, and workspace boundaries. Its catalogue skills extend the agent's workflows and integrations.
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.
npx skills add ModalityDance/PalmClaw --skill android-personalgit clone --depth 1 https://github.com/ModalityDance/PalmClawWrote 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.
[](https://agentmods.dev/skills/modalitydance/palmclaw/android-personal)<a href="https://agentmods.dev/skills/modalitydance/palmclaw/android-personal"><img src="https://agentmods.dev/badge/skills/modalitydance/palmclaw/android-personal/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.
<a href="https://agentmods.dev/skills/modalitydance/palmclaw/android-personal"><img src="https://agentmods.dev/badge/skills/modalitydance/palmclaw/android-personal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00037 | $0.00374 |
| Opus 5.5 | $0.00015 | $0.00150 |
| Sonnet 5.5 | $0.00007 | $0.00075 |
| Haiku 4.5 | $0.00004 | $0.00037 |
Grade A, and why
android-personal 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 1mo ago.
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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- 1mo ago First seen · 43 lines · 37 tokens per session scan A c001cf849848
android-personal is a skill published in the GitHub repository ModalityDance/PalmClaw (1,171 stars, last pushed 2d ago), licensed AGPL-3.0. It adds 37 tokens to every session and 374 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 2026-08-30.
Other skills, from other repositories
app_creator
Create, update, publish, or remove an on-device launcher App when the user explicitly requests a launcher-visible Lua application; not for Skills or generic Lua scripts.
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.
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.
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.
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.
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.