Borrowing it
Nothing to install: this file belongs to appclawhq/AppClaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/appclawhq/AppClaw/main/.agents/skills/use-appclaw-cli/SKILL.mdgit clone --depth 1 https://github.com/appclawhq/AppClawWrote 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/appclawhq/appclaw/use-appclaw-cli)<a href="https://agentmods.dev/skills/appclawhq/appclaw/use-appclaw-cli"><img src="https://agentmods.dev/badge/skills/appclawhq/appclaw/use-appclaw-cli/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/appclawhq/appclaw/use-appclaw-cli"><img src="https://agentmods.dev/badge/skills/appclawhq/appclaw/use-appclaw-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 8 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 6 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 218 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Prompt Injection · line 243 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium MCP Rug Pull · line 312 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 362 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Excessive Agency · line 328 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Prompt Injection · line 387 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 389 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00066 | $0.04401 |
| Opus 5.5 | $0.00026 | $0.01760 |
| Sonnet 5.5 | $0.00013 | $0.00880 |
| Haiku 4.5 | $0.00007 | $0.00440 |
Grade A, and why
use-appclaw-cli 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.
How it starts
The opening of the file, as written. The whole thing — 472 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AppClaw CLI Operator
You are an expert mobile automation engineer with deep Appium and real-device experience across Android and iOS. Help users install, configure, run, and troubleshoot AppClaw — the agentic AI layer for mobile automation via appium-mcp.
Prerequisites
AppClaw requires:
- Node.js 18+
- A connected device — USB Android, Android emulator, iOS simulator, or real iOS device
- An LLM API key (except for Ollama which runs locally)
Install
# Global install
npm install -g appclaw
# Or run from a local clone
git clone https://github.com/AppiumTestDistribution/appclaw.git
cd appclaw && npm install
Verify
appclaw --help
appclaw --version
From a local clone, use npm start instead of appclaw:
npm start -- --help
npm start "Open Settings"
npm start -- --flow examples/flows/google-search.yaml
Source of Truth
- Prefer
appclaw --helpfor current flag reference. - Inspect
.envfor the user's active configuration. - Read
.appclaw/env/for variable/secret bindings before giving flow advice. - Check connected devices via
adb devices(Android) orxcrun simctl list devices(iOS) before troubleshooting device issues. - Do not invent unsupported flags or commands.
CLI Modes & Commands
1. Agent Mode (default) — LLM-driven automation
# Resident shell — device picker, then a prompt you can run goal after goal in
appclaw
# One goal, then exit — holds the finished screen until a key is pressed
appclaw "Open Settings and turn on WiFi"
appclaw "Send hello on WhatsApp to Mom"
# With platform/device flags
appclaw --platform ios --device-type simulator "Open Safari"
appclaw --platform ios --device "iPhone 17 Pro" "Open Settings"
appclaw --udid 00008120-XXXX "Launch YouTube"
# Unattended (CI, scripts): plain console output, exits on its own
APPCLAW_TUI=off appclaw "Open Settings"
Both forms open Terminal Studio in goal mode (see below) — a plain line at its
prompt is a goal. The exit code is unchanged: 0 when every sub-goal completed, 1
otherwise. --record, --json, a non-TTY or APPCLAW_TUI=off take the plain
console path instead.
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 Changed · +18 lines 2d7e85d0c04f
- 2mo ago First seen · 454 lines · 66 tokens per session scan A 994e408988e1
use-appclaw-cli is a skill published in the GitHub repository appclawhq/AppClaw (120 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 66 tokens to every session and 4,401 once invoked, about $0.0003 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
argent-metro-debugger
Debug a JS runtime via CDP using argent debugger tools. Primary path is React Native via Metro (iOS / Android / Vega); a subset of the tools (debugger-connect, debugger-status, debugger-evaluate, debugger-log-registry) also drive a Chromium (CDP) app's renderer (an Electron app, or any Chromium browser exposing CDP)…
argent-react-native-optimization
Optimizes a React Native app by profiling first to find real bottlenecks, then sweeping for mechanical issues. Entry-point for all performance work. Use when the app feels slow, user asks to optimize, fix re-renders, reduce jank, or improve startup. Delegates to argent-react-native-profiler for measurement.
nightly-audit-engineer-getting-started
A first-conversation guide for setting up a code-audit assistant. A code audit is a focused review of source code for defects or risky behavior, with the needed repository, scope, concerns, permissions, and schedule clarified first.
mobile-automation
Control Android and iOS devices, emulators and simulators — launch apps, tap, swipe, type, take screenshots, read the accessibility tree. Use when a task involves a mobile device or app, mobile UI testing, or reproducing a bug on a phone.
nightly-audit-engineer-ops
A workflow for reviewing code for reproducible quality problems and recording the evidence behind each finding. It follows data through inputs, permissions, storage, asynchronous work, and recovery, then suggests the smallest authorized fix.
nightly-audit-engineer-evidence
A small local checker that creates stable identifiers for code-audit findings and marks duplicates within the current batch or among previously seen findings. It processes supplied JSON with Python and does not infer whether a problem was fixed.