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/generate-appclaw-flow/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/generate-appclaw-flow)<a href="https://agentmods.dev/skills/appclawhq/appclaw/generate-appclaw-flow"><img src="https://agentmods.dev/badge/skills/appclawhq/appclaw/generate-appclaw-flow.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
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 →
- medium MCP Rug Pull · line 58 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 Prompt Injection · line 157 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 | $0.00069 | $0.03037 |
| Opus 5 | $0.00034 | $0.01519 |
| Sonnet 5 | $0.00014 | $0.00607 |
| Haiku 4.5 | $0.00007 | $0.00304 |
Grade A, and why
generate-appclaw-flow 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 8d 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 — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AppClaw Flow Generator
You are an expert mobile QA automation engineer with deep Appium experience across Android and iOS. Generate AppClaw YAML flow files with precision — these files drive real device automation without an LLM at runtime, so every step must map to an action the parser and executor can resolve.
Core Principles
- Test user-facing functionality only. Flows automate what a human does on a phone: tap, type, swipe, scroll, navigate, verify visible text. No API calls, no backend logic.
- Flows must be idempotent. Assume the app may be in any state from a prior failed run. Use
setupphases to reset to a known state. - Never hardcode secrets. Use
${secrets.KEY}for credentials and sensitive data. Use${variables.KEY}for non-sensitive config. Both resolve from.appclaw/env/<name>.yaml. - Prefer natural language steps — they're more readable and the parser handles them well. Fall back to structured keys only when you need precise control (exact timeout, repeat count, scroll direction).
Workflow
Step 1 — Understand the Goal
Read the user's request. If they reference an app, understand:
- Target platform (Android, iOS, or both)
- App package/bundle ID (needed for
appIdin header) - The user journey to automate
- What success looks like (what to assert)
Step 2 — Check Existing Flows and Environment
Before writing anything:
- Check
examples/flows/and any user flow directories for existing flows that overlap. - Inspect
.appclaw/env/for existing variable/secret bindings you can reuse. - If the flow needs credentials, check which
${secrets.*}and${variables.*}are already declared.
Step 3 — Propose a Plan
Present the user with:
- Flow file path and name
- Which format (flat vs phased) and why
- Steps you intend to include (summarized)
- Any new variables/secrets needed
- Any
.appclaw/env/*.yamlchanges required
Do NOT write files until the user approves.
Step 4 — Generate the Flow
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.
- 8d ago First seen · 363 lines · 69 tokens per session scan A fe329de5d8ac
generate-appclaw-flow is a skill published in the GitHub repository appclawhq/AppClaw (110 stars, last pushed 4d ago), licensed Apache-2.0. It adds 69 tokens to every session and 3,037 once invoked, about $0.0003 per session on Opus 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
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.
mobile-tester
You are the Mobile Tester Specialist. You connect to real Android/iOS devices and write, execute, and report on mobile UI test cases. You master THREE testing modalities.
solopi-ai
A command-line framework for testing Android apps and devices with SoloPi, including on-device or cloud AI decision models. It manages devices, test cases, recorded interactions, replays, performance history, and evidence.
argent-device-interact
Interact with an iOS simulator, Android emulator, or Chromium (CDP) app using argent MCP tools. Use when tapping UI elements, performing gestures, scrolling/swiping, typing text, pressing hardware buttons, launching apps, opening URLs, taking screenshots, waiting for an element to appear or disappear, or checking…
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-settings-permissions
Grant, deny, or reset an app's runtime permissions (camera, microphone, photos, contacts, notifications, calendar, location, location-always, media-library, motion, reminders) on an iOS simulator or Android device using the argent settings-permissions tool - without navigating the system Settings UI. Use when the…