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 iurysza/android-use --skill setup-goalgit clone --depth 1 https://github.com/iurysza/android-useWrote 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/iurysza/android-use/setup-goal)<a href="https://agentmods.dev/skills/iurysza/android-use/setup-goal"><img src="https://agentmods.dev/badge/skills/iurysza/android-use/setup-goal/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/iurysza/android-use/setup-goal"><img src="https://agentmods.dev/badge/skills/iurysza/android-use/setup-goal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00039 | $0.01321 |
| Opus 5.5 | $0.00016 | $0.00528 |
| Sonnet 5.5 | $0.00008 | $0.00264 |
| Haiku 4.5 | $0.00004 | $0.00132 |
Grade A, and why
setup-goal 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup Goal
Turn an idea into an execution-ready package at ai-artifacts/goals/<slug>/. Extract intent, resolve material uncertainty, agree on testable facts, and produce a concrete plan before implementation begins.
Do not implement the goal while running this skill.
Goal package
ai-artifacts/goals/<slug>/
├── intent.md
├── facts.md
├── facts.meta.json
├── plan.md
├── dev-log.md
└── goal.md
Create files only as their phase is reached. Markdown files are the human-readable source of truth. Tool-specific working files may live beside them but must not become required inputs for execution.
Choose the interaction path
Inspect which question and review tools are available before asking the user anything.
- For several material decisions, prefer Plannotator when the
plannotatorCLI is available. Read PLANNOTATOR.md and use its interview and review adapters. - Otherwise, use the host's structured question or interview tool.
- If no question tool exists, present a short, answerable bundle in chat.
- For one quick decision, use the lightest available question tool instead of opening a full interview.
Never require or install Plannotator. The goal workflow must work without it.
1. Rearticulate the goal
State the intended outcome in two or three sentences. Include who benefits and what changes. If the request is vague, perform only enough repository exploration to ground the restatement.
Ask the user to correct the restatement before continuing. Do not ask them to repeat details already present in the conversation.
Create ai-artifacts/goals/<slug>/ after the outcome and slug are clear.
2. Extract intent
Inspect repository instructions, relevant code, docs, tests, configuration, prior decisions, and similar implementations. Answer factual questions from evidence instead of asking the user.
Separate what you learn into:
- Outcome: the observable result the user wants.
- Audience: who uses or operates it.
- Problem: why the change matters.
- Scope: behavior included in this goal.
- Non-goals: nearby behavior intentionally excluded.
- Constraints: technical, product, security, time, compatibility, or policy limits.
- Decisions: choices only the user can make.
- Assumptions: low-risk defaults accepted provisionally.
- Unknowns: unresolved items that could materially change the work.
What ships with it
1 file 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.
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 · 181 lines · 39 tokens per session scan A d41cc31e8a61
setup-goal is a skill published in the GitHub repository iurysza/android-use (20 stars, last pushed 9d ago), licensed MIT. It adds 39 tokens to every session and 1,321 once invoked, about $0.0002 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 2026-09-15.
Other skills, from other repositories
babysit
Use when a user asks to babysit, monitor, keep checking, keep an eye on, or report when a pull request, CI run, ticket, deployment, or other changing target reaches an outcome.
rubber-duck
Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…
building-agents
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…
agent-eval
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…
browser-qa
Testing web apps through a real browser: reconnaissance before acting, selector discovery, state capture, console errors and screenshot evidence. Use on a web surface end to end, or to reproduce a front-end bug.
code-review
Reviewing code for defects: diff-first reading, severity classification, evidence over inference, finding caps, and terminal verdicts. Use when reviewing a diff, PR, or patch, or auditing someone else's work.