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 tool-installgit 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/tool-install)<a href="https://agentmods.dev/skills/iurysza/android-use/tool-install"><img src="https://agentmods.dev/badge/skills/iurysza/android-use/tool-install/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/tool-install"><img src="https://agentmods.dev/badge/skills/iurysza/android-use/tool-install.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 | $0.00034 | $0.01974 |
| Opus 5.5 | $0.00014 | $0.00790 |
| Sonnet 5.5 | $0.00007 | $0.00395 |
| Haiku 4.5 | $0.00003 | $0.00197 |
Grade C, and why
tool-install scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
10. **If the install involves `curl | bash`**, flag it as high-risk and recommend Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
10. **If the install involves `curl | bash`**, flag it as high-risk and recommend How it starts
The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tool Install Planner
Purpose
Turn an "install this" or "update this" request into a fully researched, user-approved execution plan. The agent must never mutate the system without explicit sign-off.
+-----------------+ +------------------+ +------------------+
| You paste link |---->| I research tool |---->| I inspect your |
| or say "install| | + env impact | | current system |
| X" | | | | |
+-----------------+ +------------------+ +------------------+
|
+---------------------------+
v
+------------------+
| I generate plan |
| + briefing |
| + decisions |
| + rollback |
+------------------+
|
v
+------------------+
| You approve |
| (or revise) |
+------------------+
|
v
+------------------+
| I execute |
| + verify |
+------------------+
Workflow
1. Ingest the Link
Fetch the provided URL with fetch_content or web_search to understand:
- What the tool does (1-2 sentences)
- Who uses it: end users directly, developers, automation/orchestration, or AI agents
- Official installation methods (Homebrew, npm, pip, cargo, manual, etc.)
- System requirements and dependencies
- Default install paths and state mutations
- Any post-install setup (config files, env vars, services, login items)
If the user asked to update an already-installed tool, also research:
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 · 255 lines · 34 tokens per session scan C 985e1e3c5d8c
tool-install is a skill published in the GitHub repository iurysza/android-use (21 stars, last pushed 16d ago), licensed MIT. It adds 34 tokens to every session and 1,974 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). 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.