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 tech-specgit 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/tech-spec)<a href="https://agentmods.dev/skills/iurysza/android-use/tech-spec"><img src="https://agentmods.dev/badge/skills/iurysza/android-use/tech-spec/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/tech-spec"><img src="https://agentmods.dev/badge/skills/iurysza/android-use/tech-spec.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 | $0.00033 | $0.00882 |
| Opus 5.5 | $0.00013 | $0.00353 |
| Sonnet 5.5 | $0.00007 | $0.00176 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
tech-spec 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Specification
A tech spec is a typed architecture handoff. Types and call stacks define what changes; prose explains why.
This workflow is design-only. Do not implement. Write durable specs to ai-artifacts/specs/YYYY-MM-DD-<topic>.md unless the user or repository explicitly requires another location.
Choose the path
- Convert context: use when conversation, docs, and code already define the problem and constraints.
- Set up the goal first: use the
setup-goalskill when important requirements, boundaries, or acceptance criteria remain unresolved.
Answer repository questions by inspecting the repository. Ask the user only for decisions.
Build the spec
1. Establish current state
Read relevant code, tests, docs, project instructions, domain vocabulary, and architectural decisions. Trace the existing entrypoint-to-effect flow.
Capture the problem, callers, goals, non-goals, constraints, invariants, affected systems, operational concerns, risks, and open questions. Do not invent missing requirements.
2. Compare real alternatives
Offer materially different designs. They should differ in ownership, interfaces, seam placement, call stack, runtime topology, or state model—not merely names.
For each option show:
- domain and application types
- public interfaces
- module and adapter ownership
- entrypoint-to-effect call stack
- failure and cancellation behavior
- persistence and transaction boundaries
- testing seams
- costs and risks
Choose the recommendation only after comparison.
3. Define contracts
Sketch every new or changed boundary in code:
type Input = { /* parsed application values */ };
type Output = { /* caller-visible result */ };
type ExpectedFailure = FailureA | FailureB;
interface Capability {
execute(input: Input): Promise<Result<Output, ExpectedFailure>>;
}
Cover domain values, state variants, request/response shapes, parsers, functions, ports, adapters, records, events, and public APIs as applicable. State what may cross each boundary and what must remain private.
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 · 126 lines · 33 tokens per session scan A 94fc49f31eb8
tech-spec is a skill published in the GitHub repository iurysza/android-use (21 stars, last pushed 16d ago), licensed MIT. It adds 33 tokens to every session and 882 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 2026-09-15.
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.