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 reply-brogit 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/reply-bro)<a href="https://agentmods.dev/skills/iurysza/android-use/reply-bro"><img src="https://agentmods.dev/badge/skills/iurysza/android-use/reply-bro/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/reply-bro"><img src="https://agentmods.dev/badge/skills/iurysza/android-use/reply-bro.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 | $0.00046 | $0.00425 |
| Opus 5.5 | $0.00018 | $0.00170 |
| Sonnet 5.5 | $0.00009 | $0.00085 |
| Haiku 4.5 | $0.00005 | $0.00042 |
Grade A, and why
reply-bro 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.
What it actually says
Reply bro
Turn the supplied reply into a short message that sounds like an engineer typed it quickly in Slack or a PR discussion.
Rules
- Output only the rewritten message. Do not add headings, bullets, or commentary.
- Use 3 or 4 short sentences.
- Start with a positive acknowledgement, such as “Good shout.”
- Keep only the main technical concern. Cut specification detail, repeated reasoning, and formal language.
- Raise the concern as a question, not a rejection. Use natural phrasing such as “Would this fit here though?” or “It looks like…”.
- End by asking whether a simpler alternative would work, for example: “Maybe keeping
existing.attributeis simpler?” - Use plain, casual language. Avoid sounding certain, argumentative, or like a formal technical review.
Check before replying
Confirm the result starts positively, has 3–4 sentences, makes the concern a question, and ends with the simpler alternative.
Example
Source:
That page is why we should not use
hw.memory.size. It is a hardware metric for a DIMM in a monitored host, not a span attribute for phone RAM. The specification defines it as an UpDownCounter representing the size of a memory module and requires hardware-specific identity attributes. A mobile launch span has none of that. Additionally, calculating the RAM bucket in Honeycomb would require sending and storing the raw RAM value. We should keepsumup.device.ram_bucket.
Reply:
Good shout. Would
hw.memory.sizefit here though? It looks like a host memory-module metric, while we need total RAM on a mobile launch span. Calculating it in Honeycomb would also mean sending raw RAM. Maybe keepingsumup.device.ram_bucketis simpler?
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 · 35 lines · 46 tokens per session scan A f9370986fff8
reply-bro is a skill published in the GitHub repository iurysza/android-use (21 stars, last pushed 16d ago), licensed MIT. It adds 46 tokens to every session and 425 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.