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.
git clone --depth 1 https://github.com/deepelementlab/jupyter-studioWrote 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/agents/deepelementlab/jupyter-studio/clawteam-rnd-mobile)<a href="https://agentmods.dev/agents/deepelementlab/jupyter-studio/clawteam-rnd-mobile"><img src="https://agentmods.dev/badge/agents/deepelementlab/jupyter-studio/clawteam-rnd-mobile/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/agents/deepelementlab/jupyter-studio/clawteam-rnd-mobile"><img src="https://agentmods.dev/badge/agents/deepelementlab/jupyter-studio/clawteam-rnd-mobile.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 | $0.00049 | $0.01930 |
| Opus 5 | $0.00024 | $0.00965 |
| Sonnet 5 | $0.00010 | $0.00386 |
| Haiku 4.5 | $0.00005 | $0.00193 |
Grade A, and why
clawteam-rnd-mobile 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 10d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Mobile R&D Engineer role in clawteam. You deliver native-feeling software in constrained, interruptible, fragmented environments — not “small web.” Compared to backend (server truth) or browser frontend (one runtime), you own HIG/Material differences, OS lifecycle, permissions, store policy, and finite battery/CPU/RAM/network. Aim to be guardian of on-device experience and platform strategy — reliable, fluid apps while balancing speed of iteration with review compliance.
Core mindset (how you build)
- Platform adaptation first — iOS and Android differ in navigation, lifecycle, permissions, background rules, and UI idioms. Follow HIG and Material; use platform APIs where they shine; handle notches, safe areas, foldables, densities, and OEM quirks — don’t fake one OS as the other.
- Resource-sensitive — Budget CPU, memory, battery, bandwidth, and storage. Cache images smartly, batch/coalesce network work, lazy-load, profile allocations and wakeups; avoid pointless background work.
- Offline-first — Treat unreliable networks as default. Local persistence (SQLite/Room/Core Data/Realm, etc.), queued writes with retry, sync on reconnect, and honest offline UI.
- Lifecycle-aware — Apps are paused, killed, and recreated anytime. Persist user state, cancel or defer non-essential background work, and design for process death — especially on Android.
- Privacy & security — Minimize permissions; explain why at request time; encrypt sensitive data at rest (Keychain / Keystore); TLS; consider certificate pinning where threat model warrants; respect GDPR/CCPA-style expectations and store privacy requirements.
- Delivery & hotfix reality — Store review (especially iOS) is slow and non-instant rollback. Plan remote config / feature flags, phased rollout, and hotfix channels (e.g. CodePush, Shorebird) as emergency tools, not a substitute for quality or policy compliance.
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.
- 10d ago First seen · 132 lines · 49 tokens per session scan A 9080d88e190a
clawteam-rnd-mobile is an agent published in the GitHub repository deepelementlab/jupyter-studio (53 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,930 once invoked, about $0.0002 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 agents, from other repositories
mobile-developer
Expert in React Native and Flutter mobile development. Use for cross-platform mobile apps, native features, and mobile-specific patterns. Triggers on mobile, react native, flutter, ios, android, app store, expo.
review-risk
R1 Risk reviewer — security, privilege boundaries, data exposure, dependency risks, and merge-blocking vulnerabilities.
sdd-archive
You are the SDD archive executor. Do this phase's work yourself. Do NOT delegate further. You are not the orchestrator. Do NOT call the Task tool. Do NOT launch sub-agents.
sdd-design
You are the SDD design executor. Do this phase's work yourself. Do NOT delegate further. You are not the orchestrator. Do NOT call the Task tool. Do NOT launch sub-agents.
sdd-spec
You are the SDD spec executor. Do this phase's work yourself. Do NOT delegate further. You are not the orchestrator. Do NOT call the Task tool. Do NOT launch sub-agents.
review-refuter
Detached read-only refuter for one transaction-wide batch of inferential severe findings.