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 Kaguara/emerging-market-skills --skill low-end-device-performancegit clone --depth 1 https://github.com/Kaguara/emerging-market-skillsWrote 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/kaguara/emerging-market-skills/low-end-device-performance)<a href="https://agentmods.dev/skills/kaguara/emerging-market-skills/low-end-device-performance"><img src="https://agentmods.dev/badge/skills/kaguara/emerging-market-skills/low-end-device-performance/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/kaguara/emerging-market-skills/low-end-device-performance"><img src="https://agentmods.dev/badge/skills/kaguara/emerging-market-skills/low-end-device-performance.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 | $0.00094 | $0.02164 |
| Opus 5 | $0.00047 | $0.01082 |
| Sonnet 5 | $0.00019 | $0.00433 |
| Haiku 4.5 | $0.00009 | $0.00216 |
Grade A, and why
low-end-device-performance 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 12d 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Low-end device performance
The constraint
The reference device has 1–2GB of RAM shared with the operating system, a CPU roughly a quarter as fast as the phone in your pocket, storage that is almost full, and a four-year-old battery holding perhaps 60% of its original charge. It is running a browser with eleven tabs and three chat apps that all hold wake locks. Your process is a candidate for termination from the moment it is backgrounded.
Performance work here is not about being fast. It is about surviving: not being killed, not running out of memory, not freezing the one thread that handles touch.
Hard rules
| ID | Rule | Severity |
|---|---|---|
| PERF-001 | Name a reference device at tier C and make it the definition of "works". | critical |
| PERF-002 | Assume the process will be killed at any moment and restore state on return. | critical |
| PERF-003 | Bound every in-memory cache, especially image caches. | critical |
| PERF-004 | Keep long tasks off the main thread; never block input for more than 200ms. | warning |
| PERF-005 | Recycle or virtualise any list that can exceed one screen. | warning |
| PERF-006 | Precompute on the server what the device would otherwise compute. | warning |
| PERF-007 | Cap background work, wake locks, and polling. | warning |
| PERF-008 | Animate only compositor-friendly properties, and honour reduced motion. | advisory |
| PERF-009 | Give any on-device inference or heavy computation a server or static fallback. | advisory |
Full detection criteria and remedies in rules.yml.
Judgment
Your test device is the problem. Every other rule here follows from PERF-001. A team whose acceptance criteria run on flagship hardware will ship something that works, by their own honest measurement, and is unusable for the people they built it for. The fix is unglamorous and cheap: buy the entry-level device, put it on the desk, and make it the gate. No profiling technique substitutes for the moment someone feels the app stutter in their own hand.
What ships with it
2 files 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.
- 12d ago First seen · 204 lines · 94 tokens per session scan A c015fe0f8fd5
low-end-device-performance is a skill published in the GitHub repository Kaguara/emerging-market-skills (7 stars, last pushed 17d ago), licensed MIT. It adds 94 tokens to every session and 2,164 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
add-signal
Add Signal channel integration via signal-cli device-link. Native adapter — no Chat SDK bridge.
react-native-expert
Builds, optimizes, and debugs cross-platform mobile applications with React Native and Expo. Implements navigation hierarchies (tabs, stacks, drawers), configures native modules, optimizes FlatList rendering with memo and useCallback, and handles platform-specific code for iOS and Android. Use when building a React…
kotlin-specialist
Provides idiomatic Kotlin implementation patterns including coroutine concurrency, Flow stream handling, multiplatform architecture, Compose UI construction, Ktor server setup, and type-safe DSL design. Use when building Kotlin applications requiring coroutines, multiplatform development, or Android with Compose.…
offensive-mobile
Mobile (Android + iOS) application penetration testing methodology. Covers static analysis (apktool/jadx for Android, class-dump/Hopper/IDA for iOS), dynamic instrumentation with Frida and Objection, SSL pinning bypass strategies, root/jailbreak detection bypass, deep-link / URL-scheme abuse, exported component…
Mobile Application Security
Android and iOS application security testing — static and dynamic analysis, APK/IPA inspection, OWASP MASVS/MASTG verification, secure-storage and transport review, and mobile malware triage for authorized assessments.
app-store-optimization
Improves visibility and conversion in the App Store and Google Play — metadata, keywords, screenshots, ratings, and the listing experience that turns an impression into an install. Use this to audit or optimize an app listing, plan a launch listing, diagnose poor install conversion, or improve store search visibility.