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 agentmods add skills/evolplus/talos/react-native-performancenpx skills add evolplus/talos --skill react-native-performancegit clone --depth 1 https://github.com/evolplus/talosWhat 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 | $0.00050 | $0.00760 |
| Opus 5 | $0.00025 | $0.00380 |
| Sonnet 5 | $0.00010 | $0.00152 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
react-native-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 2d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
React Native Performance
When to use
Use this when a React Native/Expo task touches performance-sensitive UI: long lists, heavy images, charts, animations, frequent updates, navigation startup, slow gestures, memory pressure, or native bridge traffic. Load it alongside react-native-implementation.
Inputs and outputs
- Inputs: affected RN screens/components, existing profiling or QA evidence, device/emulator target, design manifest, data size assumptions, current state/image/list/animation libraries.
- Outputs: targeted performance changes with preserved behavior, measurable before/after evidence when feasible, and tests/checks that prove no manifest or accessibility regression.
Procedure
- Define the performance surface:
- name the slow path, expected data volume, device class, platform, and success criterion;
- inspect existing profiler/log evidence before changing code when available.
- Reduce render churn:
- avoid recreating expensive arrays, callbacks, and
renderItemclosures for large lists; - memoize only when it removes measured or obvious repeated work;
- keep derived data in selectors/memoized helpers, not inline render logic;
- split components around independently changing state.
- avoid recreating expensive arrays, callbacks, and
- Tune lists:
- use
FlatList,SectionList, or the project's virtualized list library for dynamic collections; - provide stable keys,
getItemLayoutwhen row height is fixed, bounded initial render counts, and explicit empty/loading states; - avoid nested scroll views around virtualized lists unless the project pattern proves it safe.
- use
- Handle images and assets:
- serve appropriately sized assets;
- use the project's image cache/loader;
- avoid decoding oversized local images inside frequently mounted cells;
- prefetch only high-confidence next-step assets.
- Keep animation and gestures off the busy JS path when the project stack supports it:
- prefer Reanimated/native-driver/project animation primitives for continuous motion;
- avoid state updates on every frame from JS;
- respect reduced-motion settings.
- Watch bridge/native overhead:
- batch native calls and analytics events where the project already has a batching layer;
- avoid polling native modules from render/effect loops;
- keep platform adapters small and testable.
- Verify:
- run the narrowest repeatable check: profiler capture, release/profile build smoke test, list scroll test, animation interaction test, or memory check;
- record unmeasured performance assumptions in the task notes instead of presenting them as proof.
What ships with it
1 file 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.
- 2d ago First seen · 64 lines · 50 tokens per session scan A 99c1933b3ae4
react-native-performance is a skill published in the GitHub repository evolplus/talos (8 stars, last pushed 28d ago), licensed Apache-2.0. It adds 50 tokens to every session and 760 once invoked, about $0.0003 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
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
seedance-vocab-ja
This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.