K:Supernick retweeted
this is f*cking gold for Fable 5.2
these 20 GitHub repos will turn your Fable 5.2 into a full Design studio.
skills. systems. UI. canvas. assets. QA.
01 ui-ux-pro-max → 80 UI styles, palettes and font pairings.
github.com/nextlevelbuilder/…
02 /canvas-design → Anthropic's skill for posters and art as PNG and PDF.
github.com/anthropics/skills…
03 /pptx → Real slide decks. Anthropic official.
github.com/anthropics/skills…
04 /theme-factory → 10 ready themes for slides, docs and landing pages.
github.com/anthropics/skills…
05 stitch-skills → Google Labs skills that turn a prompt into UI screens.
github.com/google-labs-code/…
06 /frontend-design → Anthropic's skill for UI that doesn't look AI-generated.
github.com/anthropics/skills…
07 DESIGN.md → Google's format that describes your visual identity to agents.
github.com/google-labs-code/…
08 Astryx → Meta's open-source design system, built for agents.
github.com/meta/astryx
09 shadcn/ui → Components you own as code.
github.com/shadcn-ui/ui
10 Tailwind CSS → Utility-first styling.
github.com/tailwindlabs/tail…
11 Magic UI → Animated components to copy and paste.
github.com/magicuidesign/mag…
12 Magic MCP → Like v0, inside Claude Code.
github.com/21st-dev/magic-mc…
13 Figma Context MCP → Figma layouts straight to your agent.
github.com/GLips/Figma-Conte…
14 Penpot → Open-source Figma alternative with an official MCP.
github.com/penpot/penpot
15 Excalidraw → Hand-drawn diagrams and wireframes.
github.com/excalidraw/excali…
16 tldraw → An infinite canvas SDK.
github.com/tldraw/tldraw
17 Lucide → Clean, consistent open-source icons.
github.com/lucide-icons/luci…
18 Leonardo → Adobe's palettes built from a contrast ratio.
github.com/adobe/leonardo
19 rembg → Background removal in one line.
github.com/danielgatis/rembg
20 agent-browser → The agent opens the page and checks the design itself.
github.com/vercel-labs/agent…
Skill → system → UI → canvas → ship.
Bookmark this then go design something people remember.
HOLY F*CK, a full video editing room for Claude Code in 14 repos
14 skills and tools that cut your video while you're away from the laptop, 160K+ stars combined, every link checked
Watch. Cut. Caption. Grade. Render.
01 video-use → raw clips in, final.mp4 out
github.com/browser-use/video…
02 ffmpeg-skill → 42 local FFmpeg tools, no cloud
github.com/kajisho5/ffmpeg-s…
03 Claude Eyes → agents that watch your footage
github.com/moritzkremb/claud…
04 WhisperX → word-level timestamps and speakers
github.com/m-bain/whisperX
05 Silero VAD → finds where speech starts and stops
github.com/snakers4/silero-v…
06 auto-editor → cuts every silent gap automatically
github.com/WyattBlue/auto-ed…
07 PySceneDetect → finds scene cuts and transitions
github.com/Breakthrough/PySc…
08 editly → a whole edit in one spec file
github.com/mifi/editly
09 OpenTimelineIO → open interchange for timelines
github.com/AcademySoftwareFo…
10 DaVinci Resolve MCP → Claude controls Resolve Studio
github.com/samuelgursky/davi…
11 Uncut → macOS editor with Claude Code inside
github.com/blazejkustra/uncu…
12 Yap Studio → agent cuts dead air, adds B-roll
github.com/cathrynlavery/yap…
13 Take One → one line in, a launch video out
github.com/talsiach/take-one
14 FFmpeg → the engine under almost every tool here
github.com/FFmpeg/FFmpeg
Footage → silence cut → word timing → scene cuts → grade → render
Bookmark this. How Opus 5.5 turned motion design into a writing skill, layer by layer, in the article below ↓
K:Supernick retweeted
Anthropic acaba de lanzar el mejor truco para Claude Code:
Fable 5.2 piensa → Sonnet 5.5 construye → Opus 5.5 revisa → Haiku 5.5 coordina un enjambre de agentes
1 minuto + el comando /advisor = 3,4 veces más barato
Así se configura:
Primero, entiende cómo funciona:
• Esta configuración sirve para cualquier tarea: Sonnet 5.5 construye, Opus 5.5 revisa al momento y un enjambre de agentes Haiku 5.5 busca información e investiga, con un coste por token 80 veces menor que Fable
• Fable 5.2 nunca escribe código. Solo se activa en 3 momentos: antes de cerrar un plan, cuando un error se repite y antes de dar el trabajo por terminado
• Solo pagas el precio de Fable para tomar decisiones. Los modelos baratos hacen todo lo demás
Así puedes montarlo:
1 → Ejecuta claude update. Fable 5.2 necesita Claude Code v2.1.321 o superior
2 → Pega el prompt de abajo en Claude Code. Primero leerá la documentación oficial de Anthropic sobre el modo advisor
3 → Configura el equipo a nivel de usuario para que funcione en todos tus proyectos: Sonnet como modelo principal, Fable como asesor, Haiku para los subagentes y Opus como revisor
4 → Hace una copia de seguridad de tu configuración y te muestra cada cambio antes de aplicarlo, comparando el antes y el después
5 → Lo que nadie te cuenta: hay una línea que le dice a Sonnet 5.5 CUÁNDO consultar a Fable. Sin ella, el asesor no se activó ni una sola vez en los 198 casos de la prueba de Anthropic
El prompt completo y la documentación oficial de Anthropic sobre el modo advisor te lo dejo abajo
Después, lee el artículo para exprimir Fable 5.2 al máximo:
K:Supernick retweeted
We've given all Pro, Max, Ultra, and Team users one free full reset, across all models and limits. Use it anytime before December 10 at 2:00PM PT.
We recently fixed a few small issues that used more limits than intended, and the Fable resets didn't do much for those of you who'd already hit your weekly limits for all models. While these issues didn't affect everyone, we want to make up for the trouble.
You'll find it in Settings > Usage, or at clau.de/reset.
K:Supernick retweeted
Confirmed: ChatGPT and Codex will share one usage limit from December.
OpenAI's help page, updated today:
- Plus, Pro and Business get one allowance across ChatGPT and Codex
- Usage is measured in tokens, so bigger models and harder tasks burn more
- Instant chat doesn't count against it
- Combined remaining usage and reset times will show in Settings > Usage
- Hit the cap and you wait, upgrade, or buy credits
OpenAI says most users won't hit resets more often than now. If you run long Codex sessions and lean on ChatGPT too, plan for both drawing from the same pool.
Fair ask to OpenAI: publish the token allowance per plan before December so people can check the maths.
help.openai.com/en/articles/…
THIS IS A PURE F*CKING GOLDMINE
Anthropic just shared one of the best tricks for Claude Code.
The idea: put a guard between the expensive model and the grunt work. Opus 5.5 asks to read 48 files, the guard says no and hands it to the swarm.
Same session, two ways: all-Opus would have burned $3.41. With the swarm it came out at $0.59. That is $2.82 kept, 83% never burned.
You just launch Claude Code like this:
claude --model opus # agents: model: haiku
here's the split:
→ Opus 5.5 plans and decides, 97k tokens for $0.52
→ every read, grep and test request gets rerouted to Haiku 5.5
→ 12 Haiku agents map files, find call sites and run tests in parallel
→ Opus comes back to 3 summaries at 6k tokens, never raw files
the part everyone gets wrong: they let the expensive model do the reading.
Opus asked for 48 files in one go. the guard caught it, sent it to the swarm, and that single reroute kept $0.27 on its own.
Haiku is 40x cheaper per token. mapping 32 files, finding 25 call sites, running 212 tests, all of it came in under a cent per lane.
one catch worth knowing: past 100k of context Haiku jumps to 5x its own price, so every agent is kept small on purpose.
grunt work never runs on Opus. that is the whole rule.
Opus thinks. Haiku reads. The guard decides which is which.
JEV engineering is the same move one layer down: 1,420 forks this run - grunt or think, which agent, retry or stop - resolved in code at 0.80 sharpness, and only the split ones ever reach Opus
the full tree
> Opus 5.5 runs the main session, plans and reviews only
> a guard sits between the brain and the tools and reroutes grunt work
> 12 Haiku 5.5 agents fan out across read, grep and test, each kept under 100k
> every agent returns a summary, never raw files or logs
> Opus 5.5 reads 3 summaries at 6k tokens and signs off
> JEV resolves 1,420 micro-forks in code and escalates only the split ones
paste the tree and this prompt into Claude Code ↓
"Rebuild my Claude Code setup around this tree:
1. Run the main session on Opus 5.5 for planning, decisions and review only.
2. Add a guard: any read, grep or test request from the main session gets rerouted to a Haiku 5.5 agent instead.
3. Fan the grunt work across parallel lanes, each agent kept under 100k of context.
4. Agents return summaries only, raw files and logs never enter the main session.
5. Add one rule to CLAUDE.md: grunt work never runs on Opus, no exceptions.
Route deterministic forks (grunt or think, agent choice, retries) through JEV.
Show me every change as a diff first. No edits until I say go."
↳ code.claude.com/docs/en/mode…
save it, it'll come in handy.
K:Supernick retweeted
llm.runonflux.com is live.
One OpenAI-compatible endpoint. Eight models. Five pools of twenty instances.
Latency-aware routing, sticky sessions, stateless API keys.
Running entirely on Flux nodes. Not on a hyperscaler we rent from.
K:Supernick retweeted
Setiap hari, puluhan aplikasi baru diluncurkan di jaringan FLUX
Server game, hosting situs web, agen AI, penelitian medis, dan lain-lain
Langsung dari GitHub atau menggunakan Docker
Pembayaran dalam mata uang FIAT, meningkatnya adopsi kalangan “bukan penggemar kripto” 🥰
Chaque jour, ce sont des dizaines de nouvelles applications qui sont déployées sur le réseau FLUX
Serveur de jeux vidéos, hébergement de site web, agent IA, recherche médicale, etc
Directement depuis Github ou avec Docker
Le paiement en FIAT est de plus en plus présent et démontre une adoption croissante d'un public "hors crypto" 🥰
K:Supernick retweeted
llm.runonflux.com is live if you missed it. Its one openai compatible endpoint in front of eight models running on flux nodes, five pools of twenty instances each. Requests go to whichever healthy instance is least busy and a conversation sticks to the same instance while its free, so the prompt cache keeps working on long chats. Theres a demo key right on the page, no signup, point any openai or ollama client at it and try. And if you want your own the whole thing is open source as ownllm, MIT, you can deploy it on flux yourself github.com/RunOnFlux/ownllm
K:Supernick retweeted
After careful review and internal discussion, we have made the decision to discontinue support for Kadena (KDA) across all Koala Wallet products and services. This includes the delisting of KDA from the Koala Wallet app, as well as the discontinuation of our Kadena-related platforms such as kdaexplorer.com and kadenaecosystem.com.
Kadena support will remain available until December 31, 2025. After this date, Kadena services and integrations will be fully retired. To maintain uninterrupted access to your Kadena assets, we recommend that all users export their Kadena private key and import it into a wallet that continues to support the network, such as Linx, Ecko Wallet, or other reputable Kadena-compatible wallets.
You can follow this step-by-step guide to export your Kadena private key from Koala Wallet:
support.koalawallet.io/hc/en…
We’re also glad to see a successful, community-run fork of Kadena emerging. If you’re participating in that ecosystem, importing your keys into a supported wallet will ensure you can access those coins as well.
Thank you for your understanding and for being part of the Koala Wallet community. If you have any questions or need assistance during this transition, our support team is here to help.
K:Supernick retweeted
🚨 KDA Fork Update - Coinmetro Supports the Community Chain 🚨
The community has spoken - the Kadena Community Fork has officially become the winning chain! 🎉
Coinmetro is fully aligned with the majority network and has already begun updating its nodes to support the new chain. Our team has been working since this morning on backups and migration, ensuring all systems transition securely and smoothly.
⏳ No ETA yet - node updates take time and precision - but our goal is to finalize the process by end of day (EOD). We’ll keep everyone posted on progress as soon as it’s safe to resume full operations.
In the meantime, we’d like to congratulate the Kadena community on this successful, community-driven outcome - a powerful example of decentralization in action. 💪
We’re also working on securing market-making support to ensure healthy liquidity once trading resumes.
Stay tuned for further updates right here - and if you’re part of the KDA community, join us on Coinmetro to be part of the next chapter of Kadena’s evolution. 🚀
K:Supernick retweeted
🎙️ New @edge_pod
🤷♀️ Understanding The Risky Business of DeFi’s Risk Curators
0:00 - Intro
5:34 - History of kpk
9:38 - What's the job of a risk curator?
13:53 - Permissionless lending markets vs vaults
24:23 - What happened with Stream and xUSD?
34:07 - How do risk curators make money?
38:07 - The role of risk ratings in DeFi
41:34 - Could they run strats in their own markets?
47:43 - Hard-coded oracles vs market price
57:06 - Prioritize safety over higher yields
1:01:26 - kpk’s approach to risk curation
1:05:30 - kpk’s retail-facing DeFi suite
1:07:11 - Closing
🙏 Thanks to @kpk_io Head of Growth @rsousamarques and Head of Risk Curation @deepcryptodive for joining us!
K:Supernick retweeted
Just in: Coinmetro exchange announces support for the community version of Kadena!
They are working on switching over nodes with a hopeful ETA of today!
They will also work to provide MM support!
Huge thanks to @KevinMurcko and @CoinMetro for always supporting the community and $KDA over the years!
K:Supernick retweeted
We are pleased to announce our support for the forthcoming hardfork of the Kadena blockchain, particularly the community edition. This development is poised to maintain and advance $KDA, independent of previous restrictions. We invite the community to unite in support of this fork, set to occur on November 8 at 4:00 AM UTC. The evolution of blockchain technology is increasingly guided by community initiatives. #FreeKadena #KDA #Blockchain
I am pleased to share that the KDA community is announcing a Community Take Over Fork!
The new X account is @communitykda and telegram is t.me/KdaCommunityEdition .
The fork will be in roughly block height 6,335,858.
@zelcore_io @eckoWALLET @FusionX_Flux will all be following the new chain as well as all @RunOnFlux products.
More information to follow. Power to the People!
K:Supernick retweeted
I’m pleased to share that I have been assisting with the new Community Takeover Team (CTO) for @kadena_io.
With that, new and exciting things are coming to $KDA! Over the next several days you will see the team making lots of changes, and building the next V2 of Kadena.
@InFlux_Limited will be helping the team to get on their feet with legal, foundation and support on all platforms. All wallets and FusionExchange will support them moving forward.
Me reason for helping was many things, right now the market sucks, and watching the KDA community get screwed, no thanks, they are our family as well. My commitment to decentralization has never been stronger.
@RunOnFlux is laying the foundational groundwork for depin and perhaps there is a possibility to see KDA in FluxCore as well, true PoUW and usecase for the chain.
Pain is temporary, decentralization is eternal!
Dan
K:Supernick retweeted
Binance will delist FLM, KDA, PERP on 2025-11-12.
More information 👉 binance.com/en/support/annou…








































