Andrew Ng just released a 2-hour course on building agentic skills from scratch with Anthropic:
• 00:00 – How to build agent skills with Claude
• 22:32 – Claude pre-built skills for AI agents
• 41:07 – Agentic skills vs tools, MCP, subagents
• 01:06:06 – Skills for long-running agents
This 2-hour watch will replace 10 paid courses on building agents, by Anthropic themselves.
Watch it today, then read how to build self-improving agentic systems in the article below.
GPT-5.6 Sol vs Fable 5.
I put both through my hardest frontend test: a 3D globe dashboard.
Same prompt. Same reference image.
Sol on the left. Fable on the right.
GPT-5.6 Sol is a major leap from 5.5.
Fable 5 still wins on spacing, balance, and first-pass polish.
For me, Sol comes close at half the cost.
Anthropic Core Agents team:
"everyone's scripting agents step by step
we spent months building complex workflows - all fragile, all wrong"
here's how Anthropic builds agents now:
step 1 → stop scripting steps. give the agent the goal - it'll find the path itself
step 2 → run two agents against each other: one proposes, one breaks it - best answer wins
step 3 → agent stuck? it calls a smarter model to unblock
step 4 → every rule you delete makes the agent smarter, not dumber
the smarter the model, the thinner the harness. stop over-engineering
watch now, new workshop from the Claude Product team on building agents ↓
VERY COOL!!
Thanks @jordandotbuilds for the tip, I can now test my iOS app on web
I asked Claude Code to set up serve-sim, a web-based iOS simulator that can stream the iOS app my Claude Code on VPS built live to me, because it's on some Mac Mini in the cloud without even a GUI (it's headless) I cannot actually try it on the Mac itself!
Before Claude would make me a page with screenshots but I had no idea how the app felt, now with this it works
This is hosted on the Mac Mini via SSH (it shows localhost but it's a tunnel via SSH to the Mac Mini), bit laggy but nice!
New in Claude Code: /checkup
Run /checkup to:
1. Clean up unused skills/MCPs/plugins and save context
2. Dedup your local CLAUDE.md against the checked in CLAUDE.md
3. Break up root CLAUDE.md into nested CLAUDE.md's + skills
4. Turn off slow hooks
5. Update your Claude Code to the latest version
6. Enable auto mode by default
7. Pre-approve frequently denied read-only commands
.. And a few other goodies.
/checkup confirms with you before making any changes. Enjoy!
this should be a huge update in your model of software engineering: rewrites can be good, cheap and fast
of course most apps are not as testable and verifiable as Bun, but the models will continue to get better at filling those gaps
If you dont know, you can use your Codex subscription inside Claude Code.
That means Fable 5 can call GPT 5.5 + 10 subagents to work together.
This will save you atleast 60% of your Fable 5 token consumption.
You just need to setup once. Here's how:
Step 1: Open Claude Code and install the Codex plugin
/plugin marketplace add openai/codex-plugin-cc
/plugin install codex@openai-codex
/reload-plugins
Step 2: Tell Fable 5 to finish the setup
Paste this prompt:
"Set up Codex inside this Claude Code environment. Use the official OpenAI Codex plugin that was just installed. Run /codex:setup. If Codex CLI is missing, install it. If Codex is installed but not authenticated, ask me to authenticate with my ChatGPT account. After auth is complete, verify that Codex works from inside Claude Code. Then confirm that the codex:codex-rescue sub-agent is available. Do not change any project code during setup."
Step 3: Authentication
Fable 5 will trigger the Codex setup.
You authenticate your ChatGPT/Codex account once.
After that, Codex runs from inside Claude Code using your Codex subscription.
Step 4: Tell Fable 5 how to delegate work
Paste this prompt:
"From now on, use this workflow:
You are the orchestrator.
> Use Fable 5 for planning, repo understanding, architecture decisions, task decomposition, and final review.
> Use codex-rescue as the executor when a task needs heavy implementation, debugging, test fixing, refactoring, or multi-file code edits.
When delegating to Codex, use /codex:rescue.
Prefer GPT 5.5 (xtra high) as the go to Codex model.
Keep Codex tasks focused and specific.
After Codex finishes, inspect the result yourself before accepting it.
Do not blindly trust Codex output."
Pro Tips:
1. Turn this into a skill (i named it Fable-GPT) and call that skill at the start of the session.
2. Use skill + goal to get the heavy tasks done. Goals are best for long horizon tasks.
3. If you're on Codex 20x pro plan, you can use subagents. I use 5-7 agents at one time and never hit 5-hour limit.
4. Context rot is real so clear the conversation after 4 compactions. Use /handoff skill to preserve context.
Claude Code on desktop now has an in-app browser.
Claude can pull up docs, designs, or any other site. It can read, click through, and interact the same way it does with your local dev servers.
It's sandboxed and configurable: you choose whether sessions persist.
On BrowseComp, we tested Claude Managed Agents w/ Fable 5 orchestrator + Sonnet 5 worker sub-agents.
The Fable 5 orchestrator achieves 96% of Fable 5 performance at 46% of the price.
Token-heavy research is delegated to Sonnet 5.
See our cookbook:
https://t.co/zDGXCK79N3