Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
ClaudeDevs Profile picture
@ClaudeDevs
Jun 9 • 9 tweets • 2 min read • Read on X
Scrolly
Claude Fable 5 is here. New model generation, new way of working.

Here's how to get started in Claude Code and on the Claude Platform: 🧵
In Claude Code, run /model and select Fable from the model picker, or switch directly with:

/model claude-fable-5
In the API, switch the model ID parameter to "claude-fable-5" in both the Messages API and Claude Managed Agents. For some accounts, an admin may need to enable access first.

The /claude-api skill in Claude Code can help you build with Fable on the API. Image
Start at the top of your difficulty range: something harder than you'd assume previous versions of Claude can accomplish.

Pick a backlog item you'd scope at a week, let Fable 5 interview you for the spec, turn on auto mode, and check back in the morning.
You may notice that Fable feels different. Thinking is always on, and responses can take longer.

Effort controls how much it thinks. We recommend high as the default. In our evals, even low/medium often beat previous models at xhigh, so save xhigh for your hardest problems.
Prompting gets simpler. Existing prompts or skills developed for prior models are often too prescriptive for Fable.

We recommend reviewing and potentially updating or removing older instructions or skills if you find default performance to be better.
Feedback loops work the same as with previous models: give Fable the success criteria to check its results against.

This can be /goal in Claude Code or Outcomes in Claude Managed Agents.
With multi-agent orchestration in Claude Managed Agents, you can use Fable to delegate work to dedicated agents using smaller models. Image
Cybersecurity and biosecurity requests may auto-reroute to Opus 4.8 (shown in the UI, billed at Opus prices).

Docs + prompting guide:

platform.claude.com/docs/en/build-…

• • •

Missing some Tweet in this thread? You can try to force a refresh
　

Keep Current with ClaudeDevs

ClaudeDevs Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @ClaudeDevs

ClaudeDevs Profile picture
May 28
New in Claude Code (research preview): dynamic workflows.

Claude writes an orchestration script on the fly, then spins up a large fleet of coordinated subagents in parallel to take on your most complex tasks.

Use the word "workflow" in a prompt to get started. Image
Dynamic workflows are useful for tasks that are too big for a single agent loop, such as service-wide bug hunts, large migrations, or stress-testing a design.

They're powerful and can be expensive, consuming a lot of tokens fast. Start with a scoped task to get a feel for it.
You can also set "/effort ultracode", a new effort level that runs at xhigh and lets Claude decide on its own when a task warrants a dynamic workflow.
Read 6 tweets
ClaudeDevs Profile picture
May 27
We’ve been putting a lot of effort into making Claude Code more responsive & reliable.

Here’s an update on everything we’ve done:
First for our new full-screen renderer (which should get rid of bugs like screen flickering), we’ve made a number of fixes for different environments and terminals.

You can turn it with the command: /tui feedback

We're working on making it the default in Claude Code soon.
We’ve greatly improved the responsiveness of Claude while working. Thinking & tool calls are streamed and we’ve fixed a number of bugs that might have made it look like Claude was hanging while it was just thinking for a long period of time.
Read 9 tweets
ClaudeDevs Profile picture
May 26
We’ve shipped a security-guidance plugin for Claude Code that helps identify and fix vulnerabilities as you’re writing code.

Available for all Claude Code users. Install from the plugin marketplace (/plugins).
It runs via hooks and reviews code on three levels:

- On file edits: looks for risky patterns like commonly misused dangerous libraries
- After model turns: reviews the full diff for harder-to-spot issues
- On commits: reads surrounding code to validate vulnerabilities
We've been using the plugin extensively at Anthropic.

Across our internal rollout and benchmarks, we’ve seen a 30-40% decrease in security-related comments on PRs opened using the plugin.

The plugin serves as a lightweight first pass, catching issues before a full code review
Read 4 tweets
ClaudeDevs Profile picture
May 13
Starting June 15, paid Claude plans can claim a dedicated monthly credit for programmatic usage.

The credit covers usage of:
- Claude Agent SDK
- claude -p
- Claude Code GitHub Actions
- Third-party apps built on the Agent SDK
We've heard your questions about SDK and claude -p usage sharing your subscription rate limits with Claude Code and chat.

Starting June 15, programmatic usage gets its own dedicated budget instead. Your subscription limits don't change, they're now reserved for interactive use.
How it works: Claim the monthly credit once, and programmatic usage will draw from it automatically. When it runs out, you can keep going with usage credits (billed at API rates you turn on/off). If usage credits are turned off, usage pauses until the credit resets.
Read 6 tweets
ClaudeDevs Profile picture
May 8
Last week we shipped 50+ Claude Code reliability fixes. This week it's 60+ more.

Smoother long-running sessions, a more efficient agent loop, auth that works in more environments, and terminal fixes: 🧵
1/ Stability

• claude -p now handles >10MB of piped stdin
• Requests resume cleanly after waking a Mac from sleep
• Memory stays bounded when a stdio MCP server writes non-protocol data to stdout (was growing past 10GB)
• Output now appears reliably after thinking completes
2/ Agent loop

• Sub-agent summaries now hit the prompt cache
• Opt-in 1-hour prompt caching is now honored correctly
• Parallel shell calls keep running if a read-only sibling fails
• 1M-context sessions use their full window before hitting "Prompt is too long"
Read 7 tweets
ClaudeDevs Profile picture
May 6
In Claude Managed Agents, we’ve added multiagent orchestration, an outcomes loop for rubric-driven self-improvement, dreaming for self-learning, & webhooks.
Multi-agent orchestration enables task delegation to specialized sub-agents.

Each sub-agent has its own context window, but they share a container + filesystem to coordinate work.

platform.claude.com/docs/en/manage…
Agents can self-improve using a rubric that describes task completion.

A dedicated grader sub-agent uses the rubric to evaluate any work done and returns feedback for the next iteration.

platform.claude.com/docs/en/manage…
Read 6 tweets

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

Send Email!

:(