AI Development

Your CLAUDE.md File Is Too Long: The Context Diet That Cut Mine 87%
AI DevelopmentClaude Code

Your CLAUDE.md File Is Too Long: The Context Diet That Cut Mine 87%

Anthropic removed ~80% of Claude Code's system prompt for Claude 5, and the internet decided that means delete your CLAUDE.md. Don't. Here's the four-bucket diet that took mine from 1,204 lines to 151 without losing a single incident-earned warning.

·
11 min
Read more
Claude Opus 5: Fable 5 intelligence at half the price, with a dial for how hard it thinks
AI Development

Claude Opus 5: Fable 5 intelligence at half the price, with a dial for how hard it thinks

Anthropic shipped Claude Opus 5 on July 24 at exactly Opus 4.8's price, landing within 0.5% of Fable 5 on coding for half the cost. A builder's read on the effort dial, the two breaking API changes, and the prompting habit you now need to delete.

·
13 min
Read more
Claude Code 2.1.216: everything that changed since 2.1.186
AI Development

Claude Code 2.1.216: everything that changed since 2.1.186

25 Claude Code releases shipped in the four weeks between 2.1.186 and 2.1.216. Claude Sonnet 5 launched as the Free and Pro default, subagents moved to the background by default, and the permission system got renamed, extended, and audited.

·
15 min
Read more
Claude Fable 5 lasted three days: why the US government pulled Anthropic's most powerful model
AI Development

Claude Fable 5 lasted three days: why the US government pulled Anthropic's most powerful model

Anthropic's first public Mythos-class model launched June 9, then a US export-control order pulled it offline three days later. A clear look at what Claude Fable 5 does, what it costs vs Opus 4.8, why it was suspended, and what comes next.

·
14 min
Read more
How to install Open Design with Claude Code in 10 minutes
AI Development

How to install Open Design with Claude Code in 10 minutes

Step-by-step Open Design setup driven by Claude Code. Node 24, Corepack, pnpm, the daemon, first generation, plus troubleshooting for the #1 install issue: PATH-based CLI detection failures.

·
9 min
Read more
Claude Opus 4.8 and dynamic workflows: what actually shipped
AIAI Agents

Claude Opus 4.8 and dynamic workflows: what actually shipped

Claude Opus 4.8 brings dynamic workflows to Claude Code and a model that flags its own mistakes. What actually changed, the latest Claude Code version, and what it means for n8n users.

·
12 min
Read more
Claude Code's /code-review vs /ce-code-review: when each one wins
AI AgentsAI Automation

Claude Code's /code-review vs /ce-code-review: when each one wins

Claude Code ships /code-review and /simplify natively. The compound-engineering plugin ships /ce-code-review and /ce-simplify-code on top. They look like duplicates – they aren't. Here's a side-by-side, the quick-review short-circuit you probably missed, and a decision matrix for which to use when.

·
10 min
Read more
Open Design, 4 weeks in: should an SMB owner touch it yet?
AI AutomationAI Agents

Open Design, 4 weeks in: should an SMB owner touch it yet?

Open Design shipped April 28 with 19 skills and 71 design systems. Four weeks later it's at 132 skills, 150 design systems, 8 stable releases, 52K stars, and now generates video. Here's the SMB go/no-go.

·
8 min
Read more
The 2 prerequisites for Claude Code (you'll regret skipping)
AIAI Agents

The 2 prerequisites for Claude Code (you'll regret skipping)

Before you install Claude Code, you need source control (GitHub or similar) and issue tracking (Linear or similar). Here's what each one does, why both matter, and the 10-minute setup to get both running.

·
16 min
Read more
A beginner's guide to source control with GitHub
Best PracticesDeveloper Tools

A beginner's guide to source control with GitHub

GitHub for beginners – what source control is, the 5 commands that do 90% of the work, branching, pull requests, and the conventions worth stealing from production AGENTS.md files.

·
15 min
Read more
Claude Code 2.1.141: the stabilization pass after 2.1.139's feature wave
AIAI Agents

Claude Code 2.1.141: the stabilization pass after 2.1.139's feature wave

Claude Code 2.1.141 ships ~60 fixes plus four real adds: terminalSequence hooks, ANTHROPIC_WORKSPACE_ID, claude agents --cwd, and Rewind's Summarize up to here. The polish wave on 2.1.139's feature drop.

·
14 min
Read more
How I shipped a 3-week-old design handoff in 18 minutes with Claude Code
AIAI Agents

How I shipped a 3-week-old design handoff in 18 minutes with Claude Code

Claude Code has 4 execution modes (default, accept-edits, plan, auto). Most people use one. Here's how I used all four to ship a design handoff to a live landing page in 18 minutes.

·
11 min
Read more
Anthropic just doubled Claude Code's rate limits – and signed for every GPU in SpaceX's Colossus 1 data center to back it up
AIAI Agents

Anthropic just doubled Claude Code's rate limits – and signed for every GPU in SpaceX's Colossus 1 data center to back it up

Anthropic doubled Claude Code's 5-hour rate limits, removed peak-hours throttling, and signed for SpaceX's Colossus 1 data center – 220,000 NVIDIA GPUs, 300+ MW, online in one month.

·
8 min
Read more
Claude Code 2.1.131: the silent 1-hour prompt cache bug, plus 64 changes since 2.1.126
AIAI Agents

Claude Code 2.1.131: the silent 1-hour prompt cache bug, plus 64 changes since 2.1.126

Claude Code 2.1.131 ships today. The buried headline is 2.1.129's silent 1-hour prompt cache TTL downgrading to 5 minutes – plus 64 changes since 2.1.126.

·
13 min
Read more
Claude Code 2.1.126: OAuth that works over SSH, sessions that survive Mac sleep, and a managed-settings security fix
AI Development

Claude Code 2.1.126: OAuth that works over SSH, sessions that survive Mac sleep, and a managed-settings security fix

Claude Code 2.1.126 lands 33 fixes. OAuth login finally works over SSH, WSL2, and containers. Sessions survive Mac sleep. claude project purge ships. Plus a managed-sandbox enforcement bug fixed.

·
12 min
Read more
Compound Engineering for Claude Code + AGENTS.md
AIAI Agents

Compound Engineering for Claude Code + AGENTS.md

I split my dev process from CLAUDE.md into AGENTS.md and let the Compound Engineering plugin run it. Here's the full pipeline, tier rules, and AGENTS.md template anchoring every PR.

·
15 min
Read more
Claude Design vs Open Design: should you buy a design tool, or teach your CLI?
AIAI Agents

Claude Design vs Open Design: should you buy a design tool, or teach your CLI?

Anthropic shipped Claude Design April 17. Open Design shipped 11 days later as the OSS clone with 71 design systems and BYOK on any CLI. Honest comparison + decision framework.

·
14 min
Read more
Claude Code 2.1.121: Opus 4.7 finally uses its full 1M window
AIAI Agents

Claude Code 2.1.121: Opus 4.7 finally uses its full 1M window

A quiet bug had Opus 4.7 autocompacting at 200K instead of 1M. 2.1.117 fixed it. Five releases, four memory leaks, and 150+ other changes since 2.1.116.

·
7 min
Read more
The one Claude Code trick that cuts context by 64%
AI DevelopmentVibe Coding

The one Claude Code trick that cuts context by 64%

Your Claude Code 1M context window isn't the win. The @file:L10-L50 trick is. Here's how line ranges cut my token use by 64% on a real refactor.

·
8 min
Read more
Claude Code 2.1.116: /resume is 67% faster and the binary went native
AI DevelopmentAI

Claude Code 2.1.116: /resume is 67% faster and the binary went native

Since Opus 4.7, Claude Code shipped four releases – a native binary, a 67% /resume speedup, hardened sandboxing, and 60+ other changes. Here's the recap.

·
9 min
Read more
Claude Opus 4.7 and Claude Code 2.1.112: what actually changed
AI DevelopmentVibe Coding

Claude Opus 4.7 and Claude Code 2.1.112: what actually changed

Claude Opus 4.7 hits 87.6% on SWE-bench Verified with a new xhigh effort level. Here's what's in Claude Code 2.1.112 and the past two weeks of releases.

·
10 min
Read more
Claude Code routines: automate your dev workflow without leaving your laptop open
AI DevelopmentAI

Claude Code routines: automate your dev workflow without leaving your laptop open

Claude Code routines run on Anthropic's cloud infrastructure. Set up scheduled tasks, API triggers, and GitHub event handlers that work while your laptop is closed.

·
9 min
Read more
Free discovery call

Ready to put AI to work?

Book a free discovery call and we'll tell you what we'd automate first – and what we wouldn't touch yet.

30 minutes. No pitch. You keep the plan.

Prefer to build it yourself? Try Flow free