Home
Notes
📚 Prompt Patterns
Archive
About
Home
Notes
📚 Prompt Patterns
Archive
About
Subscribe
Sign in
Latest
Top
Discussions
20+ Agent Skills, Repos, and Marketplaces Worth Bookmarking
An opinionated shelf of agent skills, collections, marketplaces, and adjacent tools worth installing, bookmarking, or using as templates for your own.
Jun 14
14
2
From Test-Driven to Loop-Driven Development
The evolution of AI coding from tests and prompts to agents, harnesses, and supervised loops.
Jun 11
18
1
4
Stop Babysitting Your Coding Agent. Give It Backpressure.
Backpressure is feedback that reaches the agent before the agent reaches the human.
Jun 6
16
2
May 2026
The Missing Quality Layer for AI Coding Agents
As coding agents get better at writing code, the next challenge is proving the code is safe to merge.
May 29
18
2
How Teams Scale Claude Code Across Monorepos and Large Codebases
Thirteen patterns for making Claude Code work across monorepos, shared conventions, generated files, and organizational rollout.
May 24
20
1
2
9 Principles That Separate Useful Skills from Markdown Essays
A practical framework for deciding when a skill should fire, how it should run, and how it should survive over time.
May 10
53
2
4
Distribution vs Escalation: When to Use Subagents or Advisors
Two patterns for scaling a Claude agent. Both add a second model to the loop, each with different trade offs. Here’s when to reach for each, and when to…
May 2
13
2
3
April 2026
12 MCP Patterns Behind Production Agents
A practical breakdown of the recurring design patterns behind real-world agent and mcp integrations.
Apr 25
20
3
Skill Authoring Patterns from Anthropic’s Best Practices
A practical breakdown of the recurring design patterns behind effective Claude Skills, from activation metadata to executable helpers.
Apr 19
75
6
12 Agentic Harness Patterns from Claude Code
The leaked source revealed how a production coding agent is actually assembled. Here are the design patterns behind it.
Apr 5
339
4
39
Practical Lessons From the Claude Code Leak
The most useful part of the Claude Code leak was not the drama. It was the architecture.
Apr 3
27
3
March 2026
State of AI-Assisted Coding in 2026
AI coding is converging on three domains: planning, code generation, and confidence building
Mar 29
10
2
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
