Code With the Grain: The Skill That Stops AI Coding Agents Bloating Your Repo
AI coding agents add. They write a second helper next to the first, a new layer beside the existing one, a wrapper around a function that already did the job. T...
9 min read
AI Agents
Claude Code
+3
The Architect Pattern: Let the Expensive Model Decide and a Cheaper One Type
I stopped letting my most expensive model write code. It reads, decides, briefs a cheaper worker and reviews the diff. Five weeks and 49 sessions of transcripts...
14 min read
AI Agents
Token Optimization
+3
What an AI Agent's Context Window Actually Costs You
A context window is a running meter, not storage. What fills it, why a long agent session costs far more than the work it does, how prompt caching changes the a...
8 min read
AI Agents
Context Engineering
+3
One Setting Cut My AI Coding Agent's Token Use by 17%: Here Are the Numbers
I capped how large my AI coding agent's context is allowed to grow, then measured the result across 1,117 session transcripts. Same number of prompts, 17% fewer...
8 min read
AI Agents
Token Optimization
+3
The Architect Doesn't Lay Bricks: Splitting AI Coding Between Expensive and Cheap Models
We banned our most expensive AI model from writing code. Token receipts from 606 real sessions show how the architect–implementer split cuts AI coding costs.
13 min read
AI Agents
AI Development
+3
Subtract, Align, Prove: Three Skills That Keep AI Agents From Spaghettifying Your Repo
Left alone, AI coding agents add duplication, drift, and unproven fixes. Three composable skills removed 821 lines across five Tier-3 PRs while shipping feature...
11 min read
AI Agents
Developer Productivity
+3
Developing a Full-Fledged Enterprise Application with the harnext Coding Agent
Ten months, 1,409 merged PRs, three forensic audits: how a staged agent pipeline took one enterprise codebase from 12% to 92% agent-involved development — with ...
7 min read
AI Agents
Agentic Workflows
+3
What a Context Engine Actually Buys You: We Ran 22 AI Code Reviewers Five Different Ways
Same pull request, same prompt, same model — only the context loading differed. A context-engine digest plus one policy-file read beat reading the docs on both ...
9 min read
AI Agents
Context Engineering
+3