Blog

Systems, patterns, and lessons from building with Claude Code.

Claude Code Too Verbose? Why Your Rules Stop Working [2026]

Claude Code ignoring your style rules is rarely the wording. Check it loaded with /context, then size, structure, specificity and conflicts.

2026-08-15|13 min

claude-codeclaude-mdoutput-stylesworkflow

Run Parallel Claude Code Sessions From One Terminal [2026]

Run parallel Claude Code sessions from the one you are already in. Three commands, no tmux, and the state field that lagged finished work by six seconds.

2026-08-15|20 min

claude-codeorchestrationagentsbackground-agents

Claude Code Skills vs Plugins vs MCP vs Subagents [2026]

Four Claude Code extension points, one decision rule. What a skill, a plugin, an MCP server and a subagent each actually are, and which one you need.

2026-08-15|10 min

claude-codeskillspluginsmcpsubagents

Claude Code Got Worse Over Time? Diagnose It by Symptom

Claude Code degrades in six recognisable ways after a few weeks. Start from the symptom you have, confirm it in one command, then fix the right thing.

2026-07-31|9 min

claude-codecontext-managementmemorydelegationhooks

Claude Code Code Review Needs a Non-Claude Model [2026]

A Claude Code code review shares your priors. I sent 4 designs to Fugu and grok-build with one instruction, attack this. All 4 died before any code.

2026-07-26|5 min

claude-codecode-reviewmulti-agentdecision-makingnegative-result

My Claude Code Hooks Fired 574 Times, Blocked Zero [2026]

Claude Code hooks that log are not Claude Code hooks that enforce. Mine watched 574 turns for unbacked completion claims and blocked nothing. Here is why.

2026-07-26|5 min

claude-codeclaude-code-hooksobservabilitynegative-resultmeasurement

Your CLAUDE.md Rules Have an Expiry Date [2026]

The most-copied Claude Code CLAUDE.md rules tell you to instruct verification. Anthropic's own Opus 5 guide now says delete it. I measured the gap.

2026-07-26|5 min

claude-codeclaude-mdprompt-engineeringnegative-resultopus-5

The Anatomy of My Claude Code System [2026]

A Claude Code system has a mind, reflexes, memory, and wiring, all self-healing. Here is the full anatomy: 600+ parts and 3 failures it caught itself.

2026-07-19|7 min

claude-codesystem-architectureself-improvingknowledge-graphopen-source

How to Build a Claude Code Plugin: Real Example [2026]

Build a Claude Code plugin from scratch: the plugin.json manifest, bundling commands, hooks, agents and skills, plus how to install it. Real repo example.

2026-06-15|11 min

claude-codeclaude-code-pluginpluginsevolving-liteopen-source

How I Mapped My Self-Improving Claude Code System [2026]

A self-improving Claude Code system scores its decisions and rewrites its own routing. Here is the verified map of the loop and what ships open source.

2026-06-09|6 min

claude-codeself-improvingmulti-agentevolving-liteopen-source

Autonomous Claude Code Agent: 8 Layers That Stay Safe [2026]

An autonomous Claude Code agent needs more than a loop. Here are the 8 safety layers that let it act overnight, on its own, without wrecking your repo.

2026-06-08|11 min

claude-codeautonomous-agentsai-safetyagent-architectureverification

6 Claude Code Failure Modes and How to Fix Each [2026]

Claude Code breaks in predictable ways: compaction drift, over-delegation, context poisoning. Here are 6 failure modes and the hook that fixes each.

2026-06-08|11 min

claude-codehookscontext-managementdelegationmemory

Claude Code Human-in-the-Loop: The Decision Desk [2026]

An autonomous Claude Code agent acts on everything safe. What's left needs you. The human-in-the-loop desk surfaces only the decisions that matter.

2026-06-08|9 min

claude-codehuman-in-the-loopautonomous-agentsai-safetyagent-architecture

Claude Code Verification: Why 'Done' Isn't Done [2026]

In Claude Code, 'tests pass' and 'committed' are not the same as done. Here is the 3-leg verification proof I use to know a task actually works.

2026-06-08|5 min

claude-codeverificationai-agentstestingworkflow

A Negative Result on Claude Code Agent Self-Regulation [2026]

Built CSRA to fix drift in Claude Code agents. Two benchmarks, deltas -0.8 pp and -2.0 pp. The helmet was designed for falls. The agent did not fall.

2026-05-21|12 min

claude-codeai-safetyagent-evaluationnegative-resultswe-bench

Auditing My Claude Code Correction Rate Measurement [2026]

Migrated Claude Code Opus 4.6 to 4.7. Success metric said corrections rose 60 pp. Two methodology bugs hid the truth: real number was -47.4%.

2026-05-19|6 min

claude-codemeasurementmethodologyopus-4-7

Connect Claude.ai, Cowork & Claude Code with Shared Memory

Stop losing context between Claude.ai, Cowork, and Claude Code. One free system prompt and Kairn MCP give all three Claude Code surfaces shared memory.

2026-04-07|6 min

claude-codekairnmcpevolving-litecowork

59 Experiments on Claude Code Agent Behavior

I tested 6 psychological personality profiles across 59 Claude Code agent runs. One paragraph changes agent behavior by 300% on ambiguous tasks.

2026-04-04|5 min

claude-codeagentsbenchmarkautomation

Claude Code Adaptive Research: Autonomous Loops That Learn

Claude Code adaptive research automates the entire loop. One command, quality-gated reports, personalized to your projects. Gets smarter every run.

2026-03-31|5 min

claude-codeautomationresearchplugins

Claude Code System Design: 5 Breakthroughs from Biology, Not CS

How slime mold routing, PageRank, and quantum physics built a better Claude Code system architecture than 18 months of AI papers ever could.

2026-03-25|8 min

claude-codesystem-architectureagentsknowledge-graphoptimization

How Do You Manage Parallel Claude Code Sessions?

Claude Code absorbed most of what tmux orchestration was built for. What subagents now do natively, what tmux still buys you, and how to build it.

2026-03-22|7 min

claude-codeautomationagentsorchestration

Claude Code Persistent Memory with Evolving Lite

Claude Code auto memory is a capped, machine-local index of what Claude judged worth keeping. Evolving Lite and Kairn add a knowledge graph you control.

2026-03-20|5 min

claude-codememoryevolving-litekairnopen-source

CLAUDE.md Rules: Split Instructions Across Files

Claude Code's .claude/rules/ directory lets you modularize CLAUDE.md instructions. Here's how I cut context bloat by 73% using a 2-tier rules system.

2026-03-11|5 min

claude-codeCLAUDE.mdrulesproductivity

Why Your Claude Code Agents Agree With Each Other

Multi-agent Claude Code analysis converges on shared blind spots. Structural divergence with 7 cognitive lenses fixes it. Open source.

2026-03-09|5 min

claude-codeagentsopen-sourceanalysis

Claude Code Team Guardrails That Stop AI Chaos

5 devs prompting Claude Code differently means 5 different outputs. Shared configs, rules, and hooks enforce consistency across your team.

2026-03-08|5 min

claude-codeteamcollaborationhooks

Claude Code Planning Framework: UPF + DSV Reasoning in One System

How I use a 4-stage Claude Code planning framework built on DSV reasoning to catch wrong questions before they become expensive wrong answers.

2026-03-01|10 min

claude-codeplanningreasoningai-agentsarchitecture

Claude Code Session Memory: Build Systems, Not Sessions

Most Claude Code memory plugins solve storage. This free plugin adds a complete session management system - memory, handoffs, learnings - in 60 seconds.

2026-02-28|5 min

claude-codesession-managementmemoryplugin

Claude Code Prompt Caching: The One Rule Behind It [2026]

Prompt caching drives every Claude Code design decision. Here's how prefix matching works and how to stop accidentally breaking your cache.

2026-02-27|9 min

claude-codeprompt-cachingoptimizationcontextcost

Claude Code Session Management: Why I Stopped Restarting

I tested Claude Code's prompt cache with a marker injection. Here's what breaks it, what's safe, and a loop strategy that keeps your cache warm.

2026-02-27|5 min

claude-codesession-managementprompt-cachingoptimization

Claude Code MCP: From One Server to a Full Tool System [2026]

Claude Code MCP goes beyond single-server setups. Here's how to organize multiple servers, manage context overhead, and build a tool system that scales.

2026-02-22|11 min

claude-codemcparchitecturetools

Claude Code vs Cursor: Which AI Coding Tool Fits You? [2026]

Claude Code vs Cursor in 2026 - both have agents now. Here's what actually differs and how to choose based on how you work.

2026-02-22|12 min

claude-codeagentsworkflowtoolscomparison

Why Skill Graphs Beat Flat Files in Claude Code

Flat files break at scale. Build a Claude Code knowledge graph that lets agents navigate 400+ components with progressive disclosure.

2026-02-20|5 min

claude-codeknowledge-grapharchitectureagents

Claude Code Saves Corrections but Does Not Enforce Them

Claude Code auto memory saves your corrections but does not enforce them. My hook catches them deterministically - and deliberately stops short of writing a rule.

2026-02-17|5 min

claude-codehooksautomationself-correction

Auto-Delegation in Claude Code: Score-Based Task Routing

A scoring formula that automatically routes Claude Code tasks to sub-agents and selects the right model. Zero manual routing decisions needed.

2026-02-17|7 min

claude-codeagentsdelegationautomation

Trait-Based Agent Composition in Claude Code

How I replaced 56 hardcoded Claude Code agent files with a 3-dimension trait system. 10 expertise x 8 personality x 6 approach = 480 agents on demand.

2026-02-17|5 min

claude-codeagentsarchitectureautomation

How I Plan Complex Projects With Claude Code (Open-Source)

After 117 failed plans I built a 4-stage planning framework for Claude Code. It catches the gaps that only surface during execution. Now it is open-source.

2026-02-16|5 min

claude-codeplanningopen-sourceproductivityworkflow

Claude Code Hooks: Automate Your Workflow [2026]

Claude Code hooks run shell commands on 31 event types. How to configure them, which 18 can actually block, and 5 production hooks with working code.

2026-02-15|12 min

claude-codehooksautomationproductivitytutorial

5 Real CLAUDE.md Files You Can Copy Today (With Templates)

Stop staring at a blank CLAUDE.md. Here are 5 production-ready Claude Code templates for different project types - minimal, agent-heavy, and monorepo.

2026-02-14|5 min

claude-codeCLAUDE.mdsetuptemplatestutorial

Claude Code Context Window: Stop Wasting Tokens [2026]

Claude Code loads context before you type. Here's what fills the window, what survives compaction, and how to keep sessions sharp.

2026-02-13|10 min

contextclaude-codeoptimizationtoken

From 1 to 81 Agents: Building a Sub-Agent System in Claude Code

How I built a multi-agent delegation system with 81 specialized agents in Claude Code. The full architecture, trade-offs, and lessons learned at scale.

2026-02-13|5 min

agentsclaude-codedelegationarchitecture

Claude Code Persistent Memory: Setup Guide [2026]

Claude Code has built-in memory now. Here's how to set it up, what it misses, and how to build a full persistent memory system on top.

2026-02-13|10 min

memoryclaude-codetutorialproductivity

Self-Correcting Claude Code Workflows with PreToolUse Hooks

Build self-correcting Claude Code workflows using PreToolUse hooks that detect context drift and inject relevant context mid-session automatically.

2026-02-13|5 min

claude-codehooksautomationworkflow