Skip to content
All tags

#dx

18 posts

Claude Code Config Not Taking Effect: Diagnosing with /context, /doctor, /mcp, and Error References

When CLAUDE.md rules are ignored, hooks never fire, or an MCP server shows no tools, the file usually didn't load, loaded from an unexpected location, or got overridden. This guide covers what the diagnostic entries (/context, /memory, /skills, /doctor, /mcp, and more) actually show, safe-mode bisection, and a table of six high-frequency error messages with fixes.

ai debug

How to Write a Claude Code Skill That Doesn't Eat Context: Entry Point, Thresholds, Cost, Sources

I turned Anthropic's session-cost advice into a global skill, and the first version made the very mistakes it was meant to prevent: a description stuffed with trigger keywords, hard thresholds based on file counts and minutes, and 'protect the main context' conflated with 'spend fewer tokens overall'. Three rounds later the entry point is one page, details live in references, numeric thresholds became four judgment dimensions, and every claim from a draft post was checked against official docs.

Reading Guide: Pick What Most People Use — the Other Five Criteria Are Tie-Breakers

The primary criterion has not changed: it is still adoption — and AI makes it matter more, not less, because more users means more training data means higher agent accuracy. The five criteria this series collects (machine-readable docs, types, whether the source is in your repo, data shape, machine-callability) are for breaking ties when adoption is comparable, or for costing out what picking the less popular option will charge you.

Claude Code Routines: Complete Guide to Cloud Automation — Setup, Triggers, and Real-World Examples

Routines is Claude Code's cloud automation system (formerly Cloud Scheduled Tasks). Beyond cron scheduling, you can trigger runs via API endpoint or GitHub events — scan issues, review PRs, run checks, open PRs — all while your computer is off.

tech guide

Solving Duplicate Config Files for Codex and Claude Code with a Symlink

Claude Code only reads CLAUDE.md; Codex only reads AGENTS.md. Teams using both end up maintaining two identical files. Fix: make CLAUDE.md a symlink pointing to AGENTS.md — one source of truth.

Claude Code Troubleshooting Index: Orders 33-35 on Install, Runtime, and Config Diagnosis

The original Claude Code troubleshooting collection has been split into orders 33-35: installation & login, runtime problems, and config diagnosis. This page is their index.

Claude Code Agent Teams in Practice: Team Lead, Point-to-Point Messaging, and a Shared Task Board

Agent Teams lets multiple full Claude Code sessions work as one team: a team lead assigns work while teammates each run their own context window, coordinating through point-to-point messaging and a shared task list. This post covers the three key differences from sub-agents, the trade-off between teammateMode display modes, and why token cost scales linearly with team size.

Claude Code in CI/CD: @claude on GitHub Actions and the GitLab MR Flow

Put Claude Code into GitHub Actions with anthropics/claude-code-action: /install-github-app sets everything up in one command, @claude in a PR or issue comment gets bugs fixed, branches pushed, and PR creation links returned; Bedrock/Vertex/Foundry backends switch via one input with OIDC and no stored keys; the GitLab CI/CD integration (beta) mirrors it as a single .gitlab-ci.yml job where every change flows through a merge request.

How Claude Code Sub-agents Work: Context Isolation, Frontmatter Definitions, Background Execution, and Permission Inheritance

Sub-agents are specialized assistants that work in their own context window: a single Markdown file defines their system prompt, tools, and model. Claude delegates automatically based on the description field, or you can @-mention to force one. This post breaks down the frontmatter schema, background execution and nested spawning, permission inheritance rules, and when not to use them.

tech guide

Biome: Replacing ESLint + Prettier with Rust

Biome does the work of ESLint + Prettier in a single tool, running 10–20x faster with far less configuration. DaoDao uses it across an entire monorepo — lint and format in one pass.

Claude Code Global Skills Not Found in New Sessions? Understanding Skill Discovery and How to Debug It

Global skills live in ~/.claude/skills/, but they go missing in new sessions or the Desktop App? The problem usually isn't a missing file — it's that the skill descriptions aren't being loaded into context. This post clarifies the CLI vs Desktop App differences, the role of settings.json, and the most reliable fix.

A One-Person Full-Stack Team: AI-Driven Development Workflow from OpenSpec to Auto-Deploy

Use OpenSpec to break requirements into engineering tasks, Claude Code to implement them, hooks to auto-format and protect, local review before committing, three AI reviewers running in parallel on PR, and auto-deploy after merge. This entire workflow lets one person maintain quality across six sub-projects.

Claude Code Hooks: A Complete Guide to Event-Driven AI Control

Hooks are Claude Code's event system. They trigger shell commands, HTTP requests, MCP tools, or LLM evaluations automatically before/after tool execution, when a prompt is submitted, or when a task ends. Use them to block dangerous operations, run automated reviews, inject context, or write audit logs.

Claude Code Skills: A Complete Guide to Turning Repetitive Workflows into Single Commands

A Skill is an SOP written for AI. Define the steps in a Markdown file and Claude follows them. No coding required, no frameworks to learn — just write down what an experienced person would do.

Turning Debug Sessions into GitHub Issues with a Claude Code Skill: Designing /file-bug-issue

Stuck mid-debug and can't fix it right now? Use /file-bug-issue to package the error analysis, reproduction steps, and attempted fixes from your conversation into a well-structured GitHub issue. Pair it with a Remote Agent to let AI automatically take over the fix.

Let AI Pick Up Issues, Write Code, and Open PRs: Hands-Off Development with Claude Code Remote Agent

Using Claude Code's Scheduled Remote Agent, automatically scan GitHub issues every 2 hours, implement features, open PRs, and address review feedback — no human intervention required. Humans only write issues and click merge. Pair it with the custom /publish-tasks skill to push OpenSpec engineering tasks directly to GitHub issues.

Claude Code's Three-Layer Quality Defense: Hooks, Skills, and Instruction Files

Hooks are automated safety nets (blocking bad commits), Skills are interactive workflows (running checks + auto-fixing), and instruction files (CLAUDE.md / AGENTS.md) are behavioral guidelines. Each layer operates independently, but together they enable an AI agent to automatically run lint, typecheck, and build checks before every commit.

tech guide

How to Classify Code Review Comments? From Conventional Comments to AI Review Tool Taxonomies

Three main classification systems dominate: Conventional Comments (label-based), Google's severity prefixes (Nit/Optional/FYI), and SonarQube's four quadrants (Bug/Vulnerability/Code Smell/Hotspot). AI review tools have each developed their own taxonomies, but the core dimensions consistently converge on four areas: correctness, security, performance, and maintainability.