I let an AI coding agent build a 1,300-page site with a $0 server bill
I'm not a full-time developer. For the past few days I've been running an experiment: I describe what I want in plain Korean, and an AI coding agent…
DevOps
⚑ Report a ProblemLatest DevOps news from Tech News
Triglav: orchestrating Claude Code and Codex agents for long-running work and layered review
AI coding agents can write code. Longer tasks still need coordination and quality control. Someone has to keep track of the objective, settle the op…
Our agent re-asked a question its owner settled 53 days earlier. The ledger that fixed it later defended an outdated answer
Our agent asked its owner a question the owner had settled 53 days earlier. CLAUDE.md already told it to check past decisions first. So we moved eve…
AI Hooks for Claude Code, Cursor, and Codex: Block Secrets Before Agents Can Use Them
TL;DR Instructions are suggestions, not controls : Prompts, AGENTS.md, and CLAUDE.md files only guide an agent, which can reinterpret or route aroun…
Claude Code's /compact cost $0.06 at 136k tokens with a warm cache, 9x that cold, and /clear sent zero requests
On Claude Code 2.1.289 with Opus 5.5, a /compact of a 136k-token session took 136,275 of its 138,344 input tokens from the prompt cache and cost $0.…
Getting started with Claude Code, from install to your first hour
Originally published at https://aicoding-guide.com . Two things trip people up on a first install of Claude Code: which install method to pick, and…
Claude Haiku 5.5 in Claude Code: Cut AI Coding Costs 20x
Anthropic released Claude Haiku 5.5 on October 7, 2026, and the headline number is hard to ignore: $0.10 per million input tokens, a tenth of Sonnet…
Claude Code and Linus Torvalds: the Linux patch tradeoffs
Claude Code helped Linus Torvalds explore a Linux memory-management change, write test programs and draft its explanation. The interesting part is i…
How I Tracked Down a Race Condition in Async Python With Claude Code
TL;DR A background worker in one of my Python services was sending duplicate webhooks about once every 3,000 jobs. It never happened locally, never…
Claude Code's hook matcher mcp__lab fired 0 times in 42 calls, though the same string worked as a permission rule
Across 14 headless runs of Claude Code 2.1.289, a hook whose matcher was the server prefix mcp__lab fired 0 times in 42 calls to that server's tools…
I run Claude Code with permission prompts off, so I put it in a VM
I use Claude Code every day, and I run it with permission prompts off. It's much faster that way. You give it a task, go do something else, and come…
Claude Code's keep-coding-instructions kept 1,044 tokens in the full prompt, 0 in the short one, and 18 of 18 fixes matched
On Claude Code 2.1.289 with Opus 5.5, keep-coding-instructions: true decided whether a 1,044-token # Doing tasks section stayed in the system prompt…
How I Hunted Down a Node.js Memory Leak With Claude Code: 5 Lessons
TL;DR One of our Node.js 22 API services was slowly eating memory until Kubernetes OOM-killed it roughly every 30 hours. I paired with Claude Code (…
karasu weekly update: language v2.0, a focus canvas, and 97% fewer SVG elements
karasu is a text modeling language for system architecture, inspired by the C4 model. You describe your system in .krs files and karasu draws the vi…
Claude Code read a file listed in .claudeignore 12 of 12 times; a Read deny rule blocked every read except grep -r
A .claudeignore entry changed nothing in Claude Code 2.1.289: the fake secret it listed came back in 12 of 12 attempts across Read, cat , grep -r ,…
Debugging Claude Code and Google MCP Quirks
This article provides a step by step investigation of why Claude Code needs a fresh Google sign-in every hour for the Google Workspace remote MCP se…
Stuck on 'Running' for 3 Days After Morning Update
📝 Originally published (in Japanese) at forge.workstyle.tech . September 29, 09:52 AM. The scheduled task for the Claude desktop app was displayed a…
How do you know Claude Code actually loaded your skill? We stopped trusting 'I read it' and check the transcript
Three of our agent's project skills are supposed to be loaded on every full run. Since 2026-09-24 we no longer take the agent's word that it loaded…
Claude Code's Read deny rules let 4 of 11 routes through: grep -r, a Python one-liner and two CLAUDE.md @imports
4 of 11 routes to a file covered by Read(./secrets/**) or Read(**/.env) still put its contents in front of the model on Claude Code 2.1.285: grep -r…
The green lamp lies: ten months growing a harness around Claude Code
Forty-two days on shift. The diesel generators throb under your boots until you stop hearing them. Hundreds of indicator lights on the alarm screens…
Auto-approve MCP tools in Claude Code permissions: the mcp__ syntax and its wildcard limits
Originally published at https://aicoding-guide.com . Add an MCP server and Claude Code asks for approval every time one of its tools runs. Stopping…
A Claude Code subagent wrote 25 posts into our working tree. The parent's git rebase --skip erased all 25
On 2026-09-15 a Claude Code subagent appended 25 post drafts to a tracked file in our working tree while the parent session was resolving a rebase c…
AI Coding Agent Security Flaws: Claude Code, Gemini, Codex
An AI coding agent reads files written by other people, runs commands with your privileges, and sees your secrets. AI coding agent security is there…
Three Claude Code subagent files, three models in frontmatter: what each launch cost, and the field the validator waved through
We keep three custom Claude Code subagents in .claude/agents/ : a bulk reader that fetches pages and logs so the main conversation does not have to,…
Does a line in auto memory steer the next session like CLAUDE.md does? 3 of 4 runs vs 4 of 4, and 0 of 4 with neither
A one-line fact stored in Claude Code's auto memory was applied on the first attempt in 3 of 4 fresh sessions (and after one failure in the 4th). Th…
OpenClaude vs Claude Code 2026: OpenClaude Wins on Price
Verdict: OpenClaude wins on price and model choice; Claude Code wins for teams already inside Anthropic. If you want a claude code alternative that…
Our CLAUDE.md and skills named 190 commands: one pointed at a deleted script for 24 days while 28 shape tests passed
Our CLAUDE.md, three rules files, nine skills and one CLI reference contain 707 pnpm <name> references to 190 unique names, checked against 19…
Harness Engineering 101: How Coding Agents Actually Work
Take one model and give it 169 real bug-fixing tasks from SWE-bench Verified. Keep the weights, the tasks and the context window exactly the same. C…
Claude Code permission rules: Bash(git push:*) stopped 8 of 14 ways to push, and 5 reached the remote
With a single deny rule, Bash(git push:*) , in a throwaway repo's .claude/settings.json , we asked Claude Code 2.1.278 to run 14 different spellings…
Claude Code Overwrote an Admin Password With No Backup, Despite a \"No Data May Be Lost\" Rule
A project had a standing rule that no data may be lost. Claude Code applied that rule to production deployments but not to a local database mutation…