Claude Code Hooks: Exit Code 1 Doesn't Block. 9 of 9 Commands Ran
My guard hook printed BLOCKED: git reset --hard in red text. Then Claude Code ran git reset --hard anyway, and an afternoon of uncommitted work went…
Testing & QA
⚑ Сообщить о проблемеПоследние новости Testing & QA от Tech News
Все темы
agents
ai
api
architecture
automation
backend
beginners
career
claude
cybersecurity
devchallenge
devops
discuss
javascript
llm
machinelearning
mcp
node
opensource
performance
productivity
programming
python
security
showdev
softwareengineering
testing
tutorial
typescript
webdev
Claude Sonnet 5.5 and Haiku 5.5 in Python: Two SDKs, Prompt Caching and Haiku's 100K Pricing Cliff
Short answer: call claude-haiku-5-5 for classification, extraction, routing and summaries, and claude-sonnet-5-5 for multi-step coding and long tool…
60 Claude Certified Architect Exam Questions & Answers (CCAR-F)
Which exam are you preparing for? Architect Foundations (CCAR-F) Architect Professional (CCAR-P) Associate (CCAO-F) Developer (CCDV-F) All 60 origin…
How to Rotate Claude API Keys with Secrets Manager and Lambda Without Getting Locked Out
Developers rush to rotate API keys for security, only to discover their AI‑powered apps suddenly start throwing 401 errors. The hidden culprit? A st…
Claude’s New Self‑Shutdown Feature Targets Abusive Chats
Photo by Brecht Corbeel on Unsplash A Chat Ends on Its Own Claude Opus 4 and its sibling 4.1 can now terminate a conversation without user input, a…
Where my Claude Code tokens actually go: 7 days of logs, and why tool output isn't the problem
A few days ago I tested three Claude Code token-saving tools, and all three raised my cost. So this time I stopped testing tools and measured where…
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.…
Anthropic’s Scion Shows Why AI Agents Are Forcing a Rethink of Source Control
Anthropic has redesigned its internal source-control infrastructure after AI-assisted development pushed its daily merge volume from roughly 2,500 c…
The 4 rules in my CLAUDE.md that fixed most of my bad Claude Code sessions
Claude Code is amazing for about a week. Then it refactors a file you didn't ask it to touch, over-engineers a five-line fix, or proudly announces "…
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…
Build without Limits - SDLC Briefing - Edition #1
Hi! I am Ricardo Sueiras, leading SDLC transformation at Indicium AI. That means I get to work with customers and help them understand how to use ag…
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…
Claude Code Skills for Content: How I Make Khan Academy Style Videos for Free
I opened a LinkedIn post last week with "I think Claude Code skills are mostly useless." It got about 30,000 impressions and a lot of disagreement,…
Two agent CLIs, one repo: sharing context between Claude Code and Codex without stepping on each other
I run Claude Code and Codex against the same codebase every day on macOS. For the first month they kept overwriting each other's work, and I spent m…
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…
One memory across AI agents: what it actually takes
The memory built into a coding agent lives inside that vendor's tools. What I tell one agent stays with that agent, and the next one I open in the s…
Claude Haiku 5.5 ผลการทดสอบประสิทธิภาพ
Claude Haiku 5.5 ได้คะแนน 72.4% ใน OSWorld 2.1, 1620 ใน GDPval-AA v2.1, 46.4% ใน FrontierCode 1.1 และ 39.2% ใน Terminal-Bench 4.0. Haiku 4.5 ได้คะแน…
Claude Haiku 5.5 Benchmark
Claude Haiku 5.5 mencetak 72,4% pada OSWorld 2.1, 1620 pada GDPval-AA v2.1, 46,4% pada FrontierCode 1.1, dan 39,2% pada Terminal-Bench 4.0. Haiku 4.…
Claude Haiku 5.5 vs Haiku 4.5: Apa yang Berubah dan Perubahan Merusak yang Harus Diperbaiki Pertama
Claude Haiku 5.5 ( claude-haiku-5-5 , dirilis 7 Oktober 2026) berharga 90% lebih murah daripada Haiku 4.5 untuk prompt hingga 100K token ($0,10/$0,5…
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 ,…
Five Ways My AI Agents Went Wrong (and What I Changed)
I run a small software company by myself. Claude Code agents play the engineers, QA, marketing and so on. It works better than I expected, but almos…
How I set up Claude Code: one rulebook, a 12-step relay to use it daily
Claude Code used to feel like a brilliant teammate with no onboarding. Some days: tests first, small diff, asked before pushing. Other days: no test…
Letting Claude Code drive a browser you've logged into once
A lot of the data I actually care about lives behind a login: analytics dashboards, admin panels, supplier portals. Most of them have no API, or one…
claude code token optimizer vscode extension
TL;DR I built a vscode extension that reads the session transcripts claude code already writes to ~/.claude/projects/ and turns them into a dashboar…
I Built a Full PWA Game in One Day with Claude Opus 5.5 and Claude Code (Here Is the Real Token Cost & Harness Setup)
On a Sunday, I turned a slightly silly idea into an actual game: Montanha: Zero Day , a cyberpunk platformer in the style of Mega Man X that runs in…
Your Prompt Rules Are Just Suggestions: Claude Code Hooks Auto-Format Every Edit and Block Dangerous Commands (2-Minute Setup)
You told Claude Code “always run the formatter after editing” and “never run rm -rf ”. It listened, until it didn’t. A rule in a prompt is a request…
Claude Code mods: Minesweeper and testkit
My own harness, the tooling I run around Claude Code, comes with a custom trust score. That trust score decides whether I can leave the agent alone…
The Plugin That Turns Your Claude Code into a Continuously Self-Improving Monster
Originally published on Eigenwise on 11 September 2026. Something goes wrong in a session, so you write a rule. Next week the rule gets buried under…
I got tired of logging in and out of Claude Code, so I built a one-command account switcher
Quick confession: last week I logged out of my work Claude Code account four times in one afternoon. Nothing was broken. I just have a second accoun…
I Built an Internet Court. Now I'm Trying to Find Out If Anyone Actually Wants It.
A couple of weeks ago, I had a domain sitting around: loopproof.me I owned the domain, but I didn't have a product. So I opened Claude Code and gave…