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…
Team Management
⚑ Сообщить о проблемеПоследние новости Team Management от Tech News
Все темы
Culture
agents
ai
api
architecture
automation
beginners
career
devchallenge
devops
discuss
javascript
learning
llm
machinelearning
mcp
opensource
productivity
programming
python
react
saas
security
showdev
softwareengineering
startup
testing
tutorial
typescript
webdev
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…
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…
How I build a product alone with a team of seven Claude Code agents
Someone in a founder group I am part of asked a good question: how do you let several agents work on one product in parallel without them stepping o…
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…
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…
Fable 5.1 vs GPT-6 Astra vs Gemini 3.8 Flash on Real-SWE
If you want the highest first-try success rate on real enterprise code, Fable 5.1 running inside Claude Code wins: it resolved 38.8% of tasks on the…
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…
Your AI Model Isn’t Limited. Your Request Is. So I used jev to fix it.
A prompt sent to an AI is a snapshot of what you know at the exact moment you type it. That sounds obvious, but it carries a consequence people rare…
Making Verification Visible
The hackathon gate had one output: a line in the terminal saying a task passed, failed, or needed a human. That line is honest, but it is small. It…
Open Source MCP Gateways for Claude Code in 2026
TL;DR Connecting Claude Code directly to multiple Model Context Protocol (MCP) servers causes severe token bloat, credential fragmentation, and secu…
Claude Code Changed How I Work — An Honest Developer Review
TL;DR: Claude Code is a CLI tool that reads your entire codebase and makes coordinated multi-file changes. It cut my feature development time from 4…
How pdlc-skills Makes Progress, Change Impact, and Quality Trends Visible
The last post covered the quality chain. This one is about visibility . An AI can push three features forward in an afternoon. If you can't tell whe…
Claude Code vs Cursor vs Copilot: An Honest Review After 40 Production Automations
₹40,000 to ₹70,000 — that's the extra monthly capacity my consulting practice has picked up since switching my primary dev loop to Claude Code six m…
We cut CLAUDE.md to 33KB. Eighteen days later it was 45KB again: what a size cap missed and a structure test caught
We cut our agent's CLAUDE.md from 548KB to 33KB on 2026-08-18 and put a 45KB cap on it. Eighteen days later the file was 45KB again. The cap had wat…
Auto memory on 21 projects: 17 empty, and 3 repos learned the same fix separately
Claude Code's auto memory is on by default and writes to a per-repository directory you probably have never opened. On one machine with 21 such dire…
67 Lines of Bash That Won't Let an LLM Say Done: A Stop Hook That Reads the Transcript JSONL
Back when I was a student pulling in ¥100k a month, I thought delegating work came down to three things: ask politely, check in on progress, trust t…
How to take over a design built in Figma Make and develop it with Claude Code
From February to April 2026, I launched four web apps, each starting from a code bundle that Figma Make (Figma's AI feature that generates a working…
19 Audit Nags in One Night: Making a Claude Code Stop Hook Detect Unattended Sessions
My autonomous setup earns its keep precisely because Claude Code starts on its own and finishes on its own. The thing that nearly broke that setup w…
15 AI Coding Prompts for Codex and Claude Code
Code audits, performance work, feature planning, and product research, with an installable workflow skill. Theo shared six ways he uses Astra : code…
Run your AI subscription 24 hours a day — use the quota you already pay for
Let me start with a question. Why did I fear development done by artificial intelligence? The answer is plain. AI can build software, and on top of…
The Portability Trap: When 'It Loads' Doesn't Mean 'It Works'
I ran a skill migration and nothing broke. Or so I thought. Break 3 in my migration diary noted that skills degraded silently. This is the deep dive…
Claude Code's ELI5 Skill Explained: How It Works, Setup, and When to Use It
This article reflects Claude Code's spec as of August 2026. Since Claude Code updates frequently, check the official docs for the latest behavior. T…
An AI's “Done” Can't Be Trusted — Quality Gates That Stop False Completion With Evidence
On June 29, 2026, a mobile app reported that "the first wave of parity with the PC version is complete, 162 tests green." When we actually touched i…
How I Decide a RAXXO Tool Needs a Redesign, Not a Patch
I track three signals before I touch a shipped RAXXO tool's core screens again A patch fixes one report, a redesign answers the same complaint from…
From kanban to harness: when the tracking tool becomes the orchestrator
When I shipped KittyClaw two weeks ago, the tool did one thing: serve as a board. The Claude agents ran alongside - first by hand, then via a dispat…
We cut our CLAUDE.md from 548KB to 34KB: what loads when, measured — and the commit gate that keeps it small
Our CLAUDE.md was 548KB. Every session — including every subagent — loaded all of it before doing any work. One measured headless run wrote about 15…
Don't store trust, derive it: a trust model for agent-written docs
Your coding agent writes persistent knowledge now. CLAUDE.md files, memory directories, runbooks, "what I learned about this codebase" notes. If you…
Building with mini, Part 9/9 (finale): Onboarding a running project — import-gsd, audit, map
Eight parts, the whole command set: from init through the loop, autonomous mode, state and health. But the whole time we built pycalc from scratch —…
Fixing Visual Discrepancies with Claude Code + Chrome Extension
📝 Originally published (in Japanese) at forge.workstyle.tech . You've got a code that looks correct when read, but when you open it in the browser,…