What oCMS 0.29 and 0.30 Change for Production Sites
UTC timestamps, mandatory production MFA, and health-aware deployments: what oCMS 0.29 and 0.30 change for developers running real sites.
Blog Portfolio oCMS
~/it digest
$
cat welcome.txt
// Recent Posts
AI Engineering Claude Code
I Benchmarked My Claude Code Presets. The Cheap Ones Passed Every Check.
Five Claude Code presets, four real task types, 60 runs: the light presets passed every check at a tenth of the cost of Opus at high effort. How the harness, the graders and the fairness controls were built.
AI Engineering Blog Portfolio oCMS
oCMS Now Speaks MCP: A Read-Only Server That Lets AI Agents Read Your Site
oCMS now ships a read-only MCP server: ten typed tools let Claude Code, Cursor and other agents search and read site content, with drafts hidden and every API key policy enforced.
AI Engineering Claude Code Codex
GPT-5.6 Is Out — and That's Good News Even If You're a Claude User
OpenAI's GPT-5.6 (Sol, Terra, Luna) is a serious release — and that's good for everyone: better per-task quality, flexible token budgets, and a stronger Codex + Claude Code duo.
AI Engineering
Claude Fable 5 in Practice: Faster Than Opus 4.8, Better Code — and One Real Catch
A hands-on take on Claude Fable 5: at the same effort level it's faster than Opus 4.8 with noticeably better code quality — but roughly a third of security audits get blocked by its widened cyber classifier and rerouted to Opus 4.8.
AI Engineering
Claude Fable 5 Is Back: Redeploy, a Tighter Cyber Classifier, and an Industry Jailbreak Framework
US export controls on Claude Fable 5 and Mythos 5 have been lifted; Fable 5 returns July 1 with a tighter cyber classifier (more false positives, Opus 4.8 fallback), a new industry jailbreak-severity framework, and deeper US government collaboration.
AI Engineering
Claude Fable 5: A Developer's Look at Anthropic's First Mythos-Class Model
Anthropic's new Mythos-class model, Claude Fable 5, is its strongest coding and agentic model yet — cheaper than the preview, with a new safeguard layer that can fall back to Opus 4.8.
AI Engineering Claude Code
AI Didn't Kill Engineering. It Moved Engineering Upstream.
AI did not kill engineering. It killed the illusion that typing code was the hard part. In my Claude Code + Go + oCMS workflow, the human job moved upstream: intent, constraints, architecture, verification, and context discipline.
AI Engineering Blog Claude Code Portfolio
Vibe-coding a production Telegram bot with Claude Code: how I built `it-digest-bot` in 54 commits
A 54-commit build diary: Claude Desktop drafted the spec, Claude Code executed it, and the result is a production-grade single-binary Go service scheduled by systemd.
AI Engineering Claude Code Portfolio
I Built an LLM Wiki for a 200k-Line Go Codebase. Here's What Happened.
Karpathy-style LLM Wiki over oCMS: 106 Markdown pages compiled by Claude Code in one evening, ten documentation contradictions surfaced, wikilint enforcing invariants, CLAUDE.md making the wiki consultable for agents.