Notes

Cloudflare Workers now lets you declare required secrets in wrangler.jsonc or TOML — Wrangler validates them locally, generates TypeScript types, and blocks deploys if any are missing. Small DX win that catches config drift before it hits production.

@M1Astra archived Anthropic's Claude Mythos blog post before it was taken down — a rare look at internal documentation about Claude's character, values, and the philosophical foundations behind how it was trained to engage with the world.

@appfactory's Agent-CI brings GitHub Actions workflows to local execution with a twist: when a step fails, it pauses and lets your AI agent fix the issue before retrying just that step. Uses the standard GH Actions Docker image but with near-zero caching latency, designed for the tight feedback loops agents need without burning through CI minutes.

Claude Code now supports .worktreeinclude files — drop one in your project root to automatically copy gitignored files like .env, .env.local, or config/secrets.json when Claude creates a worktree. Handy for keeping your agent's isolated branches functional without manual setup.

pi-lab lets you A/B test tools in the pi coding agent by intercepting calls, forking into isolated lanes, comparing outputs, and merging the winner back. Still experimental, but a promising approach for iterating on agent tooling without flying blind.

@jerryjliu0 on LiteParse — a fast document parser that lets agents read any PDF on the internet. No VLM under the hood, so it runs anywhere. Latest update adds URL parsing and buffer/stream support. Designed to plug into 40+ different agents.

Gemini in Google Calendar now handles meeting scheduling by analyzing availability and time zones across busy calendars. Small quality-of-life improvement for anyone who's played scheduling Tetris across multiple participants.

@FabianHiller makes the case for Valibot over Zod: 88% smaller bundles (1.91 kB vs 16.57 kB), 16× faster initialization (54 μs vs 735 μs), plus cleaner pipelines and precise TypeScript inference. If you ship to web, edge, or serverless, the numbers are hard to ignore.

@dinokupinic previews Drizzle ORM v1.0 — migration folders reworked (no more journal.json), validator packages (drizzle-zod etc.) moved into drizzle-orm itself, and Relational Queries v2. The 1.0 stabilization everyone's been waiting for.

@adibhanna ships tsm v0.6 — a native terminal multiplexer that doesn't wrap your terminal in a server. Instead of re-emulating VT output, it delegates splits to your terminal's own API. Every pane is a real native surface with GPU rendering, ligatures, and scrollback preserved. Supports cmux, kitty, Ghostty, WezTerm, plus workspace manifests and agent sidebar sync.

@Lovable ships AI-powered penetration testing for vibe-coded apps — a swarm of agents runs OWASP Top 10 checks, privilege escalation tests, and data exposure scans. Validated findings sync back as actionable issues with formal pentest reports for SOC 2 and ISO 27001. What used to take weeks and cost $5k-$50k, now built into the platform.

@claudeai ships auto mode in Claude Code — instead of approving every file write and bash command (or skipping permissions entirely), auto mode lets Claude make permission decisions on your behalf with safeguards checking each action before it runs. The middle ground between trust-nothing and YOLO.

TypeScript 6.0 is out. The headline: Temporal is finally here. Also Map#getOrInsert, RegExp.escape, and the new #/ prefix for package imports. Defaults shift to ES2025 and --strict. Deprecations include baseUrl, outFile, import assertions, and the node moduleResolution strategy. ES5 target is gone — if you're still supporting IE11, you're on your own.

@p_millerd's WordPress to Astro migration skill for Claude Code. A 7-phase migration pipeline with script templates, covering XML extraction, HTML-to-Markdown conversion, embed preservation, and common issues. Built from real migrations of his personal blog, podcast site, and consulting content.

@mvanhorn's comprehensive guide to Claude Code productivity: skip permissions, run 4-6 parallel sessions, voice-dictate via Monologue, use plan.md files before coding. The /ce:plan workflow from Compound Engineering flips traditional dev from 80% coding to 80% planning. Also covers Mac Mini for remote sessions over Telegram, Granola for meeting-to-plan conversion, and a genuinely impressive Disney World trip planning demo.

Hugging Face Papers API for hybrid semantic search over AI research. @koylanai built a skill that runs parallel searches with keyword variants, triages by relevance and recency, then fetches full paper markdown to read actual methodology sections. The insight: the gap between paper published and practitioner applies it is shrinking. Teach your agent how to think about research, not just what to search.

Riley-Coyote/polyclaude is a Claude Code plugin by @RileyRalmuto that spawns subagents not for task delegation but for perspective delegation — six viewpoints (user advocate, architect, skeptic, pragmatist, innovator, temporal) that form a "council" to pressure-test your ideas before execution. Claude picks the most relevant 3 based on context. Clever repurposing of the subagent mechanism for structured thinking rather than parallel work.

Channels let you push events — CI results, chat messages, webhooks — into a running Claude Code session from an MCP server. @trq212 highlights this early research preview as giving Claude Code ears: it can react to external signals while you're away. The pattern of ambient agent awareness is where this is all heading.

Older notes