Tessl - Blog · Scour

OpenAI open-sources Symphony, a spec for orchestrating Codex agents

Covers Codex Symphony Agent Orchestration (28 minute read)

Common Pitfalls of Skills Development (And How to Fix Them)

Anthropic postmortem shows how small changes compounded into Claude Code failure

Covers An update on recent Claude Code quality reports

As SpaceX deal looms, Cursor partners with Chainguard to secure open-source dependencies in AI-built code

Covers 2 stories including Do you respect 'Vibe Coders'? Can you actually call them devs?

Replit launches “Security Agent” to scan and fix vulnerabilities in AI-built apps

Covers 4 stories including Assessing Claude Mythos Preview's cybersecurity capabilities

Evaluating Kimi 2.5 vs Kimi 2.6: What happens to agent skills when the model gets smarter?

Anthropic, OpenAI, or Cursor model for your agent skills? 7 learnings from running 880 evals (including Opus 4.7)

Discussed on Hacker News

Cloudflare introduces “Agent Memory” to help AI agents remember across sessions

Google adds subagents to Gemini CLI to handle parallel coding tasks

Covers 2 stories including Orchestrate teams of Claude Code sessions

Anthropic adds 'routines' to Claude Code for scheduled agent tasks

Covers Claude Code Routines

Log in to enable infinite scrolling