VoicesBall Claude Code Builds Not Buys 2430 Prompts ResearchAmplifying AI·high signalXBlueskyLinkedInCopy linkClaude Code overwhelmingly builds custom solutions rather than recommending third-party tools. When it picks tools: GitHub Actions 94%, Stripe 91%.SourceSource pageAmplifying AI↳ Follow the threadShared entity / Stack layerContext Privilege Escalation Attacks Hit 12 Real Agent Harnesses, Including Claude Code and CodexarXiv 2609.01222Shared entity / Stack layerClaude Code 2.1.258 fixes a launch regression that broke macOS Monterey for three versionsGitHubShared entity / Stack layerAtlas took 895 stars in a day for linking every agent commit back to the prompts and tool calls that produced itGitHub TrendingShared entity / Stack layerClaude Code v2.1.257 Adds Claude Fable 5.1 as the Default Fable Model With 1M Context at $10/$50 per MtokAnthropic (claude-code CHANGELOG)Shared entity / Stack layerMCP compliance tracker scores five coding agents at 56% and finds the Tasks spec implemented by noneIs MCP Good Yet?Policy dependency / Stack layerFour advisories land on Databricks' Omnigent meta-harness, one critical, all reported by an autonomous security agentGitHub Security AdvisoriesPolicy dependency / Stack layerCROSS-CATEGORY: Four Unrelated Vendors Shipped Agent Authorization Control Planes Inside 48 HoursJetStream (corroborated by Genesys Xperience 2026 coverage, aiagentstore.ai and Hacker News Show HN)Policy dependency / Stack layerCORAL Puts an LLM Agent in a Live Closed Loop on Production Recommenders and Wins Two A/B TestsarXiv 2609.02730