Apiiro reports finding 2,539 credentials matching its secret-classification rules in 1,994 public GitHub repositories, including values saved after Claude Code users approved commands with 'Yes, and don't ask again.' The research explains how settings, history and agent transcripts can retain credentials and recommends rotation, repository exclusions and command-aware scanning.
Why I recommend it: Apiiro did not use or test the credentials, so 'real secret' does not mean confirmed valid. Anthropic's Head of Claude Code said the team would prototype mitigations, including basic secret scanning.
A Claude Code and Codex skill for auditing AI-generated interfaces, proposing a design direction, and refining screens. The repository uses CC BY 4.0, requiring attribution; optional image services may cost money.
Free documentation on tracking token usage, setting team spending limits, and managing Claude Code costs through context management, model selection, and preprocessing. Claude Code usage itself may require payment; cost estimates are Anthropic’s own.
Explainer on gzip compression and how compressing conversation context can reduce time to first token in Claude Code, distinguishing client-side wait from API response time.
Anthropic's Claude Code team describes risk-layered review, automated checks, human approval, merge queues and rollback. It reports more merged pull requests and fewer reverts over June–September; these are the team's own results, not an independent study.
Guide to an MIT-licensed collection of Claude Code skills for analyzing and rebuilding app workflows, from reconnaissance through testing and deployment. Discusses legal, quality and security caveats; the skills are free, but model access is separate.
#Claude Code#Agent skills#Open source#App development
Anthropic's developers share tips, playbooks and opinions on building with Claude and Claude Code, including agents, skills, context engineering and prompt caching.
Why I recommend it: Written by the company that makes Claude, so it's practical but not neutral. Best read by people who already use Claude for coding.
