ByteCode.News
RSS
Tags/

#ai agents

#ai agents

2 articles

Securing Claude Code: Guardrails for AI-Assisted Development by Jim Manico

Jim Manico of Manicode Security showed OWASP London a disciplined approach to bootstrapping projects with Claude Code using scripted prompts that generate ARCHITECTURE, SECURITY, and CLAUDE files in sequence, each reviewed and committed before the next. His core rule: Claude never writes code directly - every change becomes a tracked GitHub issue first, giving developers review points and audit trails throughout.

By Jason Lee|
ai agentsclaudedevopssecurity

AIs Onboard, too

Yury Selivanov recently released lat.md, a knowledge graph for your codebase, stored as user-editable markdown. The tool itself sounds useful enough, but checking it out and working out what it provides for your code was more useful than the tool's existence itself: effective agent management means going through an onboarding process.

By dreamreal|
aiai agentsdocumentationllmmethodology