Trace-core - linter for AI-written failure patterns
Static analyzer that catches the 24 specific failure patterns characteristic of AI-generated code, like phantom imports and almost-right API usage.
This entry doesn't have a long-form writeup yet. Follow the source link above for the full context.
Recent discussion
From the wider webnikolai-vysotskyi/trace-mcp
github.com · Apr 29, 2026
delexw/claude-code-trace
github.com · Apr 27, 2026
Protecting the Trace: A Principled Black-Box Approach Against Distillation Attacks
arxiv.org · Apr 25, 2026
Monitoring Cortex Agent Performance Using Trace Data
medium.com · Apr 20, 2026
LLM Observability Deep Dive: How to Monitor, Trace, and Debug AI Agents in Production
dev.to · Apr 20, 2026
Featured in
Security tools for AI coding agents
Sandboxes, scanners, proxies, and governance toolkits that keep autonomous agents from doing damage.
Git workflow tools beyond the basics
Better diffs, mob programming, parallel worktrees, multi-repo management, and TUI commit graphs - the git tools worth knowing past `git rebase`.
Related entries
Destructive Command Guard
Rust CLI that blocks dangerous git and shell commands before an agent can run them. Pattern-matched safety net for autonomous coding agents.
mcp-shodan - Shodan MCP server for AI agents
MCP server exposing Shodan APIs for IP reconnaissance, DNS lookups, and CVE/CPE vulnerability intelligence. Plugs into Claude Code, Codex, Gemini CLI, and Claude Desktop.
onecli - credential vault for AI agents
Open-source credential vault that gives AI agents access to third-party services without exposing raw API keys. MCP integration for Claude Code and similar agents.
skill-doctor - inspector for coding-agent skills
Local tool that audits installed agent skills for conflicts, precedence issues, and risk. Helps surface why a particular skill is (or isn't) firing.