BigHugger
sk Skill · templetongroup

agent-architecture-audit

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature. Use when an agent or LLM feature misbehaves and the failing…

installs 8w
0
30-day movement
starts with the next reading
Related entries
3
Connections
6
jsonbashJavaScript
Host repository
templetongroup/radiant
Allowed tools
Read, Write, Edit, Bash, Grep, Glob
Host stars
96
Host language
JavaScript