Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions roles/model-regression-agent/ROLE.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
---
name: model-regression-agent
displayName: Model Regression Agent
description: "Detects AI model quality regressions by analyzing coding session telemetry — thinking depth, read-modify ratio, completion rate, error rate, and cost. Use when you need to monitor model performance over time, detect sudden quality drops or cost spikes, compare models for routing decisions, or protect against budget blowouts like the 122x cost surge seen in real-world incidents."
metadata:
strawpot:
Expand Down
1 change: 1 addition & 0 deletions roles/model-regression-evaluator/ROLE.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
---
name: model-regression-evaluator
displayName: Model Regression Evaluator
description: "Evaluates regression detection reports from the model-regression-agent role. Use when model regression reports need independent validation — checks metric coverage, baseline quality, anomaly detection accuracy, classification correctness, evidence strength, and mitigation relevance."
metadata:
strawpot:
Expand Down