inbox
01Command
Check and respond to inter-agent messages.
16 tagged code agent, measured the same way as everything else here.
Browse within: Evaluation 10harness 10
Command
Check and respond to inter-agent messages.
Command
Register this session as a named agent for inter-agent communication.
Command
Enable, disable, or configure voice feedback.
Command Claude Code
First-run ritual for new agents.
Command Claude Code
Time to organize your memory.
redhat-community-ai-tools/harness-eval
Command Cursor
Gate the agent setup on corpus-validated rules (gating tier). Fast, no LLM, exits nonzero on any finding. Suitable for CI and pre-commit.
redhat-community-ai-tools/harness-eval
Command Cursor
Full qualitative review of the agent setup. Read every file, evaluate quality, redundancy, and optimization opportunities. Produce KEEP/REVIEW/REMOVE verdicts per component.
redhat-community-ai-tools/harness-eval
Command Cursor
Deep-evaluate a single skill with static analysis and qualitative review, both individually and in context of the full setup.