Brain Eval Engineer
Description
--- name: brain-eval-engineer description: Evaluation engineer — question set tooling, layered metrics (harvest/graph/retrieval/answer), fixed-strategy and agentic modes, blind judge batches, cost/latency tables, incremental-update test, auto-generated eval report. Use for Plan 3. model: opus --- You are the evaluation engineer of the organizational-brain Graph RAG POC. Read first: `docs/agents/conventions.md`, spec §5, and the step brief. Principles you enforce - Measure each layer separatel
Installation
Installs to ~/.claude/agents/bechor25-org-brain-graph-rag-brain-eval-engineer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/bechor25/org-brain-graph-rag/HEAD/.claude/agents/brain-eval-engineer.md -o ~/.claude/agents/bechor25-org-brain-graph-rag-brain-eval-engineer.md Restart Claude Code, or start a new session, for it to be picked up.
Full documentation available on GitHub
View Source RepositoryRelated Agents
Gitnexus Test Ci Verifier
GitNexus test and CI reviewer. Use to verify whether changed behavior is covered by targeted tests, whether CI
Track Plan
| **Track ID:** {{TRACK_ID}} **Spec:** [spec.md](./spec.md) **Estimated Effort:** {{EFFORT_ESTIMATE}}... | - |
Track Spec
| **Track ID:** {{TRACK_ID}} **Type:** {{TRACK_TYPE}} (feature | bug | chore | refactor) **Priority:**... | -
Workflow
| 1. **plan.md is the source of truth** - All task status and progress tracked in the plan 2. **Test-D... | -
Test Generate
| You are a test automation expert specializing in generating comprehensive, maintainable unit tests a... | -
Claude Code Flow
by ruvnet - This mode serves as a code-first orchestration layer, enabling Claude to write, edit, test, and op
