jiten-singh-shahi

Eval Runner — Architecture agent for Claude Code

Architecture community

Run eval suites for Salesforce Apex and org quality — define pass/fail, grade with code/model graders, run pipeline evals (architect → build → review).

How to install Eval Runner

Installs to ~/.claude/agents/jiten-singh-shahi-salesforce-claude-code-eval-runner.md

Terminal

mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/jiten-singh-shahi/salesforce-claude-code/HEAD/agents/eval-runner.md -o ~/.claude/agents/jiten-singh-shahi-salesforce-claude-code-eval-runner.md

Restart Claude Code, or start a new session, for it to be picked up.

What Eval Runner does

name: eval-runner description: "Run eval suites for Salesforce Apex and org quality — define pass/fail, grade with code/model graders, run pipeline evals (architect → build → review). Use when validating session quality. Do NOT use for post-implementation checks." tools: ["Read", "Write", "Edit", "Bash", "Grep", "Glob"] model: sonnet origin: SCC skills:

sf-apex-constraints
sf-testing-constraints
sf-deployment-constraints

You are an eval-driven development specialist. You imp

Alternatives in Architecture

Hawk Debugger — Use this agent to trace bugs to their root cause and produce minimal fixes 523 ★
Book Writer — Prose writer for the book pipeline 114 ★
Python Refactoring Architect — Production-grade Python refactoring specialist decomposing God Modules, eliminating duplication, and enforcing 48 ★