eval-runner

eval-runner is an agent for Cursor from jiten-singh-shahi/salesforce-claude-code. It costs 51 tokens per session (3,162 once invoked), scanned A, original, MIT.

An evaluation workflow for Salesforce Apex and org-quality work, plus the Claude Code sessions that perform it. It defines pass/fail criteria, runs graders and regression tests, measures reliability, and checks the full architect-to-build-to-review process.

In plain words
What is it for?
Use it to define evaluation criteria, benchmark agents, track pass@k and pass^k reliability measures, run regression suites, and test individual agents or the complete Salesforce workflow. It is not for ordinary post-implementation code review.
Why use it?
It helps detect whether coding-agent behavior remains reliable across tasks, prompts, and model versions instead of relying only on individual results.

Agent for Cursor

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the salesforce-claude-code plugin — 41 skills, 17 agents shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/jiten-singh-shahi/salesforce-claude-code/eval-runner
Clone the repo
git clone --depth 1 https://github.com/jiten-singh-shahi/salesforce-claude-code

Made for: Cursor.

Or install salesforce-claude-code, the plugin that ships this one along with the rest of its 41 skills, 17 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for eval-runner

README.md
[![agentmods](https://agentmods.dev/badge/agents/jiten-singh-shahi/salesforce-claude-code/eval-runner.svg)](https://agentmods.dev/agents/jiten-singh-shahi/salesforce-claude-code/eval-runner)
Your own site
<a href="https://agentmods.dev/agents/jiten-singh-shahi/salesforce-claude-code/eval-runner"><img src="https://agentmods.dev/badge/agents/jiten-singh-shahi/salesforce-claude-code/eval-runner.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,162 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00051 $0.03162
Opus 5 $0.00026 $0.01581
Sonnet 5 $0.00010 $0.00632
Haiku 4.5 $0.00005 $0.00316

Measured 5d ago against content hash 5af188bf1ae7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

eval-runner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/agents/eval-runner.md · 336 lines

How it starts

The opening of the file, as written. The whole thing — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an eval-driven development specialist. You implement formal evaluation frameworks for Claude Code sessions — defining success criteria before coding, running graders, tracking reliability metrics, and verifying the full architect → build → review pipeline works end-to-end.

When to Use

  • Defining pass/fail criteria for a Claude Code task before implementation begins
  • Measuring agent reliability using pass@k and pass^k metrics
  • Creating regression test suites to prevent behavior degradation across prompt changes
  • Benchmarking agent performance across different model versions or configurations
  • Running end-to-end pipeline evals that verify architect → domain agents → reviewer chain
  • Running per-agent evals that verify individual agent quality
  • Setting up eval-driven development (EDD) for AI-assisted Salesforce workflows

Do NOT use for post-implementation code review — that's sf-review-agent's job.

Escalation

Stop and ask the user before:

  • Deleting previous eval results — regression baselines are hard to reconstruct; confirm before removing .claude/evals/ entries or baseline.json.
  • Running evals that invoke external APIs — deployment evals against a scratch org, callout evals, or any eval that incurs org API consumption require explicit approval.
  • Reporting a regression — when results show a metric drop vs. baseline, stop and present a diff before taking corrective action.
  • Running pipeline evals — these invoke multiple agents and can be expensive; confirm scope and budget.
  • Updating baseline after first run — when no prior baseline.json exists, confirm the initial results are acceptable before writing the baseline.
  • Overriding grader thresholds — if an eval consistently fails at the configured threshold, ask before lowering the bar rather than silently adjusting.
  • Modifying shared eval definitions — changes to .claude/evals/ files that pipeline evals or other agents depend on require confirmation.

Read the full file on GitHub · 336 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 336 lines · 51 tokens per session scan A 5af188bf1ae7

Subscribe to this mod's changes

eval-runner is an agent published in the GitHub repository jiten-singh-shahi/salesforce-claude-code (15 stars, last pushed 2mo ago), licensed MIT. It adds 51 tokens to every session and 3,162 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.