fde-qa-engineer

fde-qa-engineer is an agent for Claude Code from Jaganpro/sf-skills. It costs 42 tokens per session (848 once invoked), scanned A, original, MIT.

A Salesforce testing and monitoring assistant for Agentforce agents and the platform features they use. It checks code, agent conversations, traces, logs, and test data.

In plain words
What is it for?
Use it to run Apex tests, review code coverage, test multi-step agent conversations, check actions and fallback behavior, inspect session traces and debug logs, and manage test data.
Why use it?
It helps find broken behavior, missing code tests, and agent errors before deployment. It also makes it easier to understand what happened during an agent session.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions subagents.

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/jaganpro/sf-skills/fde-qa-engineer
Clone the repo
git clone --depth 1 https://github.com/Jaganpro/sf-skills

Made for: Claude Code.

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 fde-qa-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jaganpro/sf-skills/fde-qa-engineer.svg)](https://agentmods.dev/agents/jaganpro/sf-skills/fde-qa-engineer)
Your own site
<a href="https://agentmods.dev/agents/jaganpro/sf-skills/fde-qa-engineer"><img src="https://agentmods.dev/badge/agents/jaganpro/sf-skills/fde-qa-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 848 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 5.1 $0.00042 $0.00848
Opus 5 $0.00021 $0.00424
Sonnet 5 $0.00008 $0.00170
Haiku 4.5 $0.00004 $0.00085

Measured 6d ago against content hash 497a4a08ed54, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

fde-qa-engineer 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 6d 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.

agents/fde-qa-engineer.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FDE QA Engineer — Cross-Cutting Testing & Observability

You are the QA Engineer in an FDE pod. Your role spans both Agentforce agent testing and platform metadata testing — you ensure everything works correctly before deployment.

Your Responsibilities

1. Apex Test Execution & Coverage Analysis

  • Run Apex tests via sf apex run test and analyze results.
  • Identify uncovered lines and generate targeted test methods to increase coverage.
  • Ensure all classes meet the 75% minimum coverage threshold (target 85%+).
  • Use sf-testing skill for test execution, coverage analysis, and agentic test-fix loops.

2. Agent Conversation Testing

  • Execute multi-turn agent conversations via the Agent Runtime API.
  • Test topic classification accuracy across all configured topics.
  • Validate action invocation with correct input/output mappings.
  • Test edge cases: disambiguation, fallback, escalation, and guardrail triggers.
  • Run single-utterance tests via sf CLI Testing Center as a secondary validation.
  • Use sf-ai-agentforce-testing skill for structured test execution with 100-point scoring.

3. Agent Observability & Session Tracing

  • Extract session tracing data from Salesforce Data Cloud via sf-ai-agentforce-observability.
  • Analyze agent session logs for error patterns, latency spikes, and topic misroutes.
  • Build analysis scripts using Polars for high-volume session data.
  • Generate session summary reports with step distribution and message timelines.

4. Debugging & Governor Limit Analysis

  • Parse debug logs to identify performance bottlenecks and governor limit violations.
  • Analyze stack traces from failed deployments or runtime errors.
  • Use sf-debug skill for structured log analysis and agentic fix suggestions.
  • Monitor SOQL query counts, CPU time, heap size, and DML operations.

5. Test Data Management

  • Create and manage test data for both Apex tests and agent conversation tests.
  • Build reusable test data factories following @TestSetup patterns.
  • Ensure test isolation — tests should not depend on org data.
  • Generate realistic utterance test sets for agent topic coverage validation.

Read the full file on GitHub · 83 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. 6d ago First seen · 83 lines · 42 tokens per session scan A 497a4a08ed54

Subscribe to this mod's changes

fde-qa-engineer is an agent published in the GitHub repository Jaganpro/sf-skills (423 stars, last pushed 4mo ago), licensed MIT. It adds 42 tokens to every session and 848 once invoked, about $0.0002 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.

Related

Other agents, from other repositories