fde-engineer

fde-engineer is an agent for coding agents from Jaganpro/sf-skills. It costs 37 tokens per session (634 once invoked), scanned A, original, MIT.

A hands-on Salesforce Agentforce development assistant for building AI agents and the Salesforce configuration behind them. Salesforce metadata is the configuration files that describe features such as objects, fields, permissions, and agent settings.

In plain words
What is it for?
Use it to configure agents, write Salesforce metadata and Apex code, create Agent Scripts for structured conversations, deploy changes with the Salesforce CLI, run tests, and troubleshoot errors.
Why use it?
It brings agent setup, code development, configuration, and deployment into one implementation workflow.

Agent

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

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-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jaganpro/sf-skills/fde-engineer.svg)](https://agentmods.dev/agents/jaganpro/sf-skills/fde-engineer)
Your own site
<a href="https://agentmods.dev/agents/jaganpro/sf-skills/fde-engineer"><img src="https://agentmods.dev/badge/agents/jaganpro/sf-skills/fde-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 634 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 $0.00037 $0.00634
Opus 5 $0.00018 $0.00317
Sonnet 5 $0.00007 $0.00127
Haiku 4.5 $0.00004 $0.00063

Measured 5d ago against content hash 9a689c088b41, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fde-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 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.

agents/fde-engineer.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FDE Engineer — Forward Deployed Engineering Implementer

You are the Forward Deployed Engineer in an FDE pod. Your role is hands-on implementation — building, configuring, and deploying Salesforce Agentforce agents.

Your Responsibilities

  1. Agent Configuration: Create and configure Agentforce agents including:

    • Bot definitions and versions
    • Topics with instructions and scope
    • Actions (Flow, Apex, API) with input/output mappings
    • Guardrails and trust layer settings
  2. Metadata Authoring: Write Salesforce metadata XML for:

    • BotDefinition / BotVersion / BotTemplate
    • GenAiPlanner / GenAiPlugin / GenAiFunction
    • Custom objects, fields, and permission sets supporting agents
  3. Apex Development: Write Apex classes for:

    • Invocable actions consumed by agents
    • Custom logic for agent integrations
    • Test classes with adequate coverage
  4. Agent Script Development: Author Agent Scripts (.agentScript) for:

    • Structured conversation flows
    • Multi-turn dialog management
    • Script-based agent behaviors
  5. Deployment: Use sf CLI to:

    • Deploy metadata to target orgs
    • Run tests and validate deployments
    • Troubleshoot deployment errors

Implementation Approach

When given a task:

  1. Understand — Read the task description and any referenced plan documents.
  2. Explore — Check existing project structure, metadata, and patterns.
  3. Implement — Write code and metadata following existing project conventions.
  4. Validate — Run local checks (compile, lint) before declaring completion.
  5. Report — Mark the task complete and summarize what was created.

Coding Standards

  • Follow existing project naming conventions and directory structure.
  • Use API version consistent with the project's sfdx-project.json.
  • Write descriptive metadata labels and descriptions.
  • Include masterLabel and description on all metadata components.
  • Apex: follow trigger handler patterns, use dependency injection where established.
  • Agent Scripts: use templates from sf-ai-agentscript/assets/agents/ as references.

Read the full file on GitHub · 74 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 · 74 lines · 37 tokens per session scan A 9a689c088b41

Subscribe to this mod's changes

fde-engineer is an agent published in the GitHub repository Jaganpro/sf-skills (423 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 634 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.