agentforce-testing

agentforce-testing is a skill for Claude Code, Codex from sudhasubash1990/Salesforce-Enterprise-skills. It costs 72 tokens per session (1,645 once invoked), scanned A, original, MIT.

A testing skill for Salesforce Agentforce, which provides AI agents that answer users and perform actions through connected tools.

In plain words
What is it for?
Use it to test prompts, topics, knowledge grounding, multi-turn conversations, escalation, guardrails, hallucination risk, and actions performed through Flow, Apex, or APIs.
Why use it?
It checks whether agents are accurate, grounded in trusted information, safe, and correct when using tools or changing data.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to test prompts, topics, knowledge grounding, multi-turn conversations, escalation, guardrails, hallucination risk, and actions performed through Flow, Apex, or APIs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sudhasubash1990/salesforce-enterprise-skills/agentforce-testing
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.

Any agent
npx skills add sudhasubash1990/Salesforce-Enterprise-skills --skill agentforce-testing
Clone the repo
git clone --depth 1 https://github.com/sudhasubash1990/Salesforce-Enterprise-skills

Made for: Claude Code, Codex.

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 agentforce-testing

README.md
[![agentmods](https://agentmods.dev/badge/skills/sudhasubash1990/salesforce-enterprise-skills/agentforce-testing/github.svg)](https://agentmods.dev/skills/sudhasubash1990/salesforce-enterprise-skills/agentforce-testing)
Your own site
<a href="https://agentmods.dev/skills/sudhasubash1990/salesforce-enterprise-skills/agentforce-testing"><img src="https://agentmods.dev/badge/skills/sudhasubash1990/salesforce-enterprise-skills/agentforce-testing/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for agentforce-testing

Your own site · 80×15
<a href="https://agentmods.dev/skills/sudhasubash1990/salesforce-enterprise-skills/agentforce-testing"><img src="https://agentmods.dev/badge/skills/sudhasubash1990/salesforce-enterprise-skills/agentforce-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,645 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00072 $0.01645
Opus 5 $0.00036 $0.00822
Sonnet 5 $0.00014 $0.00329
Haiku 4.5 $0.00007 $0.00164

Measured 12d ago against content hash 0905c7e29f51, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

agentforce-testing 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 12d 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.

salesforce-quality-engineering/skills/agentforce-testing/SKILL.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentforce Testing

Parent module: Salesforce Quality Engineering
Skill entry: salesforce-quality-engineering/skills/agentforce-testing/


Identity

You combine:

Lens Responsibility
Agentforce Architect Agent, topics, actions, configuration
AI QA Architect Evaluation rubric, conversation quality
Prompt Engineer Prompt adherence and safety
Solution / Technical Architect Flow/Apex/API side effects
Enterprise Test Architect Regression, release readiness

You validate AI behavior — not only UI clicks.


Mission

Make Agentforce quality visible, testable, and evidence-based so agents are accurate, grounded, safe, and business-correct before production enablement.


Vision

Every agent response is evaluated for accuracy, grounding, tool correctness, guardrails, and hallucination risk. Every mutating action is traced to impact, SOQL, and permission validation.


Scope

In scope

  • Agentforce agents, topics, instructions, prompt templates, actions (Flow, Apex, API)
  • Knowledge grounding, retrieval, conversation context, multi-turn, escalation
  • Guardrails, PII/safety, hallucination detection, response quality evaluation
  • Regression and release readiness for AI agents

Out of scope

  • Live LLM/org execution or credentials
  • Full automation scripts (Sprint 8 design only)
  • Invented confidence %, RAG accuracy %, or compliance certifications
  • Duplicating knowledge/clouds/agentforce.md encyclopedia body

Supported Components

Agents · Topics · Instructions · Prompt Templates · Actions · Flow/Apex/External Actions · Knowledge Grounding · Session Memory · Tool Invocation · Escalation · Guardrails · Monitoring signals (advisory)


QA Responsibilities

Prompt testing · Topic classification · Intent recognition · Response accuracy · Context retention · Tool/Flow/Apex/API invocation · Grounding · Hallucination · Guardrails · Security/PII · Human escalation · Multi-turn · Failure recovery · Regression · Release validation

Read the full file on GitHub · 214 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 214 lines · 72 tokens per session scan A 0905c7e29f51

Subscribe to this mod's changes

agentforce-testing is a skill published in the GitHub repository sudhasubash1990/Salesforce-Enterprise-skills (3 stars, last pushed 23d ago), licensed MIT. It adds 72 tokens to every session and 1,645 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens

atmos-validation

Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.

cloudposse/atmos · 31 tokens

skill-benchmark

Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.

HoangNguyen0403/agent-skills-standard · 16 tokens