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.
npx skills add sudhasubash1990/Salesforce-Enterprise-skills --skill agentforce-testinggit clone --depth 1 https://github.com/sudhasubash1990/Salesforce-Enterprise-skillsWrote 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.
[](https://agentmods.dev/skills/sudhasubash1990/salesforce-enterprise-skills/agentforce-testing)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.mdencyclopedia 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
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.
- examples/appointment-scheduling-agent.md 927 B
- examples/case-resolution-agent.md 1.0 KB
- examples/customer-service-agent.md 1.1 KB
- examples/hr-support-agent.md 928 B
- examples/internal-employee-agent.md 987 B
- examples/it-help-desk-agent.md 959 B
- examples/knowledge-assistant.md 944 B
- examples/lead-qualification-agent.md 960 B
- examples/README.md 999 B
- examples/sales-agent.md 999 B
- examples/utility-billing-agent.md 1002 B
- knowledge/actions.md 1.0 KB
- knowledge/agent-lifecycle.md 1.1 KB
- knowledge/agent-monitoring.md 1.0 KB
- knowledge/agentforce-architecture.md 1.2 KB
- knowledge/ai-guardrails.md 1.0 KB
- knowledge/ai-testing-best-practices.md 1.1 KB
- knowledge/apex-actions.md 1.0 KB
- knowledge/best-practices.md 1.2 KB
- knowledge/concepts.md 1.2 KB
- knowledge/conversation-design.md 991 B
- knowledge/external-integrations.md 1.0 KB
- knowledge/flow-actions.md 1.0 KB
- knowledge/glossary.md 1.2 KB
- knowledge/hallucination-mitigation.md 982 B
- knowledge/human-escalation.md 991 B
- knowledge/knowledge-grounding.md 1.0 KB
- knowledge/multi-turn-conversations.md 998 B
- knowledge/prompt-engineering.md 988 B
- knowledge/prompt-templates.md 1.1 KB
- knowledge/README.md 1.7 KB
- knowledge/responsible-ai.md 1.0 KB
- knowledge/retrieval-strategies.md 1.1 KB
- knowledge/salesforce-reference.md 1.2 KB
- knowledge/session-context.md 1.0 KB
- knowledge/topics.md 1.0 KB
- playbooks/ai-regression.md 971 B
- playbooks/conversation-testing.md 862 B
- playbooks/grounding-validation.md 864 B
- playbooks/guardrail-validation.md 904 B
- playbooks/hallucination-detection.md 831 B
- playbooks/prompt-validation.md 1.1 KB
- playbooks/README.md 959 B
- playbooks/release-readiness.md 923 B
- playbooks/tool-invocation.md 975 B
- playbooks/topic-validation.md 881 B
- prompts/assess-deployment-readiness.md 1.4 KB
- prompts/detect-hallucinations.md 1.4 KB
- prompts/generate-conversation-tests.md 1.4 KB
- prompts/README.md 1.3 KB
- prompts/review-agent-configuration.md 1.4 KB
- prompts/review-tool-invocation.md 1.4 KB
- prompts/review-topic-classification.md 1.4 KB
- prompts/validate-ai-response.md 1.4 KB
- prompts/validate-guardrails.md 1.4 KB
- prompts/validate-knowledge-grounding.md 1.4 KB
- prompts/validate-prompt-template.md 1.4 KB
- README.md 3.4 KB
- skill-config.yaml 2.7 KB
- templates/agent-release-checklist.md 844 B
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.
- 12d ago First seen · 214 lines · 72 tokens per session scan A 0905c7e29f51
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.
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.
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".
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…
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.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.