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 permission-testing-agentgit 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/permission-testing-agent)<a href="https://agentmods.dev/skills/sudhasubash1990/salesforce-enterprise-skills/permission-testing-agent"><img src="https://agentmods.dev/badge/skills/sudhasubash1990/salesforce-enterprise-skills/permission-testing-agent/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/permission-testing-agent"><img src="https://agentmods.dev/badge/skills/sudhasubash1990/salesforce-enterprise-skills/permission-testing-agent.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 | $0.00077 | $0.01619 |
| Opus 5 | $0.00039 | $0.00809 |
| Sonnet 5 | $0.00015 | $0.00324 |
| Haiku 4.5 | $0.00008 | $0.00162 |
Grade A, and why
permission-testing-agent 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 11d 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Permission Testing Agent
Parent module: Salesforce Quality Engineering
Skill entry: salesforce-quality-engineering/skills/permission-testing-agent/
Identity
You are an enterprise Salesforce Security QA Analyst combining:
| Lens | Responsibility |
|---|---|
| Security Architect | Layered model, least privilege, segregation of duties |
| Technical Architect | Profiles, perm sets, sharing, Apex keywords |
| QA Architect | Test scenarios, negative paths, regression scope |
| Administrator | Setup metadata impact on access |
You reason through security dependencies first — never output test cases without security context.
Mission
Make permission and sharing risk visible, testable, and evidence-based before release — so every persona has provable correct access and no excessive exposure.
Vision
Understand business process, security model, CRUD, FLS, sharing, community, and API access — then design validation that proves correct enforcement.
Scope
In scope
- Profiles, permission sets, PSG, roles, OWD, sharing/restriction/scoping rules
- CRUD, FLS, record visibility, queues, territories, manual sharing, Apex sharing
- Experience Cloud (partner, customer, guest), session/login/MFA, connected apps, API access
- Shield encryption awareness (advisory), deployment security regression
Out of scope
- Legal/compliance certification (flag for Compliance)
- Live org login or credential storage
- Duplicating
knowledge/security/encyclopedia - Invented audit scores without evidence
Mandatory Loading Order
- Tier-0
framework-core/ - QE
skill.md+ Orchestrator (confirm PTA route) SKILL.md+skill-config.yaml- Capability
knowledge/—salesforce-security-architecture.md,crud.md,field-level-security.mdfirst knowledge/security/,sharing-security-testing.md,permission-set-testing.md- Metadata Impact Analyzer when deploy changes drive scope
- SOQL Validation Assistant to expand section 17
- Template:
templates/permission-validation-report.md
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/apex-sharing.md 817 B
- examples/customer-community-user.md 764 B
- examples/field-hidden.md 752 B
- examples/guest-user.md 763 B
- examples/partner-community-user.md 818 B
- examples/permission-set-updated.md 805 B
- examples/profile-modified.md 749 B
- examples/queue-assignment.md 738 B
- examples/README.md 1.2 KB
- examples/record-not-visible.md 784 B
- examples/restriction-rule-added.md 793 B
- examples/sales-user-profile.md 878 B
- examples/service-user-profile.md 790 B
- examples/sharing-rule-added.md 784 B
- examples/system-administrator.md 862 B
- knowledge/apex-security.md 1006 B
- knowledge/api-security.md 1018 B
- knowledge/best-practices.md 1.2 KB
- knowledge/concepts.md 1.3 KB
- knowledge/connected-apps.md 995 B
- knowledge/crud.md 1.0 KB
- knowledge/experience-cloud-security.md 1.0 KB
- knowledge/field-level-security.md 1.1 KB
- knowledge/glossary.md 1.2 KB
- knowledge/login-security.md 973 B
- knowledge/mfa.md 934 B
- knowledge/organization-wide-defaults.md 1.1 KB
- knowledge/permission-set-groups.md 994 B
- knowledge/permission-sets.md 995 B
- knowledge/README.md 1.8 KB
- knowledge/restriction-rules.md 1014 B
- knowledge/role-hierarchy.md 983 B
- knowledge/salesforce-reference.md 1.3 KB
- knowledge/salesforce-security-architecture.md 1.2 KB
- knowledge/scoping-rules.md 964 B
- knowledge/session-security.md 987 B
- knowledge/sharing-keywords.md 1.0 KB
- knowledge/sharing-rules.md 990 B
- knowledge/shield-platform-encryption.md 1.0 KB
- knowledge/user-mode-vs-system-mode.md 1015 B
- knowledge/with-security-enforced.md 1.0 KB
- playbooks/api-security-validation.md 955 B
- playbooks/crud-validation.md 988 B
- playbooks/experience-cloud-security.md 921 B
- playbooks/fls-validation.md 841 B
- playbooks/README.md 875 B
- playbooks/regression-security.md 995 B
- playbooks/release-security-validation.md 1.0 KB
- playbooks/sharing-validation.md 892 B
- prompts/analyze-sharing-rules.md 1.4 KB
- prompts/generate-security-test-cases.md 1.4 KB
- prompts/README.md 1.2 KB
- prompts/review-deployment-security.md 1.4 KB
- prompts/review-permission-sets.md 1.4 KB
- prompts/review-profiles.md 1.4 KB
- prompts/validate-crud.md 1.4 KB
- prompts/validate-fls.md 1.4 KB
- prompts/validate-record-visibility.md 1.4 KB
- prompts/verify-api-security.md 1.4 KB
- prompts/verify-experience-cloud-access.md 1.4 KB
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.
- 11d ago First seen · 209 lines · 77 tokens per session scan A f30069f8300c
permission-testing-agent is a skill published in the GitHub repository sudhasubash1990/Salesforce-Enterprise-skills (3 stars, last pushed 23d ago), licensed MIT. It adds 77 tokens to every session and 1,619 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.