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 soql-validation-assistantgit 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/soql-validation-assistant)<a href="https://agentmods.dev/skills/sudhasubash1990/salesforce-enterprise-skills/soql-validation-assistant"><img src="https://agentmods.dev/badge/skills/sudhasubash1990/salesforce-enterprise-skills/soql-validation-assistant/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/soql-validation-assistant"><img src="https://agentmods.dev/badge/skills/sudhasubash1990/salesforce-enterprise-skills/soql-validation-assistant.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 | $0.00074 | $0.02166 |
| Opus 5 | $0.00037 | $0.01083 |
| Sonnet 5 | $0.00015 | $0.00433 |
| Haiku 4.5 | $0.00007 | $0.00217 |
Grade A, and why
soql-validation-assistant scanned grade A with 1 finding 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.
Strips warnings and disclaimerslowAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- [ ] No invented metrics without disclaimer Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SOQL Validation Assistant
Parent module: Salesforce Quality Engineering
Skill entry: salesforce-quality-engineering/skills/soql-validation-assistant/
Identity
You combine Principal Technical Architect, QA Architect, and Data Architect posture to validate Salesforce backend state through purposeful SOQL — never as a syntax generator.
| Lens | Responsibility |
|---|---|
| Business / Process | Tie every query to a validation objective |
| Data Model | Objects, relationships, fields, integrity |
| Security | CRUD, FLS, sharing, run-as context |
| Performance | Selectivity, governors, LDV |
| Release / QE | Smoke, regression, migration, production verification |
Mission
Ensure every SOQL recommendation answers a business validation question with evidence, security awareness, and performance discipline.
Vision
The assistant understands business process, data model, metadata relationships, security, and release context — and explains why a query is required before writing it.
Scope
In scope
- Validation SOQL for functional, backend, migration, integration, automation, report/dashboard, regression, release, smoke, and production verification
- Standard/custom objects, relationships, aggregates, date functions, formula fields, external/big objects (advisory), platform events (where queryable), custom metadata/settings (context)
- Performance and security analysis per query
- Alternative queries and negative validation
Out of scope
- Live org execution or stored credentials
- Full Apex/automation script generation (Sprint 8)
- Duplicating
knowledge/performance/orknowledge/data/encyclopedia bodies - Invented row counts without labeling as illustrative
Supported Query Types
List · Relationship (parent→child subquery, child→parent dot notation) · Aggregate (COUNT, SUM, GROUP BY, HAVING, ROLLUP) · LIMIT/OFFSET · Date literals and functions · Polymorphic (TYPEOF advisory) · Tooling/metadata query patterns (advisory, not live API)
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/account-validation.md 923 B
- examples/bulk-data-validation.md 819 B
- examples/case-validation.md 835 B
- examples/contact-validation.md 868 B
- examples/custom-object-validation.md 799 B
- examples/data-migration-reconciliation.md 841 B
- examples/flow-validation.md 861 B
- examples/integration-verification.md 826 B
- examples/opportunity-validation.md 891 B
- examples/README.md 1.2 KB
- examples/sales-cloud-validation.md 920 B
- examples/service-cloud-validation.md 843 B
- examples/utilities-domain-validation.md 919 B
- examples/validation-rule-verification.md 811 B
- knowledge/aggregate-functions.md 1.1 KB
- knowledge/best-practices.md 997 B
- knowledge/concepts.md 1016 B
- knowledge/date-literals.md 1.0 KB
- knowledge/formula-fields.md 1.0 KB
- knowledge/glossary.md 1011 B
- knowledge/governor-limits.md 1008 B
- knowledge/indexing.md 1015 B
- knowledge/large-data-volumes.md 1.0 KB
- knowledge/metadata-api-queries.md 1.0 KB
- knowledge/polymorphic-relationships.md 1.0 KB
- knowledge/query-best-practices.md 1.1 KB
- knowledge/query-optimization.md 991 B
- knowledge/query-selectivity.md 1.0 KB
- knowledge/README.md 1.6 KB
- knowledge/relationship-queries.md 1.1 KB
- knowledge/salesforce-reference.md 1022 B
- knowledge/security-considerations.md 1.1 KB
- knowledge/soql-fundamentals.md 1.1 KB
- knowledge/tooling-api-queries.md 1.0 KB
- playbooks/backend-validation.md 1015 B
- playbooks/data-migration-validation.md 1.1 KB
- playbooks/functional-validation.md 1.2 KB
- playbooks/integration-validation.md 1.1 KB
- playbooks/README.md 819 B
- playbooks/regression-validation.md 1015 B
- playbooks/release-validation.md 1.0 KB
- prompts/generate-aggregate-queries.md 1.2 KB
- prompts/generate-validation-soql.md 1.1 KB
- prompts/optimize-soql.md 1001 B
- prompts/README.md 1.1 KB
- prompts/review-existing-soql.md 1.2 KB
- prompts/validate-bulk-operations.md 1.2 KB
- prompts/validate-data-migration.md 1.2 KB
- prompts/validate-integration.md 1.2 KB
- prompts/verify-dashboard-data.md 1.2 KB
- prompts/verify-flow-results.md 1.2 KB
- prompts/verify-reports.md 1.2 KB
- README.md 3.7 KB
- skill-config.yaml 2.6 KB
- templates/backend-validation-checklist.md 941 B
- templates/data-verification-report.md 920 B
- templates/query-review-template.md 922 B
- templates/README.md 872 B
- templates/regression-validation-report.md 862 B
- templates/release-validation-checklist.md 881 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 · 255 lines · 74 tokens per session scan A f5d48e109d97
soql-validation-assistant is a skill published in the GitHub repository sudhasubash1990/Salesforce-Enterprise-skills (3 stars, last pushed 24d ago), licensed MIT. It adds 74 tokens to every session and 2,166 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
convex-explain-app
Explain an existing Convex app — data model + relationships, public vs internal functions, auth/ownership model, components, a request→data flow — read from the schema and function surface. Read-only.
platform-custom-field-generate
Use this skill when users need to create, generate, or validate Salesforce Custom Field metadata. Trigger when users mention custom fields, field types, Roll-up Summary fields, Master-Detail relationships, Lookup relationships, formula fields, picklists, dependent (controlling) picklists, referencing a value set from…
field-service-sobject-create-configure
Headless 360 REST API deployment step for creating sObject records. Handles describe-based field discovery, required-field derivation, entity-relationship ordering, and composite graph transactions. Use this skill when a designer skill (or a user directly) needs to create sObject records after design confirmation…
durable-objects
Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.
nornicdb-grpc
Drive NornicDB over gRPC — the Qdrant-compatible surface (Collections, Points, Snapshots) plus the additive NornicSearch service. Use when ingesting via Qdrant SDKs, migrating from Qdrant, or running hybrid text+vector search from a non-Bolt client. Covers connection, RPC catalog, collection→database mapping…