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 Clientell-Ai/salesforce-skills --skill sf-soqlgit clone --depth 1 https://github.com/Clientell-Ai/salesforce-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/clientell-ai/salesforce-skills/sf-soql)<a href="https://agentmods.dev/skills/clientell-ai/salesforce-skills/sf-soql"><img src="https://agentmods.dev/badge/skills/clientell-ai/salesforce-skills/sf-soql/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/clientell-ai/salesforce-skills/sf-soql"><img src="https://agentmods.dev/badge/skills/clientell-ai/salesforce-skills/sf-soql.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 | $0.00078 | $0.02009 |
| Opus 5 | $0.00039 | $0.01005 |
| Sonnet 5 | $0.00016 | $0.00402 |
| Haiku 4.5 | $0.00008 | $0.00201 |
Grade A, and why
sf-soql 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SOQL Query Builder & Optimizer
You are a Salesforce SOQL specialist. Build optimized, secure queries.
Security First
- ALWAYS use
WITH USER_MODEto enforce CRUD/FLS - NEVER use string concatenation for dynamic SOQL — use bind variables
- Use
Database.query()only when dynamic queries are truly needed
// GOOD
List<Account> accounts = [
SELECT Id, Name, Industry
FROM Account
WHERE Industry = :industryFilter
WITH USER_MODE
LIMIT 200
];
// BAD — injection risk
String query = 'SELECT Id FROM Account WHERE Name = \'' + userInput + '\'';
Query Patterns
Parent-to-Child (Subquery)
SELECT Id, Name,
(SELECT Id, FirstName, LastName FROM Contacts)
FROM Account
WHERE Industry = 'Technology'
WITH USER_MODE
Child-to-Parent (Dot Notation)
SELECT Id, FirstName, Account.Name, Account.Industry
FROM Contact
WHERE Account.Industry = 'Technology'
WITH USER_MODE
Aggregate Queries
SELECT Industry, COUNT(Id) cnt, SUM(AnnualRevenue) totalRevenue
FROM Account
WHERE Industry != null
WITH USER_MODE
GROUP BY Industry
HAVING COUNT(Id) > 5
ORDER BY COUNT(Id) DESC
Polymorphic (TYPEOF)
SELECT Id, Subject,
TYPEOF What
WHEN Account THEN Name, Industry
WHEN Opportunity THEN Name, StageName, Amount
END
FROM Task
WITH USER_MODE
Semi-Joins and Anti-Joins
-- Semi-join: Accounts WITH contacts
SELECT Id, Name FROM Account
WHERE Id IN (SELECT AccountId FROM Contact)
WITH USER_MODE
-- Anti-join: Accounts WITHOUT opportunities
SELECT Id, Name FROM Account
WHERE Id NOT IN (SELECT AccountId FROM Opportunity)
WITH USER_MODE
SOSL (Search Language)
Use SOSL for full-text search across multiple objects:
FIND {SearchTerm} IN ALL FIELDS
RETURNING Account(Id, Name WHERE Industry = 'Tech'),
Contact(Id, FirstName, LastName)
LIMIT 20
- Use SOSL when: searching text across objects, fuzzy matching, partial words
- Use SOQL when: exact matches, relationship queries, aggregates, DML-related queries
- Governor limit: 20 SOSL queries per transaction
What ships with it
1 file 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.
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 · 230 lines · 78 tokens per session scan A a4339dc7ce66
sf-soql is a skill published in the GitHub repository Clientell-Ai/salesforce-skills (15 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 78 tokens to every session and 2,009 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 2026-08-30.
Other skills, from other repositories
bmob-database-javascript
A JavaScript guide for using Bmob, a hosted NoSQL database service, from browsers, servers, and several cross-platform app environments. It uses Bmob's newer hydrogen-js-sdk and covers data, users, files, and related records.
bmob-database-restful
Use when interacting with Bmob backend cloud over plain HTTP / curl from ANY language that lacks a Bmob SDK — Python (requests/httpx), Go (net/http), PHP (Guzzle), C# (HttpClient), Rust (reqwest), Ruby, Java backend, Bash, Deno, server-side scripting, data migration. Also use when the user explicitly wants curl or the…
bmob
A guide for using Bmob, a backend-as-a-service platform that provides hosted databases, users, files, cloud functions, messaging, and other server features. It routes tasks to platform-specific instructions for JavaScript, Android, iOS, Flutter, and other clients.
mako-neighborhoods
TRIGGER when: user wants entity-wide context for a table, route, or RPC -- schema + RLS + readers + writers + downstream touches all at once. Covers tableneighborhood, routecontext, rpcneighborhood.
bmob-mcp
Use when the user has the Bmob MCP server configured (http://mcp.bmobapp.com/mcp) and wants to perform LIVE operations against their Bmob backend cloud project from the IDE. Triggers: 'list bmob tables', 'show bmob schema', 'create bmob table', 'add a row to bmob', 'update bmob record', 'delete bmob data', '生成 bmob…
django-patterns
Django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps.