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 hamzabellouch/agent-skills --skill salesforce-apex-lwc-devgit clone --depth 1 https://github.com/hamzabellouch/agent-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/hamzabellouch/agent-skills/salesforce-apex-lwc-dev)<a href="https://agentmods.dev/skills/hamzabellouch/agent-skills/salesforce-apex-lwc-dev"><img src="https://agentmods.dev/badge/skills/hamzabellouch/agent-skills/salesforce-apex-lwc-dev/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/hamzabellouch/agent-skills/salesforce-apex-lwc-dev"><img src="https://agentmods.dev/badge/skills/hamzabellouch/agent-skills/salesforce-apex-lwc-dev.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 | $0.00041 | $0.01612 |
| Opus 5 | $0.00020 | $0.00806 |
| Sonnet 5 | $0.00008 | $0.00322 |
| Haiku 4.5 | $0.00004 | $0.00161 |
Grade A, and why
salesforce-apex-lwc-dev 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 7d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Salesforce Apex & Lightning Web Components (LWC) Development
Overview
This skill provides production-grade architectural patterns for Salesforce core customization. It covers Apex Trigger frameworks, Governor Limits bulkification, Lightning Web Components (LWC) wire adapters, SOQL/SOSL performance tuning, security stripping (Security.stripInaccessible), and unit testing with high coverage requirements (>85%).
1. Core Salesforce Architecture Principles
- Trigger Framework Pattern: Never write raw business logic directly inside Apex trigger blocks. Use a single trigger per object that delegates execution to a structured Handler class adhering to context methods (
beforeInsert,afterUpdate). - Bulkification by Default: All Apex code must handle collections of records (
List<SObject>). Never issue SOQL queries or DML statements (insert,update,delete) insideforloops. - Strict Governor Limits Compliance: Respect SOQL query limits (100 per transaction), DML statements (150 per transaction), and Heap Size limits (6MB synchronous / 12MB asynchronous).
- Field-Level Security (FLS) & Object Permissions: Always enforce CRUD/FLS checks before mutating or querying data using
WITH USER_MODEorSecurity.stripInaccessible(). - LWC Reactive Data Binding & LDS: Prefer Lightning Data Service (
lightning-record-form,@wire) over imperative Apex calls for UI components to leverage automatic client-side cache management.
2. Salesforce Execution Architecture
[ LWC UI Component ] ──(Wire Adapter / Imperative Call)
│
│ 1. Client-side Controller (JS)
▼
[ Apex Controller Class ] ──(Security.stripInaccessible / USER_MODE)
│
│ 2. DML Execution
▼
[ Apex Trigger Handler ] ──(Bulkified Collections)──▶ [ SOQL Database Layer ]
| Salesforce Mechanism | Best Practice / Pattern | Key Limit / Metric |
|---|---|---|
| Apex Triggers | 1 Trigger Per Object + Trigger Handler Framework | 200 records per chunk execution |
| SOQL Queries | Index indexed fields (External ID, Id, Lookup); Use WITH USER_MODE |
Max 100 queries / 50,000 rows fetched |
| DML Operations | Aggregate list mutations before single Database.insert() call |
Max 150 DML statements per transaction |
| Asynchronous Apex | @future, Queueable, Batchable for long-running processes |
50 concurrent Queueable jobs limit |
| LWC State Engine | @track for deep object properties; @wire for automated reactivity |
Reactive property cache client-side |
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.
- 7d ago First seen · 171 lines · 41 tokens per session scan A 089d968d0dd1
salesforce-apex-lwc-dev is a skill published in the GitHub repository hamzabellouch/agent-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 1,612 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
api-integration
When connecting a component to a REST API, handling loading/error states, or implementing optimistic updates.
websockets
WebSockets real-time bidirectional communication. Use for real-time features.
sse
Server-Sent Events one-way real-time. Use for live updates.
remix
Remix React framework with nested routing and data loading. Use for full-stack React.
sveltekit
SvelteKit full-stack Svelte framework with SSR and routing. Use for Svelte applications.
nuxt
Nuxt.js Vue framework with SSR and auto-imports. Use for full-stack Vue applications.