salesforce-claude-code

Multi-source Salesforce research — Apex patterns, org architecture, platform event trade-offs, deploy strategies. Use when investigating complex decisions requiring cited reports. Do NOT use for single doc lookups.

Sync Salesforce project docs with codebase — codemaps, ADRs, data dictionaries, deployment runbooks, ApexDoc. Use when updating docs after sprints or architect planning. Do NOT use for authoring design docs or CLAUDE.md.

Run eval suites for Salesforce Apex and org quality — define pass/fail, grade with code/model graders, run pipeline evals (architect → build → review). Use when validating session quality. Do NOT use for post-implementation checks.

Build learning loops for Salesforce Apex and org development — observe patterns, create confidence-scored instincts, feed insights to sf-architect and sf-review-agent. Use when improving quality over time. Do NOT use for single-session tasks.

Run autonomous loops over Salesforce tasks — iterating Apex refactors, test coverage improvements, deploy validations, or multi-agent pipeline execution with safety gates. Use when running repeated or multi-step tasks. Do NOT use for single-pass.

Use when removing dead Apex code, unused metadata, or duplicate logic from a Salesforce project using PMD with safety tiers (SAFE/CAREFUL/RISKY). Do NOT use before production deploys.

Configure Salesforce org — objects, fields, relationships, permissions, sharing, Custom Metadata, Experience Cloud. Use PROACTIVELY when setting up org config. For new features, use sf-architect first. Do NOT use for Apex, LWC, or Flow.

Build and test Agentforce AI agents — Agent Script, topics, Apex actions, metadata deployment. Use PROACTIVELY when building Agentforce. Do NOT use for standard Apex.

Build, test, and review Apex classes, triggers, batch, async, and callouts via TDD. Use PROACTIVELY when modifying Apex. For new features, use sf-architect first. Do NOT use for LWC, Flow, or org config.

Classify work, interview user, run impact analysis, design Salesforce Apex/LWC/Flow solutions, decompose into agent tasks with deploy order and rollback plan. Use PROACTIVELY when planning ANY change — FIRST agent. Do NOT skip to domain agents.

Use when reviewing or maintaining Aura components for architecture, events, Locker/LWS compliance, performance, and LWC migration readiness. Do NOT use for LWC components or Apex-only review.

Diagnose and fix Salesforce build errors, Apex test failures, metadata conflicts, and deployment issues with minimal diffs. Use PROACTIVELY when builds or deploys fail. Do NOT use for new features or refactoring.

Build, test, and review Record-Triggered, Screen, Scheduled, and Orchestration Flows with approvals and sub-flow decomposition. Use PROACTIVELY when modifying Flows. For new features, use sf-architect first. Do NOT use for Apex or LWC.

Build and review Salesforce integrations — REST/SOAP callouts, Named Credentials, Platform Events, CDC, retry via Finalizers. Use PROACTIVELY when building integrations. For new features, use sf-architect first. Do NOT use for internal Apex or LWC.

Build, test, and review LWC with SLDS, accessibility, wire, and events. Use built in lightning components first otherwise build own using SLDS. Use PROACTIVELY when modifying LWC. For new features, use sf-architect first. Do NOT use for Apex/Aura/VF.

Final Salesforce quality gate — validate Apex, LWC, Flow against architect plan; audit security, governor limits, tests, and deploy readiness. Use PROACTIVELY when reviewing as LAST agent before deploy. Do NOT use for writing/fixing.

Reviews Visualforce pages for XSS, SOQL injection, ViewState, CRUD/FLS, and LWC migration readiness. Use when reviewing or maintaining Visualforce pages. Do NOT use for LWC or Apex classes.

Use when saving current Salesforce development session state. Persist org context, Apex progress, and pending work to a dated file for future session resumption.

Use when researching existing Salesforce tools, Apex libraries, or metadata patterns before writing custom code. Search-first workflow with agent. Do NOT use for implementing code — only for discovery and evaluation.

Use when scanning Salesforce org Claude Code configuration for security vulnerabilities, deploy misconfigurations, and injection risks in CLAUDE.md, hooks, and MCP servers. Do NOT use for Apex code review — use sf-security.

Use when you need a quick Salesforce answer mid-task. Answer a side question about Apex, org config, or metadata without losing context, then resume work automatically.

Use when saving Salesforce development progress. Create a named checkpoint via git stash before risky Apex deploys or org changes for easy recovery.

Use when setting up SCC for Salesforce Apex and LWC development. Interactive wizard to install profiles, modules, and customize the harness for your org.

Use when building autonomous Claude Code loops for Salesforce Apex and LWC projects. Patterns from sequential pipelines to RFC-driven multi-agent DAG systems with quality gates. Do NOT use for single-shot Apex tasks.

Use when building MCP servers for Salesforce Apex or org integration. Node/TypeScript SDK patterns — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Do NOT use for Apex class writing or deployment.

Use when selecting Claude model tier for Salesforce development tasks. Recommend haiku, sonnet, or opus based on Apex complexity, deploy risk, and budget.

Use when improving a Salesforce, Apex, or LWC prompt. Analyze intent and gaps, match SCC skills/agents, output a ready-to-paste optimized prompt. Advisory only.

Use when cleaning up Salesforce Apex or LWC code. Dead code removal and consolidation using PMD and Salesforce Code Analyzer for safe cleanup.

Use when resuming a previous Salesforce development session. Load saved org context and Apex work-in-progress to continue where the last session ended.

Salesforce API design — custom REST endpoints, batch operations, Composite API, error envelopes, auth. Use when designing APIs exposed from Salesforce. Do NOT use for outbound callouts or Platform Events.

Use when designing Salesforce Apex approval processes, multi-step approvals, or Flow-integrated submissions. Do NOT use for general Apex or Flow-only work.

Salesforce Aura component development — bundles, events, server-side actions, Locker Service, and LWC migration. Use when maintaining or migrating Aura.

Auto-fix Salesforce build errors — Apex compilation, metadata conflicts, dependencies, test failures. Use when build errors block deployment. Do NOT use for writing new features or refactoring.

Use when looking up Salesforce CLI sf commands — org login, project deploy, apex run test, data query, package install, scratch org creation. Do NOT use for web documentation lookup or Apex code patterns.

Use when designing Salesforce custom objects, relationships, Custom Metadata, or sharing models for scalable org architecture. Do NOT use for SOQL optimization or Apex patterns.

Salesforce debugging — debug logs, SOQL explain plan, Flow debug, LWC DevTools, error resolution. Use when diagnosing Apex exceptions, governor breaches, or Flow failures. Do NOT use for tests or build errors.

Enforce deployment safety — validation-only first, test coverage gates, metadata ordering, rollback readiness. Use when deploying or packaging ANY Salesforce metadata. Do NOT use for local dev or scratch org pushes.

Use when deploying to a Salesforce org. SF CLI source deploy, metadata API, package deployment, validation-then-quick-deploy, rollback planning, and production deployment best practices.

Use when setting up Salesforce CI/CD pipelines. GitHub Actions, JWT auth, scratch org workflows, sandbox promotion, and deployment automation.

Use when looking up official Salesforce documentation. Apex reference, LWC docs, platform guides, API references, and SF CLI commands via WebSearch.

Use when writing Salesforce Apex end-to-end integration tests, deployment verification, or bulk scenario validation. Do NOT use for unit tests or TDD.

Salesforce Experience Cloud — site setup, guest users, external sharing, LWC in communities, CMS, auth. Use when building portals or partner communities. Do NOT use for internal Lightning apps.

Salesforce Flow development — flow types, patterns, bulkification, error handling, testing, subflows, Flow vs Apex. Use when building or reviewing Flows. Do NOT use for pure Apex or Platform Event architecture.

Use when hitting Salesforce governor limits in Apex — SOQL, DML, heap, CPU optimization, async offloading, bulk processing strategies. Do NOT use for general Apex or LWC patterns.

Use when auditing SCC harness for Salesforce development completeness. Check hooks, agents, skills, and rules health for Apex and LWC coverage, and score each category.

Use when asking what SCC can do. Discover SCC agents and skills — organized by Salesforce workflow to answer what tools are available and which to use.

Use when building Salesforce Apex integrations — REST/SOAP callouts, Named Credentials, inbound API, External Services. Do NOT use for Platform Events or Flow-only automation.

Enforce LWC naming, security, accessibility, and performance rules. Use when writing or reviewing ANY LWC component, template, or JS controller. Do NOT use for Apex, Aura, Visualforce, or Flow.

LWC development — components, reactive properties, wire service, Apex integration, events, lifecycle hooks. Use when building LWC components or debugging wire/reactivity. Do NOT use for Aura, Visualforce, or Flow.

LWC Jest testing — component mounting, wire/Apex mocking, user interaction simulation, toast/navigation verification. Use when writing or debugging LWC Jest tests. Do NOT use for Apex or Flow testing.

Use when working with Salesforce metadata types, package.xml, or .forceignore. Source vs metadata format, retrieval, deployment, and org comparison.

Salesforce Platform Events and CDC — Apex publish/subscribe, event replay, testing patterns. Use when designing event-driven integrations or data sync.

Use when setting up SCC on a Salesforce project. Detect Apex, LWC, or mixed project type, recommend configuration, install appropriate profile.

Enforce CRUD/FLS, sharing model, SOQL injection prevention, and XSS protection for Apex and LWC. Use when writing or reviewing ANY Apex, trigger, LWC, or VF page. Do NOT use for Flow-only configuration.

Use when implementing Salesforce Apex security — CRUD/FLS enforcement, sharing keywords, SOQL injection prevention, AppExchange review prep. Do NOT use for general Apex or LWC patterns.

Enforce SOQL/SOSL safety rules, selectivity, and governor limit compliance. Use when writing or reviewing ANY SOQL query, SOSL search, or database operations. Do NOT use for Apex structure, LWC, or Flow.

SOQL optimization — selective queries, index strategy, query plans, relationship efficiency, large data volumes. Use when queries hit limits or designing for 100K+ records. Do NOT use for general Apex, LWC, or Flow.

Use when doing test-driven Salesforce Apex development — RED-GREEN-REFACTOR cycle for classes, triggers, and LWC Jest. Do NOT use for test patterns only.

Enforce Apex testing standards — 75% coverage minimum, test isolation, assertions, TestDataFactory. Use when writing or reviewing ANY Apex test class or method. Do NOT use for LWC Jest or Flow tests.

Enforce one-trigger-per-object, handler delegation, bulkification, and recursion prevention. Use when writing or reviewing ANY Apex trigger or handler. Do NOT use for non-trigger Apex, LWC, or Flow.

Salesforce Apex trigger framework patterns — TriggerHandler, FFLIB Domain, TDTM, bypass and recursion control. Use when adopting or refactoring triggers.

Visualforce development — pages, controllers, extensions, ViewState, JS Remoting, LWC migration. Use when maintaining VF pages, building PDFs, or planning VF-to-LWC migration. Do NOT use for LWC, Aura, or Flow.

Use when managing context during long Salesforce Apex development sessions. Suggests manual compaction at logical intervals to preserve deploy and org context across phases.

Use when syncing documentation after Salesforce Apex code changes. Update README, API docs, and deploy metadata references to match the current org codebase.

Update Salesforce platform reference docs with latest release features and deprecation announcements. Use when SessionStart hook warns docs are outdated or a new Salesforce release has shipped. Do NOT use for Apex or LWC development.

Use when managing Salesforce Claude Code session history. List, load, alias, and inspect saved Apex and org development sessions stored in ~/.claude/sessions/.

Use when user asks for a 2GP security review, AppExchange readiness check, or pass/fail prediction for Apex, LWC, SOQL. Do NOT use for general security patterns.

Agentforce agent development — Agent Script, topics/subagents, actions, testing, metadata. Use when building Agentforce agents, Apex InvocableMethod actions, or agent SOQL patterns. Do NOT use for non-Agentforce Apex or Flow-only automation.

MCP Server actions for Agentforce — registry, auth, prebuilt servers, Apex integration. Use when configuring MCP as an Agentforce action type. Do NOT use for building MCP servers.

Async Apex patterns — @future, Queueable, Batch, Schedulable, Platform Events, chaining. Use when choosing or implementing async processing. Do NOT use for synchronous Apex or constraint enforcement.

Use when writing production-ready Salesforce Apex classes — organization, error handling, collection patterns. Do NOT use for test classes or triggers.

Enforce Apex governor limits, naming, bulkification, and security rules. Use when writing or reviewing ANY Apex class, trigger, or batch job. Do NOT use for LWC, Flow, or Visualforce.

Apex Cursor API for paginating large SOQL results (up to 50M records) — cursor navigation, Queueable chaining, LWC pagination. Use when paginating queries or migrating from OFFSET. Do NOT use for small result sets.

Use when implementing Salesforce Apex Enterprise Patterns (FFLIB) — Selector, Domain, Service, Unit of Work layers. Do NOT use for simple orgs or constraints.

Apex unit testing — test structure, TestDataFactory, governor limit testing, async testing, mocks, coverage. Use when writing tests or improving coverage. Do NOT use for TDD workflow or LWC Jest tests.

29 hooks across 7 events

Official Salesforce DX MCP Server — org management, metadata, data, testing, code analysis, LWC, DevOps

Salesforce CLI v2 — direct CLI access for commands not covered by MCP toolsets