sf-compound-engineering

<span data-proof="authored" data-by="ai:claude">Use this index to find agents by topical concern. After the V3 migration, all agents live in a flat</span> <span data-proof="authored" data-by="ai:claude">`agents/`</span> <span data-proof="authored" data-by="ai:claude">directory and are named</span> <span data-proof="authored" data-by="ai:claude">`sf-<name>.agent.md`. The topical groupings below are documentation aids — they do not correspond to filesystem paths.</span>

Conditional document-review persona, selected when the Salesforce planning document has >5 requirements or implementation units, makes significant architectural decisions, covers high-stakes domains (sharing, integrations, AppExchange release), or proposes new abstractions. Spawned by sf-doc-review for Deep plans.

Conditional code-review persona, selected when the Salesforce diff is large (>=50 changed lines) or touches high-risk surfaces like sharing, profile/permset, payments, callouts, or data mutations. Actively constructs failure scenarios to break the implementation.

Expert in Apex bulk processing patterns, collection handling, and trigger context optimization

Expert in Apex error handling, exception patterns, and graceful degradation

Build, modify, debug, and deploy Agentforce agents written in Agent Script. Use when creating or modifying .agent files or aiAuthoringBundle metadata, designing subagents and actions, writing or reviewing an Agent Spec, or running sf agent generate / preview / validate / publish / activate. Trigger phrases: 'build an Agentforce agent', 'create an agent for', 'write an Agent Script', 'design subagents for', 'add an action to my agent', 'deploy this agent', 'publish my Agentforce bundle'. Do NOT trigger for plain Apex, Flow, LWC, or Prompt Template work.

Analyze production Agentforce agent behavior using STDM session traces in Data Cloud, plus a fallback path using sf agent test + sf agent preview --authoring-bundle when STDM is unavailable. Use when investigating production failures, regressions, or performance regressions; querying ssot__AiAgentSession__dlm; reproducing reported issues in preview; or improving the .agent file based on production evidence. Trigger phrases: 'why is my agent failing in production', 'analyze production sessions', 'investigate this Agentforce regression', 'what happened in this session', 'reproduce this production issue', 'find sessions where the agent misrouted'. Do NOT trigger for development-time iteration — use /agentforce-develop or /agentforce-test.

Write, run, and analyze test suites for Agentforce agents — preview-based smoke tests, Testing Center batch suites, action execution, trace diagnosis, and iterative fix loops. Use when running sf agent test create / run / run-eval / results, writing AiEvaluationDefinition test specs, building regression suites, integrating Agentforce tests into CI/CD, or interpreting test failures. Trigger phrases: 'test my Agentforce agent', 'run a smoke test on this agent', 'build a test suite for', 'write an AiEvaluationDefinition', 'why is my agent test failing'. Do NOT trigger for general Apex test class work — use sf-work / sf-review for that.

Generate Apex classes and tests with bulkification, CRUD/FLS, and the project's trigger framework wired in. Covers services, selectors, domain classes, batch / queueable / schedulable, invocable methods, REST resources, and the matching test classes with TestDataFactory + 251+ record bulk tests. Trigger phrases: 'create an Apex class', 'generate a service class', 'write a queueable for', 'scaffold a batch class', 'build an @InvocableMethod', 'add a REST resource', 'generate Apex tests for', 'cover this class with tests'. Pairs with `apex-patterns` (reference) and `test-factory` (TDF reference). Do NOT trigger for triggers themselves — use `apex-trigger-refactor` for trigger work.

Common Apex design patterns including Selector, Service, Domain, and Trigger Handler patterns