agentforce-adlc
Agentforce Agent Development Life Cycle — author, discover, scaffold, deploy, test, and optimize .agent files
/plugin install agentforce-adlc@claude-plugins-officialHow to start
- Paste the command into Claude Code and press Enter.
- Restart Claude Code so the plugin loads.
- Just ask Claude. Its skills step in when your request fits.
What it adds
4 agents · 3 skills · 2 hooks
Agents Claude hands work to these
adlc-authorWrites Agentforce Agent Script (.agent) files from requirementsadlc-engineerPlatform engineer — scaffolds Flow/Apex metadata and deploys agent bundlesadlc-orchestratorPlan-mode orchestrator for the Agent Development Life Cycleadlc-qaTests Agentforce agents and optimizes based on session trace analysis
Skills Claude loads these when the task fits
agentforce-generateBuild, modify, audit, repair, optimize, debug, and deploy agents with Agentforce Agent Script. TRIGGER when: user creates, reviews, or changes .agent files or…agentforce-observeAnalyze production Agentforce agent behavior using session traces and Data Cloud, and manage Agent Health Monitoring (AHM) alerts. TRIGGER when: user queries S…agentforce-testWrite, run, and analyze structured test suites for Agentforce agents — functional AND security. TRIGGER when: user writes or modifies test spec YAML (AiEvaluat…
Hooks Run on their own at these moments
PreToolUseBefore Claude uses a tool.PostToolUseAfter Claude uses a tool.
Read from the plugin's own files in SalesforceAIResearch/agentforce-adlc, 26 Oct 2026.
What it needs
No keys or settings: its files ask for none.
More in Development
See all →superpowers
Superpowers teaches Claude brainstorming, subagent driven development with built in code review, systematic debugging…
mattpocock-skills
Matt Pocock's agent skills for real engineering — grilling, spec/ticket flows, TDD, code review, domain modelling and…
chrome-devtools-mcp
Control and inspect a live Chrome browser from your coding agent. Record performance traces, analyze network requests…
deepeval
Skills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI…
huggingface-skills
Build, train, evaluate, and use open source AI models, datasets, and spaces.
atomic-agents
Comprehensive development workflow for building AI agents with the Atomic Agents framework. Includes specialized…