agentforce-adlc Cursor规则

Prerequisites

• Python 3.9+ — check with python3 --version. If older, upgrade: brew install python@3.13 (macOS) / sudo apt install python3.13 (Ubuntu) / python.org (Windows)
• Salesforce CLI (sf) v2.x — install guide
• Claude Code (~/.claude/) or Cursor (~/.cursor/) — at least one must be installed
• Salesforce org with Agentforce enabled

Installation

Option B: Install via marketplace

claude plugin marketplace add SalesforceAIResearch/agentforce-adlc claude plugin install agentforce-adlc@agentforce-adlc ```

When installed as a plugin, skills are namespaced: /agentforce-adlc:agentforce-generate, /agentforce-adlc:agentforce-test, /agentforce-adlc:agentforce-observe.

File-copy install (Cursor or legacy Claude Code)

```bash

One-command install

curl -sSL https://raw.githubusercontent.com/SalesforceAIResearch/agentforce-adlc/main/tools/install.sh | bash

Post-install management

```bash

What installs where

Plugin installation is self-contained — no files are copied to ~/.claude/. The file-copy installer is for Cursor and legacy Claude Code setups.

1. Build and deploy (`/agentforce-generate`)

This single skill handles the full development workflow — authoring, discovery, scaffolding, and deployment:

/agentforce-generate

Build a service agent that helps customers check order status,
request returns, and track shipments. It should verify identity
before showing order details. Deploy to my-org.

The skill will: 1. Author — Generate a .agent file with topics, actions, variables, and deterministic logic 2. Discover — Check which Flow/Apex/Retriever targets exist in the org 3. Scaffold — Generate stubs for missing targets (Flow XML, Apex classes, test classes, PermSets) 4. Deploy — Validate, publish the authoring bundle, and activate the agent

Each phase can also be triggered individually (e.g., "just discover targets for OrderService.agent").

If the package is unavailable or stale, build the pinned source and validate

node tests/validate_agent_assets_from_source.mjs \ skills/agentforce-generate/assets

Install from local clone (for development)

python3 tools/install.py --force ```

The SDK-backed validator rejects versions older than the minimum declared in tests/agentscript-toolchain.json. It uses the public @sf-agentscript/agentforce package without adding it to the repository or the installed skills. When that package is unavailable or stale, use the source command to clone and build the pinned salesforce/agentscript revision. CI uses that revision as the reproducible merge gate and checks main separately on a schedule. Update the pin and declared minimum together when AgentScript advances. Target-org compilers can differ, so run sf agent validate authoring-bundle against the deployment org before release. Installing or using the skills does not add a Node or AgentScript SDK runtime dependency.

Quick start

Option A: Load directly (development)

claude --plugin-dir ./agentforce-adlc

Clone and set up dev environment

git clone https://github.com/SalesforceAIResearch/agentforce-adlc.git cd agentforce-adlc pip install -e ".[dev]"

Skills reference

Validate shipped assets with the supported public AgentScript SDK

npx --yes --package=@sf-agentscript/agentforce@2.9.27 -- \ node tests/validate_agent_assets.mjs \ skills/agentforce-generate/assets

Pipeline

User prompt
  |  /agentforce-generate
  v
+--------------------------+
| Safety Review (Phase 0)  |<-- LLM-driven, 7 categories
| .agent file generated    |
+--------+-----------------+
         |  /agentforce-generate (discover)
         v
+--------------------------+
| Check org for targets    |--missing--> scaffold stubs
+--------+-----------------+
         |  /agentforce-generate (deploy)
         v
+--------------------------+
| Safety Gate -> Validate  |<-- Pre-publish check
| -> Publish -> Activate   |
+--------+-----------------+
         |  /agentforce-test
         v
+--------------------------+
| Preview + Batch tests    |<-- Safety probe utterances (adversarial)
| + Action execution       |
+--------+-----------------+
         |  /agentforce-observe
         v
+--------------------------+
| STDM session analysis    |<-- Safety issue detection in traces
| -> Reproduce -> Improve  |
+--------------------------+

Each skill can be invoked independently. Run /agentforce-test on an existing agent without touching the development steps. Run /agentforce-observe on production session data without redeploying.

Claude Code plugin (recommended)

```bash

Plugin management

claude plugin list # List installed plugins claude plugin update agentforce-adlc@agentforce-adlc # Update plugin claude plugin uninstall agentforce-adlc@agentforce-adlc # Remove plugin