claudecodex

sf-compound-engineering

Salesforce compound engineering: ten skills (plan, work, generate, review, debug, deploy, ship, compound, lfg, know) with on-demand modes, stack review lenses, and institutional knowledge compounding for Apex, LWC, Flow, integrations, and Agentforce.

11 on GitHubby Gella Sangamesh Guptav4.0.1MITupdated 3 days ago
/

Plugin sf-compound-engineering from marketplace sf-compound-engineering-marketplace in divingsbysangam/salesforce-compound-engineering-plugin. Commands read from the repo's manifest — 2 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.

What it installs

Skills (11)

  • create-agent-skills

    Guide for adding new personas and skills to the SF Compound Engineering Plugin. Use when creating a new review/research persona, adding a domain-knowledge or workflow skill, or wiring a new specialist concern into sf-review / sf-review mode:doc / sf-plan. Encodes the agentless (V3.1) conventions: pe

  • sf-compound

    Capture durable Salesforce knowledge in docs/solutions/, or refresh stale learnings. Use when the lesson is not in the final code or tests. Use sf-debug for an open failure.

  • sf-debug

    Diagnose a Salesforce failure or explain code: tests, governor limits, deploys, LWC, sharing. Use for 'debug' or 'why is this failing'. Use sf-work when the change is already known.

  • sf-deploy

    Validate, deploy, retrieve, and delete Salesforce metadata; manage orgs, manifests, test runs, and test data; set up the environment. Use for 'deploy', 'validate', 'retrieve', 'package.xml', 'scratch org', 'setup'.

  • sf-generate

    Generate Salesforce source: Apex, triggers, Flows, objects/fields/tabs/apps, permission sets, validation rules, FlexiPages, test data, prompt templates, MCP tools, Agentforce agents and tests.

  • sf-know

    Salesforce platform knowledge on demand: governor limits, Apex/LWC/Flow patterns, security (CRUD/FLS, sharing), integrations, GraphQL, Hosted MCP, agent-native design. Use when a question needs platform facts.

  • sf-lfg

    Take a Salesforce request through to an open PR without check-ins. Use only for 'lfg' or an explicit end-to-end ship. Use sf-plan or sf-work when each step stays in review.

  • sf-plan

    Plan Salesforce work before code: ideate, brainstorm, strategy, or an implementation plan. Use for 'plan this' or STRATEGY.md. Use sf-work to implement; use sf-debug when a test is already failing.

  • sf-review

    Review a Salesforce diff or planning doc for governor limits, CRUD/FLS, sharing, LWC, and Flow. Use for 'review this'. Use sf-ship to judge comments already left on a PR.

  • sf-ship

    Commit, open or describe a PR, judge review feedback, or watch a PR until it looks mergeable. Use for 'open a PR' or 'babysit this PR'. Use sf-review before feedback exists.

  • sf-work

    Implement Salesforce work from a plan or a concrete prompt (Apex, LWC, Flow, metadata). Use for 'build this'. Use sf-plan when the approach is still open; use sf-debug for an open bug.

MCP servers (2)

  • context7

    connects to: https://mcp.context7.com/mcp

  • salesforce-dx

    runs: npx -y @salesforce/mcp --orgs DEFAULT_TARGET_ORG --toolsets orgs,metadata,data,testing,code-analysis,lwc-experts

Hooks (10)

  • SessionStart

    "${CLAUDE_PLUGIN_ROOT}/scripts/session-start"

  • SessionStart

    "${CLAUDE_PLUGIN_ROOT}/scripts/sfce-gate-selfcheck" SessionStart

  • SessionStart

    "${CLAUDE_PLUGIN_ROOT}/scripts/sfce-skill-observer" SessionStart

  • SessionEnd

    "${CLAUDE_PLUGIN_ROOT}/scripts/sfce-skill-observer" SessionEnd

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/scripts/sfce-metadata-gate" PreToolUse

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/scripts/sfce-deploy-gate" PreToolUse

  • PostToolUse

    "${CLAUDE_PLUGIN_ROOT}/scripts/sfce-metadata-gate" PostToolUse

  • PostToolUse

    "${CLAUDE_PLUGIN_ROOT}/scripts/sfce-bash-observer" PostToolUse

  • PostToolUse

    "${CLAUDE_PLUGIN_ROOT}/scripts/sfce-skill-observer" PostToolUse

  • UserPromptExpansion

    "${CLAUDE_PLUGIN_ROOT}/scripts/sfce-skill-observer" UserPromptExpansion

View source on GitHub

Similar plugins

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

agentic-qe-fleet

claude

Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data

9 skills · 9 commands · 11 agents · 1 MCP server

ruvnet/ruflo 81,589

headroom

claude

Headroom startup hooks for Claude Code and GitHub Copilot CLI.

hooks

headroomlabs-ai/headroom 79,508

agentic-awesome-skills

claudecodex

Expose the plugin-safe Claude Code subset of Agentic Awesome Skills through a single marketplace entry.

200 skills

sickn33/agentic-awesome-skills 49,620

ai-plugins

claude

Set up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain

12 skills · 11 agents · hooks

anthropics/claude-plugins-official 47,076

Maintain sf-compound-engineering?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted