Borrowing it
Nothing to install: this file belongs to divingsbysangam/salesforce-compound-engineering-plugin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/divingsbysangam/salesforce-compound-engineering-plugin/main/CLAUDE.mdgit clone --depth 1 https://github.com/divingsbysangam/salesforce-compound-engineering-pluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/divingsbysangam/salesforce-compound-engineering-plugin/claude-md)<a href="https://agentmods.dev/instructions/divingsbysangam/salesforce-compound-engineering-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/divingsbysangam/salesforce-compound-engineering-plugin/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/divingsbysangam/salesforce-compound-engineering-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/divingsbysangam/salesforce-compound-engineering-plugin/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02280 | $0.02280 |
| Opus 5.5 | $0.00912 | $0.00912 |
| Sonnet 5.5 | $0.00456 | $0.00456 |
| Haiku 4.5 | $0.00228 | $0.00228 |
Grade A, and why
salesforce-compound-engineering-plugin CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this repo is
A multi-platform AI plugin (Claude Code, Cursor, Codex, and 9 other AI coding tools via a CLI installer) that adds Salesforce-aware compound engineering workflows. The product is the markdown under skills/ — those files are what get distributed and what other AI clients load. The TypeScript CLI under cli/ translates that markdown into each target tool's expected directory layout and hosts the optional local Tend feed runtime (CLI-only).
A Salesforce developer using this plugin gets ten skills (V4): sf-plan, sf-work, sf-generate, sf-review, sf-debug, sf-deploy, sf-ship, sf-compound, sf-lfg, and sf-know. Each skill has modes (/sf-plan mode:brainstorm, /sf-generate type:apex, /sf-know topic:limits); a mode's guide lives at skills/<skill>/references/<mode>/guide.md and loads only when that mode runs, so only ten short descriptions are always in context. Reviews run through nine review lenses, concise stack checklists dispatched as isolated subagents (parallel on Claude Code, inline on harnesses without a subagent primitive). An optional repo-root STRATEGY.md (maintained by /sf-plan mode:strategy) grounds planning when present.
Agentless (V3.1). The plugin ships no standalone registered agents — formal agent definitions are not a reliable common denominator across Claude, Codex, Cursor, Gemini, Pi, OpenCode, etc. Specialist behavior lives as skill-local prompt assets, review lenses under skills/sf-review/references/lenses/<stack>.md and a few personas under skills/<owner>/references/personas/<name>.md, owned by the workflow skill that dispatches them and referenced cross-skill by relative path. They ship to every platform as ordinary skill files (the CLI copies a skill's whole subtree).
Principles are the source of truth
PRINCIPLES.md lists seven numbered principles that govern every skill, every persona, and every code review. README, this file, and the workflow skills reference them by number rather than restating them. When something in this repo (a skill, an agent, a PR) conflicts with a principle, fix the implementation — don't soften the principle. When principles conflict with each other (rare), the lower-numbered principle wins.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +10 lines · +123 tokens per session f6ec6c68ec8d
- 1mo ago Changed · +52 tokens per session c44170d71489
- 2mo ago First seen · 94 lines · 2,105 tokens per session scan A fa2b680efa4a
salesforce-compound-engineering-plugin CLAUDE.md is an instructions file published in the GitHub repository divingsbysangam/salesforce-compound-engineering-plugin (11 stars, last pushed 4d ago), licensed MIT. It adds 2,280 tokens to every session, about $0.0091 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
salesforce-compound-engineering-plugin CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| salesforce-compound-engineering-plugin CLAUDE.mddivingsbysangam/salesforce-compound-engineering-plugin | Instructions file | 11 | 4d ago | MIT | A | 2,280 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |