Borrowing it
Nothing to install: this file belongs to PranavNagrecha/Salesforce-Intelligence. 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/PranavNagrecha/Salesforce-Intelligence/main/CLAUDE.mdgit clone --depth 1 https://github.com/PranavNagrecha/Salesforce-IntelligenceWrote 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/pranavnagrecha/salesforce-intelligence/claude-md)<a href="https://agentmods.dev/instructions/pranavnagrecha/salesforce-intelligence/claude-md"><img src="https://agentmods.dev/badge/instructions/pranavnagrecha/salesforce-intelligence/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/pranavnagrecha/salesforce-intelligence/claude-md"><img src="https://agentmods.dev/badge/instructions/pranavnagrecha/salesforce-intelligence/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 | $0.00616 | $0.00616 |
| Opus 5.5 | $0.00246 | $0.00246 |
| Sonnet 5.5 | $0.00123 | $0.00123 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
Salesforce-Intelligence 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 10d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sf-intelligence: working in this checkout
You are in the source repository of sf-intelligence, a read-only, offline
MCP server and CLI that answers questions about one Salesforce org from a
local metadata vault. This file is read only by someone who opens the clone
in Claude Code (a contributor or an evaluator); it is not shipped to users.
The instructions users get are the skills under .claude/skills/, which the
Claude Code plugin installs. Start with using-sf-intelligence.
Build and run from here
pnpm install && pnpm build # compile every package; the CLI bundles the MCP server
node packages/cli/bin/sfi.js demo # serve the built-in demo org (Verdant Energy), no Salesforce login
.mcp.json at the repo root points Claude Code at that CLI, so a session
launched from this folder has the sfi.* tools. To answer about a real org,
build its vault inside that org's Salesforce DX project (sfi init --target-org <alias>, then sfi refresh) and start the server with
node packages/cli/bin/sfi.js mcp --vault /absolute/path/to/org-kb.
Rebuild after any change under packages/; a running server does not pick
up edits.
When a question is about a Salesforce org
Load .claude/skills/using-sf-intelligence/SKILL.md first. The default
profile exposes the 16-tool core roster; every other analysis runs through
the gateway tool sfi.run_analysis, given the analysis name and its
arguments. Every org fact comes from a tool result, cited by its component
id. Never fill a gap with general Salesforce knowledge, and say plainly when
the vault did not retrieve something.
Two rules for contributors
- No real org names in tracked files or commit messages. Fixtures and
examples use the demo org (Verdant Energy) and
Demo_*/Acme_*names.pnpm scan:leaksmust pass. See CONTRIBUTING.md. pnpm lint && pnpm testbefore a pull request. CI runs the private gates on top.
Where things live
packages/: the source, one package per layer;packages/cliis the one published to npm.docs/: user documentation, indexed indocs/README.md.website/: sfi.auditforce.cloud..claude/skillsand.claude/commands: shipped by the plugin..claude/agents: the two optional/sfi-field-auditagents, not shipped;.claude/agents/maintainer: agents for working on this repo.REPO-STRUCTURE.md: the repository map.RELEASING.md: release steps.
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.
- 10d ago Changed · +1 lines · +21 tokens per session bde707732a1f
- 11d ago Changed · -137 lines · -1,880 tokens per session 4af58348dc00
- 13d ago Changed · +5 tokens per session 7e5e8c5b42ad
- 16d ago Changed · +4 lines · +47 tokens per session dbbeda12423d
- 24d ago Changed 598912c025d4
- 1mo ago Changed · +3 lines · +63 tokens per session 1b4cff81bce1
- 1mo ago First seen · 181 lines · 2,360 tokens per session scan A aba6571b17d4
Salesforce-Intelligence CLAUDE.md is an instructions file published in the GitHub repository PranavNagrecha/Salesforce-Intelligence (2 stars, last pushed 9d ago), licensed MIT. It adds 616 tokens to every session, about $0.0025 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.