using-sf-intelligence

using-sf-intelligence is a skill for Claude Code from PranavNagrecha/Salesforce-Intelligence. It costs 106 tokens per session (4,839 once invoked), scanned C, original, no licence file.

An entry point for the SfIntelligence plugin, which provides guidance about the Salesforce organisation used in this repository. Salesforce is a platform for business data, workflows, permissions, and custom code.

In plain words
What is it for?
Use it for questions about the org’s schema, dependencies, permissions, naming, automation, Apex, Flow, integrations, sharing, or contained components.
Why use it?
It helps an agent understand the organisation’s local rules and components before answering Salesforce-related questions.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Part of the sf-intelligence plugin — 26 skills, 5 commands, 4 agents, 2 MCP servers shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/pranavnagrecha/salesforce-intelligence/using-sf-intelligence
Any agent
npx skills add PranavNagrecha/Salesforce-Intelligence --skill using-sf-intelligence
Clone the repo
git clone --depth 1 https://github.com/PranavNagrecha/Salesforce-Intelligence

Made for: Claude Code.

Or install sf-intelligence, the plugin that ships this one along with the rest of its 26 skills, 5 commands, 4 agents, 2 MCP servers.

Wrote 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.

agentmods badge for using-sf-intelligence

README.md
[![agentmods](https://agentmods.dev/badge/skills/pranavnagrecha/salesforce-intelligence/using-sf-intelligence.svg)](https://agentmods.dev/skills/pranavnagrecha/salesforce-intelligence/using-sf-intelligence)
Your own site
<a href="https://agentmods.dev/skills/pranavnagrecha/salesforce-intelligence/using-sf-intelligence"><img src="https://agentmods.dev/badge/skills/pranavnagrecha/salesforce-intelligence/using-sf-intelligence.svg" alt="Measured on agentmods" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,839 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00106 $0.04839
Opus 5 $0.00053 $0.02420
Sonnet 5 $0.00021 $0.00968
Haiku 4.5 $0.00011 $0.00484

Measured 6d ago against content hash 4dc5cbf6d72d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

using-sf-intelligence scanned grade C with 1 finding 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 6d 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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

graphs and Flow explanation SHIP — use them; don't refuse.)
.claude/skills/using-sf-intelligence/SKILL.md · 356 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

Changes

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.

  1. 6d ago First seen · 356 lines · 106 tokens per session scan C 4dc5cbf6d72d

Subscribe to this mod's changes

using-sf-intelligence is a skill published in the GitHub repository PranavNagrecha/Salesforce-Intelligence (2 stars, last pushed 4d ago), with no licence file. It adds 106 tokens to every session and 4,839 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

prompt-optimizer

Use when improving a Salesforce, Apex, or LWC prompt. Analyze intent and gaps, match SCC skills/agents, output a ready-to-paste optimized prompt. Advisory only.

jiten-singh-shahi/salesforce-claude-code · 40 tokens

sf-agentforce-development

Agentforce agent development — Agent Script, topics/subagents, actions, testing, metadata. Use when building Agentforce agents, Apex InvocableMethod actions, or agent SOQL patterns. Do NOT use for non-Agentforce Apex or Flow-only automation.

jiten-singh-shahi/salesforce-claude-code · 55 tokens

sf-integration

Use when building Salesforce Apex integrations — REST/SOAP callouts, Named Credentials, inbound API, External Services. Do NOT use for Platform Events or Flow-only automation.

jiten-singh-shahi/salesforce-claude-code · 38 tokens

continuous-agent-loop

Use when building autonomous Claude Code loops for Salesforce Apex and LWC projects. Patterns from sequential pipelines to RFC-driven multi-agent DAG systems with quality gates. Do NOT use for single-shot Apex tasks.

jiten-singh-shahi/salesforce-claude-code · 43 tokens

sf-apex-cursor

Apex Cursor API for paginating large SOQL results (up to 50M records) — cursor navigation, Queueable chaining, LWC pagination. Use when paginating queries or migrating from OFFSET. Do NOT use for small result sets.

jiten-singh-shahi/salesforce-claude-code · 55 tokens

sf-apex-enterprise-patterns

Use when implementing Salesforce Apex Enterprise Patterns (FFLIB) — Selector, Domain, Service, Unit of Work layers. Do NOT use for simple orgs or constraints.

jiten-singh-shahi/salesforce-claude-code · 41 tokens