agentmods.dev

salesforce-crm

salesforce-crm is a skill for Claude Code, Codex from ozgurkarahan/salesforce-meta-tool-identity-propagation. It costs 68 tokens per session (774 once invoked), scanned A, original, MIT.

A set of instructions for reading and changing Salesforce, a cloud system for managing customer accounts, contacts, sales deals, and support cases. It explains when to look up records, inspect fields, run searches, and make updates.

In plain words
What is it for?
Use it to find accounts, contacts, opportunities, cases, approvals, and custom records, or to create, update, delete, and approve Salesforce records.
Why use it?
It reduces mistakes when finding Salesforce records or changing them. It also helps ensure that updates use the current field rules and that results are explained in plain language.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 4repo today A scan 68 tokens original MIT

Good fit Use it to find accounts, contacts, opportunities, cases, approvals, and custom records, or to create, update, delete, and approve Salesforce records.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ozgurkarahan/salesforce-meta-tool-identity-propagation/salesforce-crm
View source ↗ ozgurkarahan/salesforce-meta-tool-identity-propagation ozgurkarahan.com
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.

Any agent
npx skills add ozgurkarahan/salesforce-meta-tool-identity-propagation --skill salesforce-crm
Clone the repo
git clone --depth 1 https://github.com/ozgurkarahan/salesforce-meta-tool-identity-propagation

Made for: Claude Code, Codex.

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 salesforce-crm

README.md
[![agentmods](https://agentmods.dev/badge/skills/ozgurkarahan/salesforce-meta-tool-identity-propagation/salesforce-crm/github.svg)](https://agentmods.dev/skills/ozgurkarahan/salesforce-meta-tool-identity-propagation/salesforce-crm)
Your own site
<a href="https://agentmods.dev/skills/ozgurkarahan/salesforce-meta-tool-identity-propagation/salesforce-crm"><img src="https://agentmods.dev/badge/skills/ozgurkarahan/salesforce-meta-tool-identity-propagation/salesforce-crm/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.

agentmods 80×15 button for salesforce-crm

Your own site · 80×15
<a href="https://agentmods.dev/skills/ozgurkarahan/salesforce-meta-tool-identity-propagation/salesforce-crm"><img src="https://agentmods.dev/badge/skills/ozgurkarahan/salesforce-meta-tool-identity-propagation/salesforce-crm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 774 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original 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 $0.00068 $0.00774
Opus 5.5 $0.00027 $0.00310
Sonnet 5.5 $0.00014 $0.00155
Haiku 4.5 $0.00007 $0.00077

Measured today against content hash f23ee9bb751e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

salesforce-crm 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 today.

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.

skills/salesforce-crm/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Salesforce CRM

Workflow

  1. Identify the user only when needed. If the user says "my"/"me", reuse a UserId already in this conversation; otherwise call whoami once. Filter with OwnerId = '<UserId>' or CreatedById = '<UserId>'.
  2. Find the object. Skip for well-known standard objects (Account, Contact, Opportunity, Case, Lead, Task, Event, User). Otherwise call list_objects(filter=...) and use the name (API name), never the label.
  3. Learn the fields.
    • Reads: skip describe_object when you only need common fields (Id, Name, CreatedDate, OwnerId, LastModifiedDate) or fields already seen in this conversation. Otherwise use mode="slim" (types, referenceTo, childRelationships) or mode="names" to only validate names.
    • Writes: describe_object(mode="full") is REQUIRED every time — picklists and validation rules change.
  4. Execute.
    • soql_query for exact filters, joins and aggregates.
    • search_records (SOSL) when the object is unknown or for fuzzy keyword search.
    • write_record(operation=create|update|upsert|delete).
    • process_approval(action=Submit|Approve|Reject).
  5. Summarize in plain language. Never dump raw JSON.

SOQL rules

  • Always include LIMIT (default 20–50) unless the user explicitly asks for all rows. max_records defaults to 100, cap 500.
  • API names are PascalCase: Account, OpportunityLineItem, Custom_Field__c.
  • Parent fields via dot notation: SELECT Name, Account.Name FROM Opportunity.
  • Child subqueries use the relationshipName from childRelationships, not the object name: SELECT Name, (SELECT Subject FROM Cases) FROM Account.
  • Open opportunities and open cases: IsClosed = false.
  • Date literals: CloseDate = NEXT_N_DAYS:90, CreatedDate = LAST_N_DAYS:30.
  • Quote string values with single quotes; escape embedded quotes.

Error recovery

  • INVALID_FIELD / MALFORMED_QUERY: the error contains availableFields (name, type, referenceTo). Fix the query from it and retry immediately — do NOT call describe_object again. If the field is absent, the org hides it; look for a path through the parent's childRelationships.
  • INSUFFICIENT_ACCESS: the user lacks permission. Say which object/field and stop.
  • ENTITY_IS_DELETED: tell the user the record was deleted.
  • UNABLE_TO_LOCK_ROW: retry once.
  • Explain any error in plain language before retrying.

Read the full file on GitHub · 59 lines

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. today First seen · 59 lines · 68 tokens per session scan A f23ee9bb751e

Subscribe to this mod's changes

salesforce-crm is a skill published in the GitHub repository ozgurkarahan/salesforce-meta-tool-identity-propagation (4 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 774 once invoked, about $0.0003 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 2026-10-17.

Backend and APIsazure-ai-foundryazure-api-managementbicepentra-ididentity-propagationjwt-bearer
Related

Other skills, from other repositories

claude-on-foundry

End-to-end assistant skill for the Claude on Foundry Starter Kit (Azure-Samples/claude). Walks customers through deploying, verifying, modifying, debugging, and tearing down a Claude model deployment on Microsoft Foundry using either the Bicep or Terraform IaC variant in this repo, with one-command guidance via azd…

Azure-Samples/claude · 239 tokens

api-security-design

Guidance for designing secure APIs on Azure - authentication, authorization, gateway controls, input validation, rate limiting, secret management, and runtime threat detection - aligned to OWASP API Security Top 10 and Azure API Management. WHEN: API security design, secure API, OWASP API Top 10, API authentication…

vinayaklatthe/microsoft-security-skills · 131 tokens

entra-id

Guidance for Microsoft Entra ID (formerly Azure AD) — cloud identity and access management and the control plane for Zero Trust. Covers tenant and identity model, authentication methods (passkeys, FIDO2, certificate-based), hybrid identity with Entra Connect or Cloud Sync, app registrations and consent governance…

vinayaklatthe/microsoft-security-skills · 196 tokens

defender-for-apis

Guidance for Microsoft Defender for APIs — a Defender for Cloud plan that discovers, prioritizes by risk, and protects APIs published in Azure API Management against threats and abuse. Covers onboarding, security findings, and threat detection. WHEN: Defender for APIs, API threat protection, secure APIs in API…

vinayaklatthe/microsoft-security-skills · 89 tokens

om-grounded-sql

Ground every query in the catalog before writing SQL; abstain when the catalog cannot ground it.

calvinchengx/data-agent-service · 24 tokens

dashboard-authoring

Turn a recurring query template into a semantic-model + report definition, deterministically.

calvinchengx/data-agent-service · 19 tokens