design-object

design-object is a command for Claude Code from BanibrataChatterjee/AwesomeSalesforceSkills. It costs 0 tokens per session (544 once invoked), scanned A, original, Apache-2.0.

A Salesforce planning command for defining a new custom data object from a business idea. A Salesforce object is similar to a database table that stores one kind of record.

In plain words
What is it for?
Use it to design fields, relationships, security and integration details, an SFDX metadata scaffold, and the order for deploying the object.
Why use it?
It turns an informal concept into a deployment-ready specification while considering existing objects, data volume, integrations, and sensitive information.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Use it to design fields, relationships, security and integration details, an SFDX metadata scaffold, and the order for deploying the object.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/banibratachatterjee/awesomesalesforceskills/design-object
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.

Clone the repo
git clone --depth 1 https://github.com/BanibrataChatterjee/AwesomeSalesforceSkills

Made for: Claude Code.

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 design-object

README.md
[![agentmods](https://agentmods.dev/badge/commands/banibratachatterjee/awesomesalesforceskills/design-object/github.svg)](https://agentmods.dev/commands/banibratachatterjee/awesomesalesforceskills/design-object)
Your own site
<a href="https://agentmods.dev/commands/banibratachatterjee/awesomesalesforceskills/design-object"><img src="https://agentmods.dev/badge/commands/banibratachatterjee/awesomesalesforceskills/design-object/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 design-object

Your own site · 80×15
<a href="https://agentmods.dev/commands/banibratachatterjee/awesomesalesforceskills/design-object"><img src="https://agentmods.dev/badge/commands/banibratachatterjee/awesomesalesforceskills/design-object.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 544 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 $0.00000 $0.00544
Opus 5 $0.00000 $0.00272
Sonnet 5 $0.00000 $0.00109
Haiku 4.5 $0.00000 $0.00054

Measured 10d ago against content hash ba23377f3ac0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

design-object 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.

commands/design-object.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/design-object — Design a Setup-ready sObject from a business concept

Wraps agents/object-designer/AGENT.md. Produces a complete object spec + sfdx metadata scaffold + deployment order.


Step 1 — Collect inputs

Ask the user:

1. Business concept (one sentence describing what the object represents)?
   Example: "Track maintenance contracts linked to Accounts, with a primary technician and warranty expiration"

2. Target org alias (required — agent probes for overlapping design)?

3. Expected row volume? small (<100k) / medium (100k-10M) / large (>10M)
   (Default: medium)

4. Integration source (optional)?
   If rows will be sourced from an external system, pass the system name.
   Drives External ID + upsert recommendations.

5. Sensitivity? standard / pii / phi / pci
   (Default: standard; affects encryption + access recommendations)

If the concept is under 8 words or lacks enough signal to infer 3+ fields, STOP and ask clarifying questions.


Step 2 — Load the agent

Read agents/object-designer/AGENT.md + all mandatory reads.


Step 3 — Execute the plan

Follow the 10-step plan exactly:

  1. Probe org for overlapping design
  2. Decide standard vs custom
  3. Generate API name + label per naming conventions
  4. Design the field set
  5. Decide record types (only if persona variance signaled)
  6. Design sharing posture via the sharing-selection decision tree
  7. Plan validation rules at object creation
  8. Plan indexes (LDV objects or integration sources)
  9. Emit the deployment order
  10. Emit the spec + scaffold

Step 4 — Deliver the output

Return the Output Contract:

  • Summary + confidence
  • Design spec
  • Scaffold metadata (fenced XML blocks, one per file)
  • Deployment order
  • Process Observations
  • Citations

Step 5 — Recommend follow-ups

Suggest (but do not auto-invoke):

  • /architect-perms to design the persona PSes for the new object
  • /audit-validation-rules after initial VRs are deployed
  • /design-duplicate-rule if the object is human-identity data
  • /build-flow for any automation on the new object

Read the full file on GitHub · 81 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. 10d ago First seen · 81 lines · 0 tokens per session scan A ba23377f3ac0

Subscribe to this mod's changes

design-object is a command published in the GitHub repository BanibrataChatterjee/AwesomeSalesforceSkills (3 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 544 tokens. 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.