agentmods.dev

optimize-soql

optimize-soql is a command for Claude Code from BanibrataChatterjee/AwesomeSalesforceSkills. It costs 0 tokens per session (427 once invoked), scanned A, original, Apache-2.0.

A command that reviews Salesforce Object Query Language (SOQL), the query language used to read Salesforce data, for common problems.

In plain words
What is it for?
Use it to scan selected files or folders for queries inside loops, broad filters, missing security clauses, and requests for every field, then receive ranked fixes and example code changes.
Why use it?
It finds queries that may be slow, unsafe, or inefficient before they cause issues in a Salesforce application.

Command for Claude Code

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

not rated 4repo 6mo ago A scan 0 tokens original Apache-2.0

Good fit Use it to scan selected files or folders for queries inside loops, broad filters, missing security clauses, and requests for every field, then receive ranked fixes and example code changes.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/banibratachatterjee/awesomesalesforceskills/optimize-soql
View source ↗ BanibrataChatterjee/AwesomeSalesforceSkills
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 optimize-soql

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/banibratachatterjee/awesomesalesforceskills/optimize-soql"><img src="https://agentmods.dev/badge/commands/banibratachatterjee/awesomesalesforceskills/optimize-soql.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 427 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 $0.00427
Opus 5.5 $0.00000 $0.00171
Sonnet 5.5 $0.00000 $0.00085
Haiku 4.5 $0.00000 $0.00043

Measured 2mo ago against content hash cd0991700b24, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

optimize-soql 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 2mo 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/optimize-soql.md · 62 lines

What it actually says

/optimize-soql — Find and fix SOQL anti-patterns

Wraps agents/soql-optimizer/AGENT.md. Scans a scope for queries-in-loops, non-selective WHEREs, missing security clauses, and SELECT-star patterns. Returns ranked fixes.

Step 1 — Collect inputs

Ask:

1. What scope should be analyzed?
   File or folder path. Example: force-app/main/default/classes/AccountService.cls
   or: force-app/main/default/classes/

2. Expected record count for any objects queried? (optional — escalates severity for LDV)

3. Target-org alias? (optional — enables live-org context)

Step 2 — Load the agent

Read agents/soql-optimizer/AGENT.md fully + every skill and template listed in its Mandatory Reads.

Step 3 — Execute

Follow the 5-step plan:

  1. Extract every SOQL query in scope
  2. Classify (query-in-loop, select-star, non-selective, no-security, etc.)
  3. Propose before/after fixes for P0 and P1 findings
  4. Recommend centralization if > 3 queries on the same sObject
  5. (Optional) org-side validation

Step 4 — Deliver

  • Summary counts (files, queries, findings by severity)
  • Findings table (file, line, severity, code, one-liner)
  • Per-finding before/after code block for P0 and P1
  • Centralization recommendation
  • Citations

Step 5 — Recommend follow-ups

  • /refactor-apex on any class whose queries should move into a BaseSelector subclass.
  • /score-deployment before shipping selector changes to production.

What this command does NOT do

  • Does not modify files.
  • Does not create custom indexes in the org.
  • Does not attempt to rewrite Database.query(<variable>) dynamic SOQL.
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. 2mo ago First seen · 62 lines · 0 tokens per session scan A cd0991700b24

Subscribe to this mod's changes

optimize-soql is a command published in the GitHub repository BanibrataChatterjee/AwesomeSalesforceSkills (4 stars, last pushed 6mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 427 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.

Databases
Related

optimize-soql compared with commands from other repositories

optimize-soql next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
optimize-soqlBanibrataChatterjee/AwesomeSalesforceSkillsCommand46mo agoApache-2.0A0Claude Code
initfcakyon/claude-codex-settingsCommand1.2ktodayApache-2.0A0Claude Code
securityajitpratap0/GoSQLXCommand1243d agoApache-2.0A21Claude Code
database-setupimsaif/design-with-claudeCommand112d agoMITA36Claude Code
new-migrationRaNDoM6913/claude-code-superkitCommand3todayMITA22Claude Code
json.batch_getstratalab/strata-coreCommand51mo agoApache-2.0A0Claude Code
json.index.dropstratalab/strata-coreCommand51mo agoApache-2.0A0Claude Code