Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add tsmztech/claude-code-plugins/plugin install salesforce-cliWrote 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/skills/tsmztech/claude-code-plugins/data-query)<a href="https://agentmods.dev/skills/tsmztech/claude-code-plugins/data-query"><img src="https://agentmods.dev/badge/skills/tsmztech/claude-code-plugins/data-query/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/skills/tsmztech/claude-code-plugins/data-query"><img src="https://agentmods.dev/badge/skills/tsmztech/claude-code-plugins/data-query.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 | $0.00180 | $0.03871 |
| Opus 5.5 | $0.00072 | $0.01548 |
| Sonnet 5.5 | $0.00036 | $0.00774 |
| Haiku 4.5 | $0.00018 | $0.00387 |
Grade A, and why
data-query 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.
How it starts
The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SOQL Query
Run any SOQL query against a connected Salesforce org. This skill handles all query types through dedicated scripts optimized for each pattern.
Prerequisites
You must be authenticated to a Salesforce org before running queries. If not authenticated, run the authentication script first.
Authentication
If the user is not authenticated or gets an auth error, run the authentication script:
node ${CLAUDE_PLUGIN_ROOT}/scripts/sf-auth.js --status
To authenticate interactively (opens browser):
node ${CLAUDE_PLUGIN_ROOT}/scripts/sf-auth.js --alias <alias>
To authenticate to a sandbox:
node ${CLAUDE_PLUGIN_ROOT}/scripts/sf-auth.js --alias <alias> --instance-url https://test.salesforce.com
See scripts/sf-auth.js --help for all authentication options.
Query Types & Scripts
This skill provides three scripts, one for each query pattern. Choose the right one based on what the user needs.
Note: For aggregate queries (SUM, AVG, MIN, MAX with GROUP BY / ROLLUP / CUBE / HAVING), use the
salesforce-cli:aggregate-queryskill instead.
1. Standard Query (includes child-to-parent dot notation)
Use for normal SELECT queries, including traversing parent relationships via dot notation.
node ${CLAUDE_PLUGIN_ROOT}/skills/data-query/scripts/query.js "<SOQL>" [options]
Examples
# Simple query
node ${CLAUDE_PLUGIN_ROOT}/skills/data-query/scripts/query.js "SELECT Id, Name FROM Account LIMIT 10"
# With WHERE clause
node ${CLAUDE_PLUGIN_ROOT}/skills/data-query/scripts/query.js "SELECT Id, Name FROM Account WHERE Industry = 'Technology' AND AnnualRevenue > 1000000"
# Child-to-parent dot notation (up to 5 levels)
node ${CLAUDE_PLUGIN_ROOT}/skills/data-query/scripts/query.js "SELECT Id, Name, Account.Name, Account.Owner.Name FROM Contact WHERE Account.Industry = 'Finance'"
# Custom relationship dot notation (__r instead of __c)
node ${CLAUDE_PLUGIN_ROOT}/skills/data-query/scripts/query.js "SELECT Id, Broker__r.Name, Broker__r.Email FROM Property__c"
# ORDER BY, LIMIT, OFFSET
node ${CLAUDE_PLUGIN_ROOT}/skills/data-query/scripts/query.js "SELECT Id, Name, CreatedDate FROM Account ORDER BY CreatedDate DESC LIMIT 20 OFFSET 10"
# Date literals
node ${CLAUDE_PLUGIN_ROOT}/skills/data-query/scripts/query.js "SELECT Id, Name FROM Opportunity WHERE CloseDate = LAST_N_DAYS:30"
# LIKE operator with wildcards
node ${CLAUDE_PLUGIN_ROOT}/skills/data-query/scripts/query.js "SELECT Id, Name FROM Account WHERE Name LIKE 'Acme%'"
# IN operator
node ${CLAUDE_PLUGIN_ROOT}/skills/data-query/scripts/query.js "SELECT Id, Name FROM Account WHERE Industry IN ('Technology', 'Finance', 'Healthcare')"
# INCLUDES/EXCLUDES for multi-select picklists
node ${CLAUDE_PLUGIN_ROOT}/skills/data-query/scripts/query.js "SELECT Id, Name FROM Lead WHERE LeadSource INCLUDES ('Web', 'Phone')"
# USING SCOPE
node ${CLAUDE_PLUGIN_ROOT}/skills/data-query/scripts/query.js "SELECT Id, Name FROM Account USING SCOPE Mine"
# WITH SECURITY_ENFORCED
node ${CLAUDE_PLUGIN_ROOT}/skills/data-query/scripts/query.js "SELECT Id, Name FROM Account WITH SECURITY_ENFORCED"
# TYPEOF for polymorphic relationships
node ${CLAUDE_PLUGIN_ROOT}/skills/data-query/scripts/query.js "SELECT TYPEOF What WHEN Account THEN Name, Phone WHEN Opportunity THEN Name, Amount ELSE Name END FROM Event"
# FIELDS() function
node ${CLAUDE_PLUGIN_ROOT}/skills/data-query/scripts/query.js "SELECT FIELDS(ALL) FROM Account LIMIT 200"
node ${CLAUDE_PLUGIN_ROOT}/skills/data-query/scripts/query.js "SELECT FIELDS(STANDARD) FROM Contact"
node ${CLAUDE_PLUGIN_ROOT}/skills/data-query/scripts/query.js "SELECT FIELDS(CUSTOM) FROM Opportunity LIMIT 200"
# FORMAT() and toLabel()
node ${CLAUDE_PLUGIN_ROOT}/skills/data-query/scripts/query.js "SELECT Id, FORMAT(Amount), toLabel(StageName) FROM Opportunity LIMIT 5"
# convertCurrency() for multi-currency orgs
node ${CLAUDE_PLUGIN_ROOT}/skills/data-query/scripts/query.js "SELECT Id, convertCurrency(Amount) FROM Opportunity"
# DISTANCE() and GEOLOCATION() for location-based queries
node ${CLAUDE_PLUGIN_ROOT}/skills/data-query/scripts/query.js "SELECT Id, Name, BillingLatitude, BillingLongitude FROM Account WHERE DISTANCE(BillingAddress, GEOLOCATION(37.7749, -122.4194), 'mi') < 50 ORDER BY DISTANCE(BillingAddress, GEOLOCATION(37.7749, -122.4194), 'mi')"
# FOR VIEW / FOR REFERENCE / FOR UPDATE
node ${CLAUDE_PLUGIN_ROOT}/skills/data-query/scripts/query.js "SELECT Id, Name FROM Account FOR VIEW"
# Against a specific org
node ${CLAUDE_PLUGIN_ROOT}/skills/data-query/scripts/query.js "SELECT Id, Name FROM Account LIMIT 5" --target-org myDevOrg
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 318 lines · 180 tokens per session scan A a249c2887a31
data-query is a skill published in the GitHub repository tsmztech/claude-code-plugins (2 stars, last pushed 8mo ago), licensed MIT. It adds 180 tokens to every session and 3,871 once invoked, about $0.0007 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 skills, from other repositories
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
platform-custom-field-generate
Use when users create, generate, or validate Salesforce Custom Field metadata. Trigger on custom fields, field types, Roll-Up Summary, Master-Detail/Lookup relationships, formula fields, picklists, dependent (controlling) picklists, referencing a value set from a field, or scoping picklist values per record type; also…
field-service-sobject-create-configure
Headless 360 REST API deployment step for creating sObject records. Handles describe-based field discovery, required-field derivation, entity-relationship ordering, and composite graph transactions. Use this skill when a designer skill (or a user directly) needs to create sObject records after design confirmation…
durable-objects
Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.
nornicdb-grpc
Drive NornicDB over gRPC — the Qdrant-compatible surface (Collections, Points, Snapshots) plus the additive NornicSearch service. Use when ingesting via Qdrant SDKs, migrating from Qdrant, or running hybrid text+vector search from a non-Bolt client. Covers connection, RPC catalog, collection→database mapping…
nw-ddd-eventsourcing
Event Sourcing and CQRS as DDD implementation patterns — when to use, aggregate event streams, projections, snapshots, sagas, upcasting, conflict resolution.