test-connection

A command that checks whether an Apideck connection works by making a small list request. Apideck is a service that connects applications to business tools through shared APIs.

In plain words
What is it for?
Use it to test CRM contacts, accounting invoices, HR employees, stored files, or recruiting jobs and inspect a sample record when the request succeeds.
Why use it?
It quickly separates connection problems from application code and gives likely fixes for authentication, plan limits, missing services, or authorization.

Command

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 commands/apideck-libraries/api-skills/test-connection
Clone the repo
git clone --depth 1 https://github.com/apideck-libraries/api-skills
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 266 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00015 $0.00266
Opus 5 $0.00008 $0.00133
Sonnet 5 $0.00003 $0.00053
Haiku 4.5 $0.00002 $0.00027

Measured 2d ago against content hash f70ae027db43, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-connection 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 2d 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.

providers/claude/plugin/commands/test-connection.md · 23 lines

What it actually says

Test Apideck Connection

Verify that an Apideck connection is working by making a simple list call:

  1. Accept the unified API name (e.g., crm, accounting, hris) and service ID (e.g., salesforce, quickbooks) from arguments
  2. Use the appropriate SDK to make a list call with limit: 1 to the primary resource for that API:
    • crm → list contacts
    • accounting → list invoices
    • hris → list employees
    • file-storage → list files
    • ats → list jobs
  3. If successful, show the connection status, service name, and a sample record
  4. If it fails, explain the error and provide troubleshooting steps:
    • 401: Check API key, App ID, and Consumer ID
    • 402: Check API plan limits
    • 404: Verify the service ID and that the connection is authorized in Vault
  5. Suggest using Vault to manage the connection if authorization is needed
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. 2d ago First seen · 23 lines · 0 tokens per session scan A f70ae027db43

Subscribe to this mod's changes

test-connection is a command published in the GitHub repository apideck-libraries/api-skills (3 stars, last pushed 3d ago), licensed Apache-2.0. It adds 15 tokens to every session and 266 once invoked, about $0.0001 per session on Opus 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.