oxy:test

A command guide for running evaluation tests on Oxy agents and workflows. These tests check whether configured tasks produce reliable results and meet defined expectations.

In plain words
What is it for?
Use it to test `.agent.yml` and `.workflow.yml` files and inspect their assertions and results.
Why use it?
It makes it easier to select the right file, run its tests, see individual pass or fail results, and review the final summary.

Command

Part of the oxy-skills plugin — 8 skills, 6 commands, 1 agent shipped together

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/oxy-hq/skills/test
Clone the repo
git clone --depth 1 https://github.com/oxy-hq/skills

Or install oxy-skills, the plugin that ships this one along with the rest of its 8 skills, 6 commands, 1 agent.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 659 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 $0.00011 $0.00659
Opus 5 $0.00005 $0.00329
Sonnet 5 $0.00002 $0.00132
Haiku 4.5 $0.00001 $0.00066

Measured 2d ago against content hash 454b5ea444e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

oxy:test 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.

commands/test.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Oxy Agents and Workflows

Run evaluation tests defined in agent or workflow configuration files to validate reliability and output quality.

Pre-Test Steps

  1. Check for Oxy installation

    • Run oxy --version to verify Oxy CLI is installed
    • If not found, inform the user they need to install Oxy first
  2. Determine test file

    • If command invoked with argument (file path), use that file
    • If no argument:
      • Check if there's a currently open file in the editor
      • If it's a .agent.yml or .workflow.yml file, use it
      • Otherwise, ask user to specify which file to test using AskUserQuestion

File Selection (if needed)

If no file specified:

  1. Search for test files using Glob: **/*.agent.yml and **/*.workflow.yml
  2. Use AskUserQuestion to let user select which file to test
  3. Options should show clear file paths

Test Execution

  1. Run tests

    • Execute oxy test <file-path> with default options
    • Use pretty format for readable output
    • Show test progress to user
  2. Monitor test execution

    • Display each test case as it runs
    • Show which assertions pass/fail

Results Summary

After tests complete, provide a clear summary:

If all tests pass:

✅ All tests passed!

File: <file-path>
Test cases: X passed, 0 failed
Accuracy: 100%

Your agent/workflow is ready to use.

If tests fail:

⚠️  Some tests failed

File: <file-path>
Test cases: X passed, Y failed
Accuracy: Z%

Failed tests:
1. [Test name]: [Reason for failure]
2. [Test name]: [Reason for failure]

Review the test configuration and agent/workflow logic.

Error Handling

Common issues:

  • No tests defined: File has no tests: section - inform user they need to add tests
  • File not found: Verify the file path is correct
  • Invalid test format: Check test configuration syntax in the YAML file
  • Execution error: Show the error and suggest checking agent/workflow configuration

Test Options

The command uses these defaults (recommended for most cases):

  • Format: Pretty (human-readable)
  • Threshold mode: Average (overall accuracy)
  • Min accuracy: Not enforced (show results regardless)

Read the full file on GitHub · 102 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. 2d ago First seen · 102 lines · 11 tokens per session scan A 454b5ea444e4

Subscribe to this mod's changes

oxy:test is a command published in the GitHub repository oxy-hq/skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 659 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.