tommymorgan:test

A test command that reads project plans when available and chooses browser, API, or command-line testing from their scenarios or description.

In plain words
What is it for?
Use it to test planned UI flows, REST or GraphQL endpoints, and command-line behavior. Without a plan, describe the task and let it determine a suitable test type.
Why use it?
It removes the need to decide manually which kind of test fits each task. It can check planned user requirements and technical details against the implementation.

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/tommymorgan/claude-plugins/test
Clone the repo
git clone --depth 1 https://github.com/tommymorgan/claude-plugins
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,036 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 $0.00020 $0.01036
Opus 5 $0.00010 $0.00518
Sonnet 5 $0.00004 $0.00207
Haiku 4.5 $0.00002 $0.00104

Measured 2d ago against content hash 91e675d07b39, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tommymorgan: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.

tommymorgan/testing/commands/test.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Smart Test Command

Intelligent test command that adapts to context:

  • Plan-aware mode: Reads Gherkin scenarios from plan and validates implementation
  • Standalone mode: Parses description to determine appropriate test type

Workflow

Step 1: Detect Plan File

Search for plan file in current project:

# Look in project plans directories
find . -path "*/plans/*.md" -type f | grep -E "(apps|libs|tools)" | sort -r | head -1

If plan file found, go to Step 2: Plan-Aware Mode If no plan file, go to Step 3: Standalone Mode

Step 2: Plan-Aware Mode

When plan file exists, use Gherkin scenarios to guide testing:

  1. Read the plan file:

    Read(<plan_file_path>)
    
  2. Parse Gherkin sections:

    • Extract User Requirements section → Browser testing scenarios
    • Extract Technical Specifications section → API/CLI testing scenarios
  3. Determine test types based on Gherkin content:

    For User Requirements (always browser testing):

    • User-focused scenarios test UI flows
    • Launch browser-explorer agent

    For Technical Specifications (analyze keywords):

    • API indicators: "endpoint", "POST", "GET", "REST", "GraphQL", "status code" → Launch api-explorer agent
    • CLI indicators: "command", "script", "shell", "exit code", "stdout" → Launch cli-tester agent
  4. Launch appropriate agents:

    For browser testing:

    Task({
      subagent_type: "tommymorgan:browser-explorer",
      description: "Test User Requirements scenarios",
      prompt: `Validate implementation against User Requirements:
    

${user_requirements_gherkin}

Test each scenario systematically. Report findings.` })


For API testing:
```typescript
Task({
  subagent_type: "tommymorgan:api-explorer",
  description: "Test Technical Specifications",
  prompt: `Validate API implementation against Technical Specifications:

${technical_specs_gherkin}

Test endpoints, authentication, error handling. Report findings.`
})

Read the full file on GitHub · 175 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 · 175 lines · 20 tokens per session scan A 91e675d07b39

Subscribe to this mod's changes

tommymorgan:test is a command published in the GitHub repository tommymorgan/claude-plugins (4 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 1,036 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.