Borrowing it
Nothing to install: this file belongs to Smart-AI-Memory/empathy-framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Smart-AI-Memory/empathy-framework/main/.claude/commands/testing.mdgit clone --depth 1 https://github.com/Smart-AI-Memory/empathy-frameworkWrote 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/commands/smart-ai-memory/empathy-framework/testing)<a href="https://agentmods.dev/commands/smart-ai-memory/empathy-framework/testing"><img src="https://agentmods.dev/badge/commands/smart-ai-memory/empathy-framework/testing/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/commands/smart-ai-memory/empathy-framework/testing"><img src="https://agentmods.dev/badge/commands/smart-ai-memory/empathy-framework/testing.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 | $0.00015 | $0.02215 |
| Opus 5.5 | $0.00006 | $0.00886 |
| Sonnet 5.5 | $0.00003 | $0.00443 |
| Haiku 4.5 | $0.00002 | $0.00221 |
Grade A, and why
testing 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 — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing
Aliases: /test-hub, /tests
Testing operations powered by Socratic agents that help you understand failures and design better tests.
Quick Examples
/testing # Interactive menu
/testing run # Run tests with guided failure analysis
/testing coverage # Coverage analysis with risk prioritization
/testing generate # Batch generate tests to boost coverage
/testing tdd # Test-driven development guidance
/testing benchmark # Performance benchmarking
Discovery
Question:
header: "Task"
question: "What testing task do you need?"
options:
- label: "Run tests"
description: "Execute tests with guided failure analysis"
- label: "Coverage analysis"
description: "Find gaps prioritized by risk"
- label: "TDD workflow"
description: "Test-driven development guidance"
- label: "Benchmarks"
description: "Performance testing and regression detection"
Run Tests
Agent: test-writer | Workflow: test_runner
Execute tests with Socratic failure analysis that helps you understand why tests fail.
Invoke:
/testing run # Run full test suite
/testing run tests/unit/ # Run specific directory
/testing run -k "auth" # Run tests matching pattern
/testing run --failed # Re-run failed tests only
The test-writer agent will:
- Run pytest with your chosen options
- For failures, guide you through understanding why it failed
- Ask: "Where does this value come from? What would cause it to be None?"
- Help you distinguish test bugs from code bugs
- Suggest whether to fix the test or the code
Philosophy: Instead of just showing "AssertionError: None != User", you'll hear "The test expects a User but got None. Let's trace: where does the User come from in this test?"
Coverage Analysis
Agent: quality-validator | Workflow: test_coverage_boost
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 · 324 lines · 15 tokens per session scan A f71d69c2decf
testing is a command published in the GitHub repository Smart-AI-Memory/empathy-framework (13 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 2,215 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
p5-impl-red
Writes unit tests for a feature BEFORE production code exists. Tests must fail.
tdd
Test-driven development with TodoWrite planning and comprehensive testing.
cpp-test
Enforce TDD workflow for C++. Write GoogleTest tests first, then implement. Verify coverage with gcov/lcov.
test-suite
Run comprehensive test suite with coverage analysis.
test
Design or run focused test validation for a task, bug, or diff.
debug
Systematic root-cause investigation, then fix with TDD — never proposes a fix before finding the cause; resumable diagnosis + regression test in .orc/ state. Workspace-aware. For a quick one-off look without session state, prefer the bundled /debug.