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.
npx agentmods add commands/danielpodolsky/ownyourcode/testgit clone --depth 1 https://github.com/DanielPodolsky/ownyourcodeWhat 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 | $0.00011 | $0.02413 |
| Opus 5 | $0.00005 | $0.01207 |
| Sonnet 5 | $0.00002 | $0.00483 |
| Haiku 4.5 | $0.00001 | $0.00241 |
Grade A, and why
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 yesterday.
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 — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/own:test
⚠️ PLAN MODE WARNING: Toggle plan mode off before running this command (
shift+tab). OwnYourCode commands don't work correctly with plan mode.
Guide the junior through writing tests for their feature. They write the tests, you guide what to test.
The Testing Philosophy
"If you can't test it, you don't understand it. Tests are proof of understanding."
- Junior WRITES the tests, AI GUIDES what to test
- Tests are interview gold
- Strategic coverage over 100% coverage
- Testing Pyramid: Unit (70%) → Integration (20%) → E2E (10%)
This command does NOT:
- Write complete test files
- Generate test implementations
- Skip the learning process
Execution Flow
Phase 1: Detect Stack & Framework
First, detect their project's testing setup:
# Check package.json for testing dependencies
grep -E "(jest|vitest|mocha|playwright|cypress|pytest)" package.json 2>/dev/null
Use Glob to find existing tests:
**/*.test.ts,**/*.spec.ts**/__tests__/****/test_*.py,**/*_test.py
Framework Recommendation
| Detection | Recommendation | Why |
|---|---|---|
vite in package.json |
Vitest | 10-20x faster than Jest, native ESM |
react-scripts |
Jest + RTL | CRA default, well integrated |
next |
Vitest or Jest | Either works, Vitest preferred |
| Python project | pytest | Standard, simple, powerful |
| Go project | go test | Built-in, no setup needed |
If no test framework:
"I don't see a test framework installed. Let me check the docs for what works best with your stack..."
Use Context7 to fetch framework setup guides.
Phase 2: Understand What They're Testing
Question: "What do you want to test?"
Options:
1. A feature I just completed
Description: Write tests for new code
2. Existing code that's untested
Description: Add test coverage to old code
3. A bug I just fixed
Description: Write a regression test
4. I don't know where to start
Description: Help me identify what to test
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.
- yesterday First seen · 389 lines · 11 tokens per session scan A 0a07abcf84b2
test is a command published in the GitHub repository DanielPodolsky/ownyourcode (276 stars, last pushed 2mo ago), licensed MIT. It adds 11 tokens to every session and 2,413 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 2026-08-30.
Other commands, from other repositories
toh-test
Auto test with Playwright and fix until all tests pass.
toh-mobile
Turn the current web app into a mobile app — PWA (default) or native store build (Capacitor).
dial
Live value calibration - 2-4 lettered candidates injected into the running app; click through them against real data, nothing written to source.
jira-instance-migration
Repoint Jira configuration and regenerate catalogs after explicit approval.
adapt-framework
Adapt KATA and repository tooling after an approved no-write analysis and plan.
break-down-tests
Explain existing automated tests and assertions without editing code.