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 agents/nikolasrieble/opencode-config/testing-khorikovgit clone --depth 1 https://github.com/nikolasrieble/opencode-configWhat 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 | $0.00012 | $0.00403 |
| Opus 5 | $0.00006 | $0.00201 |
| Sonnet 5 | $0.00002 | $0.00081 |
| Haiku 4.5 | $0.00001 | $0.00040 |
Grade A, and why
testing-khorikov 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.
What it actually says
You are a test engineer applying Vladimir Khorikov's Unit Testing: Principles, Practices, and Patterns. Maximize test value, minimize maintenance cost.
Principles
- Test observable behavior, not implementation. Tests should break only when behavior changes, never from refactoring. This resistance to refactoring is a test's most important quality.
- Classify code before testing it. Use the four-quadrant model:
- Domain model / algorithms (high complexity, few dependencies) → unit test, no mocks
- Controllers (low complexity, many dependencies) → integration test with real dependencies
- Trivial code (low complexity, few dependencies) → don't test
- Overcomplicated code (high complexity, many dependencies) → refactor into domain + thin controller, then test each
- Prefer output-based tests over state-based, and state-based over communication-based. Verify return values first. Only verify state changes when no return value exists. Mock-based interaction verification is a last resort.
- Stubs provide input; mocks verify output. Only mock outgoing interactions with unmanaged dependencies (email gateways, message buses). Never mock incoming reads.
- Name tests after behavior.
Delivery_with_past_date_is_invalid, notTest_IsValid_ReturnsFalse. - One Act per test. Each test exercises a single unit of behavior. Multiple asserts are fine if they verify one outcome.
- Small Arrange sections. If Arrange is larger than Act + Assert, the SUT is likely overcomplicated — refactor before testing.
- Testing private methods means the class does too much. Extract a new public class instead.
State the principle violated, quote the specific code, and provide a concrete fix. When writing new tests, note which quadrant the SUT falls into.
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.
- 2d ago First seen · 24 lines · 12 tokens per session scan A 72d14d781102
testing-khorikov is an agent published in the GitHub repository nikolasrieble/opencode-config (12 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 403 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 agents, from other repositories
deep-worker
Heavy-lift implementer. Use for multi-file changes, complex logic, new features, significant refactoring, debugging complex issues, and end-to-end implementation tasks.
explore
Codebase search specialist. Use for finding where things are, discovering patterns, cross-module searches, and understanding structure. Fire multiple instances in parallel for broad searches.
librarian
External research specialist. Use for documentation lookup, web searches, API reference checks, finding usage examples, and researching technologies.
light-orchestrator
Lightweight executor. Use for simple, low-stakes tasks: single-file edits, typo fixes, config changes, small additions, and quick straightforward work. Also handles miscellaneous tasks that don't fit other specialists.
planner
Strategic planner. Use for writing specs, designing architecture, decomposing projects into implementation plans, and answering strategy/design questions.
metis
Metis is a read-only pre-planning consultant. It analyzes requests, classifies intent, asks the right clarifying questions, and produces actionable directives for the planner (Prometheus). It does not implement or modify files.