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/srstomp/pokayokay/testgit clone --depth 1 https://github.com/srstomp/pokayokayWhat 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 | $0.00006 | $0.01157 |
| Opus 5 | $0.00003 | $0.00579 |
| Sonnet 5 | $0.00001 | $0.00231 |
| Haiku 4.5 | $0.00001 | $0.00116 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing Strategy Workflow
Design or implement tests for: $ARGUMENTS
Mode Detection
Parse $ARGUMENTS to determine mode:
--auditflag present → Coverage audit mode (creates tasks for gaps)- No flag → Design/implement mode (default behavior)
Agent Delegation
When running tests (not designing strategy), delegate test execution to the yokay-test-runner agent for isolated output. This keeps verbose test output separate from the main conversation.
Use the yokay-test-runner agent to run the test suite.
Return only failures and summary to this conversation.
The agent will:
- Detect test framework (Jest, Vitest, pytest, etc.)
- Run test suite
- Return only failures with context, not all passing tests
Use delegation for:
- Running full test suites
- Verifying fixes
- Pre-commit test runs
Run inline for:
- Writing new tests
- Debugging specific test failures
- Test strategy design
Steps
1. Identify Test Context
Detect from project:
- Framework: React, Vue, Node, etc.
- Test runner: Vitest, Jest, Mocha
- E2E tool: Playwright, Cypress
- Coverage: Current coverage targets
2. Identify Task Type
From $ARGUMENTS, determine the goal:
- Strategy: Design test approach for feature/project
- Unit tests: Write isolated component/function tests
- Integration tests: Test component interactions
- E2E tests: Write end-to-end user flow tests
- Debug: Fix flaky or failing tests
3. Apply Test Pyramid
- Many unit tests (fast, isolated)
- Some integration tests (component interaction)
- Few E2E tests (critical user paths)
4. Execute Task
For Strategy:
- Recommend test types for the feature
- Define coverage targets
- Identify critical paths
- Plan test data strategy
For Implementation:
- Write tests following AAA pattern (Arrange, Act, Assert)
- Use appropriate mocking
- Ensure tests are deterministic
- Add to CI pipeline
For Debugging:
- Identify flakiness source
- Add proper waits/retries
- Isolate test dependencies
- Fix timing issues
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 · 171 lines · 6 tokens per session scan A e175828413fb
test is a command published in the GitHub repository srstomp/pokayokay (9 stars, last pushed 1mo ago), licensed MIT. It adds 6 tokens to every session and 1,157 once invoked, about $0.0000 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.