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/go4cas/quiver/add-testgit clone --depth 1 https://github.com/go4cas/quiverWhat 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 | $0.00000 | $0.00714 |
| Opus 5 | $0.00000 | $0.00357 |
| Sonnet 5 | $0.00000 | $0.00143 |
| Haiku 4.5 | $0.00000 | $0.00071 |
Grade A, and why
add-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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write tests for: $ARGUMENTS
The argument is a file path (e.g. src/pages/users/index.js, src/composables/useForm.js, src/framework/router.js).
Follow this process:
Step 1 — Determine test type
| Source location | Test type | Output location |
|---|---|---|
src/framework/*.js |
Unit (Vitest) | tests/framework/<name>.test.js |
src/composables/*.js |
Unit (Vitest) | tests/composables/<name>.test.js |
src/pages/**/*.js |
E2E (Playwright) | tests/e2e/<name>.test.js |
src/components/*.js |
E2E (Playwright) | tests/e2e/<name>.test.js |
src/state/*.js |
Unit (Vitest) | tests/composables/<name>.test.js |
If an existing test file for this source already exists, extend it rather than creating a new one.
Step 2 — Write unit tests (Vitest)
import { describe, it, expect, beforeEach } from 'vitest'
import { functionUnderTest } from '../../src/path/to/file.js'
describe('functionUnderTest', () => {
it('does the expected thing', () => {
expect(functionUnderTest(input)).toBe(expectedOutput)
})
it('handles edge case', () => {
expect(functionUnderTest(edgeInput)).toBe(edgeOutput)
})
})
- Test pure function behaviour and edge cases
- Use
beforeEachto reset any shared state between tests - Do not mock framework internals unless unavoidable
Step 3 — Write E2E tests (Playwright)
import { test, expect } from '@playwright/test'
test.describe('FeatureName', () => {
test.beforeEach(async ({ page }) => {
await page.goto('/')
})
test('happy path', async ({ page }) => {
await page.getByRole('link', { name: 'Nav link' }).click()
await expect(page).toHaveURL(/\/expected-path/)
await expect(page).toHaveTitle('Expected Title')
await expect(page.getByRole('heading', { name: 'Heading' })).toBeVisible()
})
})
- Prefer role-based selectors:
getByRole,getByLabel,getByText - Use
getByTestIdfor elements with no semantic role; adddata-testidattributes to the source if needed - Cover: happy path, key edge cases, error states where applicable
- Do not test implementation details — test what the user sees and can do
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 · 74 lines · 0 tokens per session scan A 23e4e1d1add6
add-test is a command published in the GitHub repository go4cas/quiver (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 714 tokens. 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
verify
Run the right verification gates for what changed.
verify
Grade work that already exists and decide whether it can merge. Runs the project's current unit, integration, and E2E suites plus security scanning and type checking, scores every dimension 0-10, and returns a merge verdict with a VERIFIED-vs-CLAIMED evidence manifest. Writes no test files and edits no source. Use…
run-all-tests-and-fix
Execute the full test suite and systematically fix any failures, ensuring code quality and functionality. All test-related commands must pass before completion.
add-page
Add a page to an existing module.
add-theme
Scaffold a theme: vpr gen:theme $ARGUMENTS.
test-run
Run all tests and report coverage to @chief.