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 instructions/dev-lou/pixelpilot/ai-test-generationgit clone --depth 1 https://github.com/dev-lou/PixelPilotWhat 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 | $0.03865 | $0.03865 |
| Opus 5 | $0.01932 | $0.01932 |
| Sonnet 5 | $0.00773 | $0.00773 |
| Haiku 4.5 | $0.00386 | $0.00386 |
Grade A, and why
PixelPilot ai-test-generation.instructions.md 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 — 509 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Test Generation 2026
User story → test scenarios → Playwright / Cypress implementation → CI integration. Generates behaviour-focused tests that catch real regressions, not just implementation details.
TESTING PHILOSOPHY
Write tests that resemble how users interact with your application.
— Kent C. Dodds
Tests should catch real regressions, not break on refactors.
Good test: "user can complete checkout" — survives CSS class rename
Bad test: "button has class 'btn-primary'" — breaks on any rename
Rule: Test outcomes, not implementation.
STEP 1 — EXTRACT TEST SCENARIOS FROM USER STORIES
Input format — User Story
As a [role], I want to [action] so that [outcome].
Acceptance criteria:
- [criterion 1]
- [criterion 2]
- [criterion 3]
Process: Story → Scenarios
For each user story, generate test scenarios covering:
## Test Scenarios for: {Story Title}
### Happy Path
1. {Normal, expected flow from start to success}
### Alternate Paths
2. {Alternative but valid path}
3. {Optional step skipped}
### Error Paths
4. {Required field missing}
5. {Invalid input format}
6. {Network/server error during submission}
7. {Session expires mid-flow}
### Edge Cases
8. {Minimum valid input}
9. {Maximum length input}
10. {Special characters in input}
### Accessibility
11. {Complete flow using keyboard only}
12. {Complete flow with screen reader announced states}
STEP 2 — PLAYWRIGHT E2E TESTS
File structure
tests/
├── e2e/
│ ├── auth/
│ │ ├── login.spec.ts
│ │ └── registration.spec.ts
│ ├── checkout/
│ │ ├── checkout-happy-path.spec.ts
│ │ └── checkout-errors.spec.ts
│ └── fixtures/
│ ├── users.ts
│ └── products.ts
├── integration/
│ ├── api/
│ │ └── orders.test.ts
│ └── components/
│ └── CheckoutForm.test.tsx
└── playwright.config.ts
Playwright config
// playwright.config.ts
import { defineConfig, devices } from '@playwright/test';
export default defineConfig({
testDir: './tests/e2e',
fullyParallel: true,
forbidOnly: !!process.env.CI,
retries: process.env.CI ? 2 : 0,
workers: process.env.CI ? 1 : undefined,
reporter: [['html'], ['github']],
use: {
baseURL: process.env.BASE_URL ?? 'http://localhost:3000',
trace: 'on-first-retry',
screenshot: 'only-on-failure',
video: 'retain-on-failure',
},
projects: [
// Setup — create auth state once
{ name: 'setup', testMatch: /.*\.setup\.ts/ },
// Browsers
{
name: 'chromium',
use: { ...devices['Desktop Chrome'] },
dependencies: ['setup'],
},
{
name: 'Mobile Chrome',
use: { ...devices['Pixel 5'] },
dependencies: ['setup'],
},
{
name: 'Mobile Safari',
use: { ...devices['iPhone 14'] },
dependencies: ['setup'],
},
],
webServer: {
command: 'npm run build && npm run start',
url: 'http://localhost:3000',
reuseExistingServer: !process.env.CI,
},
});
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 · 509 lines · 3,865 tokens per session scan A 365ec5543cd5
PixelPilot ai-test-generation.instructions.md is an instructions file published in the GitHub repository dev-lou/PixelPilot (2 stars, last pushed 4mo ago), licensed MIT. It adds 3,865 tokens to every session, about $0.0193 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 instructions, from other repositories
packmind packmind-frontend-navigation-with-react-router.instructions.md
Instructions for PackmindHub/packmind: This codebase uses React Router v7 with organization and space scoping in URLs (e.g., /org/{orgSlug}/space/{spaceSlug}/recipes). To maintain consistency, improve maintainability, and simplify navigati... .
packmind packmind-e2e-page-object.instructions.md
Instructions for PackmindHub/packmind: Write proper PageObjects for our E2E tests .
inspecto CLAUDE.md
Instructions for inspecto-dev/inspecto, covering inspecto — claude code development guide, project overview, monorepo structure, development phases (load each file as needed) and key architectural decisions.
arai CLAUDE.md
Instructions for taniwhaai/arai, covering claude.md — arai, commands, architecture, prompt-collector module (src/promptcollector.rs) and extending the match pipeline.
Design-Learn CLAUDE.md
Instructions for GalaxyXieyu/Design-Learn, covering claude.md, todo, quick start, server and vscode extension.
arai AGENTS.md
Instructions for taniwhaai/arai, covering agents.md — arai, core discipline (non-negotiable), taniwha / subagent rules, work style and tool usage.