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/paruff/ufawkesai/testinggit clone --depth 1 https://github.com/paruff/uFawkesAIWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/paruff/ufawkesai/testing)<a href="https://agentmods.dev/instructions/paruff/ufawkesai/testing"><img src="https://agentmods.dev/badge/instructions/paruff/ufawkesai/testing.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00574 | $0.00574 |
| Opus 5 | $0.00287 | $0.00287 |
| Sonnet 5 | $0.00115 | $0.00115 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
Testing Instructions 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing Instructions
Test-First Discipline
Always write the failing test before the implementation.
The commit order is:
test(scope): failing test for [what you're building]— REDfeat(scope): implement [what you're building]— GREENrefactor(scope): clean up [if needed]— REFACTOR
Never commit a test that already passes before you write the implementation.
Test Categories and Where They Live
| Category | Location | What Goes Here |
|---|---|---|
| Unit | tests/unit/ |
Pure functions in src/utils/ |
| Service | tests/integration/ |
Service functions with Firebase emulator |
| Component | tests/unit/ |
React component rendering and interactions |
| E2E | tests/e2e/ |
BDD scenarios (Cucumber + Playwright) |
Unit Test Pattern
[PLACEHOLDER — replace with your actual test framework and patterns. Example using Jest:]
// tests/unit/utils/compoundInterest.test.ts
import { projectGrowth } from "../../../src/utils/compoundInterest";
describe("projectGrowth", () => {
it("returns initial amount when rate is 0", () => {
expect(projectGrowth(1000, 0, 12)).toBe(1000);
});
it("throws ValidationError for negative principal", () => {
expect(() => projectGrowth(-100, 5, 12)).toThrow(ValidationError);
});
it("handles monthly compounding correctly", () => {
// 1000 at 12% annual = 1126.83 after 12 months
expect(projectGrowth(1000, 12, 12)).toBeCloseTo(1126.83, 1);
});
});
What Every Test Must Have
- A
describeblock named after the function/component being tested - At least one happy path test
- At least one error/edge case test (invalid input, empty state, network failure)
- Descriptive
it()names — read like sentences: "returns X when Y"
What Tests Must NEVER Do
- Call live Firebase (use emulator or mock)
- Have side effects on other tests (clean up state in
afterEach) - Import from
screens/orcomponents/in unit tests forutils/ - Be deleted to make CI pass — fix the code instead
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 · 67 lines · 574 tokens per session scan A 9365fce64f7e
Testing Instructions is an instructions file published in the GitHub repository paruff/uFawkesAI (2 stars, last pushed 12d ago), licensed MIT. It adds 574 tokens to every session, about $0.0029 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 2026-09-03.
Other instructions, from other repositories
agentic-playwright data-strategy.instructions.md
Instructions for idavidov13/agentic-playwright, covering data strategy, critical, file locations, instructions and phase 1: classify the value you need.
instrMCP CLAUDE.md
Instructions for caidish/instrMCP, covering claude.md, development commands, always use conda environment instrmcpdev for testing, unit tests (fast, no hardware required - all mocked) and e2e tests (requires playwright and browser automation).
vibe-mcp AGENTS.md
Instructions for VibeTechnologies/vibe-mcp, covering vibe-mcp agent memory, canonical eval reference, relay and connection semantics, what counts as real e2e and fake extension test harness rules.
trellis copilot-instructions.md
Instructions for craigcossairt/trellis: Read and follow AGENTS.md at the repository root - it is the canonical instruction file for all AI agents on this project. Full methodology docs live in docs/methodology/: TDD workflow, bug-fix protocol, and session habits. Append bug patterns to docs/common-gotchas.md and…
atelier CLAUDE.md
Instructions for ahamedzoha/atelier, covering claude.md, first thing, every session, skills available in this repo, memory and mode reminder.
tokrepo-search-skill AGENTS.md
Instructions for henu-wang/tokrepo-search-skill, covering tokrepo — ai asset registry, search, install, fetch raw content and mcp server.