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/lirantal/agent-rules/testinggit clone --depth 1 https://github.com/lirantal/agent-rulesWhat 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 | $0.06713 | $0.06713 |
| Opus 5 | $0.03356 | $0.03356 |
| Sonnet 5 | $0.01343 | $0.01343 |
| Haiku 4.5 | $0.00671 | $0.00671 |
Grade A, and why
agent-rules testing.instructions.md scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
To test command-line tools, use `node:child_process` to execute the CLI and assert on its output. For asynchronous operations where you need to capture streamed output or handle more complex interactions, using `exec` wi How it starts
The opening of the file, as written. The whole thing — 715 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing Guidelines for Node.js applications
This document outlines the rules and guidelines for AI agents generating test code for modern Node.js applications.
The following are project tests code standards, principles and strategy for for JavaScript and TypeScript projects that you should apply and follow if you are working on a task related to writing tests, updating existing tests, or overall refactoring and making changes to test code.
General Testing Principles
Guiding Principles
- Modern Node.js: All test code must be compatible with Node.js version 22 and above.
- Latest JavaScript: Utilize the latest JavaScript features (ES2022 and beyond), including top-level
awaitand modern syntax. - Built-in Tools: Exclusively use the built-in Node.js test runner (
node:test) and assertion library (node:assert). No third-party testing frameworks (e.g., Jest, Mocha, Chai) should be used. - ES Modules: All code should be written using ES Modules (
import/export). CommonJS (require) should be avoided. - Asynchronous Focus: Tests should be written with an
async-first mindset, effectively handling promises and asynchronous operations. - Clarity and Readability: Tests should be easy to understand. Use descriptive names for
describeblocks andtestcases.
Descriptive Test Naming (Three-Part Structure)
A well-named test clearly communicates its purpose, making test reports more informative and debugging easier for anyone, regardless of their familiarity with the codebase. Adopt a three-part structure for your test names:
- What is being tested? (The unit under test, e.g.,
ProductsService.addNewProduct) - Under what circumstances/scenario? (The specific conditions, e.g.,
no price is passed to the method) - What is the expected result? (The outcome, e.g.,
the new product is not approved)
This structure ensures that a failing test immediately tells you what broke, when it broke, and what the expected behavior was.
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 · 715 lines · 6,713 tokens per session scan A b04fff89ddc7
agent-rules testing.instructions.md is an instructions file published in the GitHub repository lirantal/agent-rules (62 stars, last pushed 14d ago), licensed Apache-2.0. It adds 6,713 tokens to every session, about $0.0336 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
skill-bill AGENTS.md
AGENTS.md instructions for oila-gmbh/skill-bill, covering agents.md, project context, product intent, taxonomy and source and generated files.
backend-pro-max-skill CLAUDE.md
Instructions for shashankswe2020-ux/backend-pro-max-skill, covering claude.md, project overview, search command, useful flags and domains.
skill-bill CLAUDE.md
Claude Code instructions for oila-gmbh/skill-bill, a project described as: SkillBill packages your engineering judgment into governed skills, then uses a durable Kotlin runtime to ensure agents actually execute that process consistently, resumably, and with bounded context.
claude-code-settings copilot-instructions.md
Instructions for feiskyer/claude-code-settings, covering claude.md, environment setup, required dependencies, configuration and skills.
turbo-flow CLAUDE.md
Claude Code instructions for marcuspat/turbo-flow, covering claude.md — turbo flow, what this repo is, key files and conventions.
Elliot CLAUDE.md
Instructions for EliBarak12/Elliot, covering elliot — claude.md, project mission, before every push — mandatory checks, branch strategy and rules.