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/yurakawa/mskills/testinggit clone --depth 1 https://github.com/yurakawa/mskillsWhat 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 | $0.00541 | $0.00541 |
| Opus 5 | $0.00270 | $0.00270 |
| Sonnet 5 | $0.00108 | $0.00108 |
| Haiku 4.5 | $0.00054 | $0.00054 |
Grade A, and why
mskills testing.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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing Instructions
Test Framework
This project uses Vitest for testing.
Test File Location
- Co-locate test files with source files
- Naming:
filename.test.ts(e.g.,manager.test.tsformanager.ts)
Test Structure
import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';
describe('Feature Name', () => {
beforeEach(() => {
// Setup
});
afterEach(() => {
// Cleanup
});
it('should do something specific', async () => {
// Arrange
const input = 'test';
// Act
const result = await functionUnderTest(input);
// Assert
expect(result).toBe(expected);
});
});
Mocking
File System Operations
When mocking Node.js built-in modules, the mock path must match the import statement. If you import with the node: protocol, use the same protocol in the mock:
// If importing with node: protocol
import fs from 'node:fs/promises';
// Mock with the same path
vi.mock('node:fs/promises', () => ({
default: {
readFile: vi.fn(),
writeFile: vi.fn(),
mkdir: vi.fn(),
// ... other methods
},
}));
External Libraries
Mock chalk and ora to avoid terminal output during tests:
vi.mock('chalk', () => ({
default: {
green: vi.fn((text) => text),
red: vi.fn((text) => text),
cyan: vi.fn((text) => text),
},
}));
vi.mock('ora', () => ({
default: vi.fn(() => ({
start: vi.fn().mockReturnThis(),
succeed: vi.fn(),
fail: vi.fn(),
})),
}));
Test Coverage
- Test both success and error paths
- Test edge cases (empty inputs, invalid data, etc.)
- Verify error messages and exit codes
- Mock external dependencies (file system, network, etc.)
Running Tests
- Run all tests:
npm test - Tests run automatically on build via the prepare script
- Vitest runs in watch mode by default during development
Assertions
- Use descriptive assertion messages
- Prefer specific assertions (
toBe,toEqual,toThrow) over generic ones - Test async functions with
awaitand handle rejections appropriately
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 · 106 lines · 541 tokens per session scan A aa7b57f8869b
mskills testing.instructions.md is an instructions file published in the GitHub repository yurakawa/mskills (3 stars, last pushed 4mo ago), licensed MIT. It adds 541 tokens to every session, about $0.0027 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
mcp-steroid CLAUDE.md
Instructions for jonnyzzz/mcp-steroid, covering claude.md, agents.md, design philosophy, recursive context lookup (do this before sub-folder work), sub-folder guides and must do.
vitaecontext copilot-instructions.md
Copilot instructions for vitaecontext/vitaecontext, covering repository instructions for github copilot, repository model, coding and documentation rules and validation.
open-pr CLAUDE.md
Instructions for TOMOSIA-VIETNAM/open-pr, covering claude.md, plugin, layout, how to work and hard edges (product breaks if ignored).
cavil-loop AGENTS.md
Instructions for GigleAI/cavil-loop, covering agents.md, what this project is, directory layout, conventions and shell scripts.
rig AGENTS.md
Instructions for githubnext/rig, covering agents.md, project overview, architecture, commands and code style.
excalidraw-icons-mcp CLAUDE.md
Instructions for iagogfe/excalidraw-icons-mcp, covering excalidraw-icons-mcp, ci, conventions, code style and comments.