test-writing

test-writing is a skill for Claude Code, Codex from reasvyn/docsgrep. It costs 16 tokens per session (714 once invoked), scanned A, original, MIT.

A testing skill for writing unit and integration tests for docsgrep tool handlers and utilities. It describes how to find comparable tests, mock external file operations, and run Vitest tests.

In plain words
What is it for?
Use it to add tests for docsgrep handlers and utilities, including success and error cases, with mocked file-system and search operations.
Why use it?
It provides project-specific testing patterns, reducing the chance of tests that are inconsistent or depend on real external files.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/reasvyn/docsgrep/test-writing
Any agent
npx skills add reasvyn/docsgrep --skill test-writing
Clone the repo
git clone --depth 1 https://github.com/reasvyn/docsgrep

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for test-writing

README.md
[![agentmods](https://agentmods.dev/badge/skills/reasvyn/docsgrep/test-writing.svg)](https://agentmods.dev/skills/reasvyn/docsgrep/test-writing)
Your own site
<a href="https://agentmods.dev/skills/reasvyn/docsgrep/test-writing"><img src="https://agentmods.dev/badge/skills/reasvyn/docsgrep/test-writing.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 714 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.00714
Opus 5 $0.00008 $0.00357
Sonnet 5 $0.00003 $0.00143
Haiku 4.5 $0.00002 $0.00071

Measured 3d ago against content hash 236040fa1e71, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-writing 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 3d 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.

.agents/skills/test-writing/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Before writing tests

  1. Read AGENTS.md for test commands and conventions.
  2. Find an existing test file for a similar handler and copy its structure.

Run tests

bun run test                          # all tests
bun run vitest run tests/path/to.test.ts  # single file

Unit test pattern

Place in tests/unit/. Mock all external IO at module level:

import { describe, it, expect, vi, beforeEach } from "vitest";
import { handleMyTool } from "../../../src/tools/my-tool.js";

vi.mock("node:fs/promises");
vi.mock("glob");

beforeEach(() => vi.resetAllMocks());

describe("handleMyTool", () => {
  it("returns results", async () => {
    vi.mocked(fs.stat).mockResolvedValue({ isDirectory: () => true } as any);
    vi.mocked(glob).mockResolvedValue(["docs/readme.md"] as any);

    const result = await handleMyTool({ dirPath: "/test" });
    const data = JSON.parse(result.content[0].text);

    expect(data).toHaveProperty("files");
    expect(result.isError).toBeUndefined();
  });

  it("returns error for invalid path", async () => {
    const result = await handleMyTool({ dirPath: "" });
    expect(result.isError).toBe(true);
  });
});

Key rules

  • Mock at module level: vi.mock('node:fs/promises'), vi.mock('glob'), vi.mock('simple-git'), etc.
  • Reset between tests: beforeEach(() => vi.resetAllMocks()).
  • Parse responses: always JSON.parse(result.content[0].text) before asserting on data.
  • Mock shapes: match real return types (e.g., fs.stat needs { isDirectory: () => true }).
  • Conditional mocks: use mockImplementation to return different values per input.

Integration test pattern

Place in tests/integration/. Spawns the real MCP server over stdio:

import { Client } from "@modelcontextprotocol/sdk";
import { StdioClientTransport } from "@modelcontextprotocol/sdk";
import path from "node:path";
import { fileURLToPath } from "node:url";

const __dirname = path.dirname(fileURLToPath(import.meta.url));
const serverPath = path.join(__dirname, "..", "..", "src", "index.ts");

let transport: StdioClientTransport;
let client: Client;

beforeAll(async () => {
  transport = new StdioClientTransport({ command: "npx", args: ["tsx", serverPath] });
  client = new Client({ name: "test-client", version: "1.0.0" }, { capabilities: {} });
  await client.connect(transport);
}, 30000);

afterAll(async () => { await client.close(); });

Read the full file on GitHub · 88 lines

Changes

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.

  1. 3d ago First seen · 88 lines · 16 tokens per session scan A 236040fa1e71

Subscribe to this mod's changes

test-writing is a skill published in the GitHub repository reasvyn/docsgrep (0 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 714 once invoked, about $0.0001 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.

Related

Other skills, from other repositories