documcp-test

documcp-test is an agent for Claude Code from tosin2013/documcp. It costs 15 tokens per session (844 once invoked), scanned A, original, MIT.

Project instructions for writing tests for DocuMCP, including unit, integration, API, end-to-end, memory, benchmark, and edge-case tests. They define coverage targets and reusable test patterns.

In plain words
What is it for?
Use them when adding tests for DocuMCP tools, integrations, APIs, functional workflows, benchmarks, or unusual and failing inputs.
Why use it?
They provide a consistent way to verify tools and error handling without each test author inventing a separate structure.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Not installable on its own: it reads a path above its own folder, which only exists inside its repository. The line is import { formatMCPResponse } from "../../src/types/api.js";.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code.

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 documcp-test

README.md
[![agentmods](https://agentmods.dev/badge/agents/tosin2013/documcp/documcp-test.svg)](https://agentmods.dev/agents/tosin2013/documcp/documcp-test)
Your own site
<a href="https://agentmods.dev/agents/tosin2013/documcp/documcp-test"><img src="https://agentmods.dev/badge/agents/tosin2013/documcp/documcp-test.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 844 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 5.1 $0.00015 $0.00844
Opus 5 $0.00008 $0.00422
Sonnet 5 $0.00003 $0.00169
Haiku 4.5 $0.00002 $0.00084

Measured 6d ago against content hash f0f19ae55c5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

documcp-test 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 6d 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.

.github/agents/documcp-test.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert at writing tests for DocuMCP.

Testing Strategy

Coverage Requirements

  • Global: 80% (branches, functions, lines, statements)
  • Complex tools (e.g., recommend-ssg.ts): 60%
  • Excluded: Experimental memory features, src/index.ts

Test Structure

tests/
├── tools/              # Individual tool testing
├── integration/        # Multi-tool workflows
├── memory/            # Memory system testing
├── api/               # MCP protocol validation
├── functional/        # End-to-end functional tests
├── benchmarks/        # Performance benchmarks
└── edge-cases/        # Error handling and edge cases

Tool Test Pattern

import { myTool } from "../../src/tools/my-tool.js";
import { formatMCPResponse } from "../../src/types/api.js";
import { promises as fs } from "fs";
import path from "path";
import { tmpdir } from "os";

describe("myTool", () => {
  let testDir: string;

  beforeEach(async () => {
    testDir = path.join(tmpdir(), `test-${Date.now()}`);
    await fs.mkdir(testDir, { recursive: true });
  });

  afterEach(async () => {
    await fs.rm(testDir, { recursive: true, force: true });
  });

  it("should return success for valid input", async () => {
    const result = await myTool({
      path: testDir,
      depth: "standard",
    });

    expect(result.success).toBe(true);
    expect(result.data).toBeDefined();
    expect(result.metadata.toolVersion).toBeDefined();
    expect(result.metadata.executionTime).toBeGreaterThan(0);
  });

  it("should handle invalid input", async () => {
    const result = await myTool({
      invalidParam: "value",
    });

    expect(result.success).toBe(false);
    expect(result.error).toBeDefined();
    expect(result.error.code).toBe("TOOL_ERROR");
  });

  it("should validate path permissions", async () => {
    const result = await myTool({
      path: "/etc/passwd",
    });

    expect(result.success).toBe(false);
    expect(result.error.message).toContain("permission");
  });
});

Read the full file on GitHub · 146 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. 6d ago First seen · 146 lines · 15 tokens per session scan A f0f19ae55c5b

Subscribe to this mod's changes

documcp-test is an agent published in the GitHub repository tosin2013/documcp (10 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 844 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 agents, from other repositories

test-automator

Use this agent when you need to create comprehensive test suites, improve test coverage, or set up test automation infrastructure. This includes writing unit tests with mocks, integration tests with test containers, E2E tests with Playwright/Cypress, configuring CI/CD pipelines for testing, or establishing test data…

czlonkowski/n8n-mcp · 0 tokens

test-generator

Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.

travisjneuman/.claude · 27 tokens

testing

You are the TESTING agent for increment [INCREMENTID].

anton-abyzov/specweave · 0 tokens

qa

Use proactively when user asks to write tests, add test coverage, or check edge cases. Writes Vitest unit tests and Playwright E2E tests. Runs linting, type checking, and detects edge cases.

dlupiak/claude-session-dashboard · 45 tokens

tester

Use this agent when you need to create, maintain, or improve tests for your codebase. This includes writing unit tests for new functions or components, creating integration tests for API endpoints or user workflows, updating existing tests after code changes, reviewing test coverage, or establishing testing patterns…

ecorkran/context-forge · 252 tokens

backend-test-engineer

Backend test engineer for Arthur MCP. Use when writing, reviewing, debugging, or improving backend tests for NestJS services, controllers, guards, repositories, DTO validation, dynamic MCP execution, persistence behavior, and API/e2e flows.

alexmmatos/arthur-mcp · 52 tokens