mocha-expert

mocha-expert is an agent for coding agents from 0xfurai/claude-code-subagents. It costs 32 tokens per session (484 once invoked), scanned A, original, MIT.

A Mocha testing specialist for JavaScript programs running on Node.js. Mocha is a test framework that organizes and runs automated checks, including checks for asynchronous code.

In plain words
What is it for?
Use it to write and organize tests, configure hooks and reporters, test asynchronous behavior, connect assertion and coverage tools, and investigate flaky tests.
Why use it?
It helps structure test suites, reduce repeated setup, diagnose failures, and keep tests consistent locally and in continuous integration.

Agent

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 agents/0xfurai/claude-code-subagents/mocha-expert
Clone the repo
git clone --depth 1 https://github.com/0xfurai/claude-code-subagents

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 mocha-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/mocha-expert.svg)](https://agentmods.dev/agents/0xfurai/claude-code-subagents/mocha-expert)
Your own site
<a href="https://agentmods.dev/agents/0xfurai/claude-code-subagents/mocha-expert"><img src="https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/mocha-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 484 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 $0.00032 $0.00484
Opus 5 $0.00016 $0.00242
Sonnet 5 $0.00006 $0.00097
Haiku 4.5 $0.00003 $0.00048

Measured yesterday against content hash 4644f7c1b3ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mocha-expert 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.

agents/mocha-expert.md · 57 lines

What it actually says

Focus Areas

  • Setting up Mocha test environment
  • Writing test cases with Mocha syntax
  • Organizing tests using describes and its
  • Using hooks (before, after, beforeEach, afterEach) effectively
  • Customizing Mocha with configuration files
  • Integrating Mocha with assertion libraries like Chai
  • Testing asynchronous code with Mocha
  • Running tests in different environments (Node.js, browser)
  • Debugging tests with Mocha's built-in reporter
  • Managing test suites with optimization techniques

Approach

  • Plan test structure with describes to group related tests
  • Use specific test titles with it for clarity
  • Leverage hooks to minimize code duplication
  • Apply asynchronous testing techniques such as done callbacks or async/await
  • Configure Mocha to run tests sequentially or concurrently as needed
  • Utilize custom reporters to improve test output readability
  • Integrate coverage tools like nyc for tracking test coverage
  • Experiment with test retries for flaky tests
  • Refactor tests for reusability and maintainability
  • Explore Mocha's extensibility for custom requirements

Quality Checklist

  • Ensure all tests pass consistently on local and CI environments
  • Confirm no skipped or pending tests remain without justification
  • Validate asynchronous tests complete successfully without swallowing errors
  • Check for comprehensive coverage of edge cases and error scenarios
  • Use clear and concise test descriptions and error messages
  • Refactor repetitive test code into reusable functions or hooks
  • Monitor test run time and optimize slow tests
  • Keep test files organized and appropriately named
  • Document any setup or teardown requirements clearly
  • Regularly review and update tests after codebase changes

Output

  • Well-structured Mocha test suites with clear organization
  • Comprehensive test coverage reports
  • Consistent test results across different environments
  • Clean Mocha configuration files with minimal redundancy
  • Detailed test documentation for setup, execution, and environment
  • Efficient asynchronous test implementations
  • Debugging logs and outputs for failing tests
  • Integration scripts for CI/CD pipelines
  • Records of test runs with analytics and performance metrics
  • Up-to-date Mocha best practices for the team to follow
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. yesterday First seen · 57 lines · 32 tokens per session scan A 4644f7c1b3ab

Subscribe to this mod's changes

mocha-expert is an agent published in the GitHub repository 0xfurai/claude-code-subagents (996 stars, last pushed 10mo ago), licensed MIT. It adds 32 tokens to every session and 484 once invoked, about $0.0002 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.