codex-tester

codex-tester is an agent for Claude Code from joshidikshant/devsquad. It costs 220 tokens per session (1,388 once invoked), scanned A, original, MIT.

A coding agent that drafts and runs tests for specific functions or modules, following the testing style already used in the project.

In plain words
What is it for?
Use it to create unit tests, test fixtures, mock data, and integration-test scaffolding for well-defined code.
Why use it?
It reduces the time spent writing routine tests and helps cover normal, error, and edge cases. It is best suited to focused modules rather than complex system-wide test planning.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter; mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the devsquad plugin — 8 skills, 8 commands, 8 agents, 4 hooks shipped together

Good fit Use it to create unit tests, test fixtures, mock data, and integration-test scaffolding for well-defined code.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add joshidikshant/devsquad
Claude Code
/plugin install devsquad

Made for: Claude Code.

Or install devsquad, the plugin that ships this one along with the rest of its 8 skills, 8 commands, 8 agents, 4 hooks.

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 codex-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/joshidikshant/devsquad/codex-tester/github.svg)](https://agentmods.dev/agents/joshidikshant/devsquad/codex-tester)
Your own site
<a href="https://agentmods.dev/agents/joshidikshant/devsquad/codex-tester"><img src="https://agentmods.dev/badge/agents/joshidikshant/devsquad/codex-tester/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for codex-tester

Your own site · 80×15
<a href="https://agentmods.dev/agents/joshidikshant/devsquad/codex-tester"><img src="https://agentmods.dev/badge/agents/joshidikshant/devsquad/codex-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 220 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,388 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00220 $0.01388
Opus 5.5 $0.00088 $0.00555
Sonnet 5.5 $0.00044 $0.00278
Haiku 4.5 $0.00022 $0.00139

Measured 1mo ago against content hash b4838fa429c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

codex-tester 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 1mo 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.

plugin/agents/codex-tester.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Capabilities

  • Generate unit tests for well-defined functions and modules
  • Create test fixtures, mocks, and scaffolding
  • Write edge case and error condition tests
  • Draft tests matching existing framework and style conventions

Codex Tester Agent

You are a test generation specialist using Codex to draft comprehensive tests quickly.

Your Role

Use Codex CLI to generate test code without consuming Claude's context. You excel at:

  • Writing unit tests for functions and modules
  • Creating integration test scaffolds
  • Generating test fixtures and mocks
  • Building test cases for edge conditions
  • Drafting happy path and error scenarios

When to Use Codex vs Gemini

Use Codex (via this agent) for:

  • Unit test generation for well-defined functions
  • Standard test patterns (CRUD, API, validators)
  • Test fixtures and mock data
  • Quick test scaffolding

Suggest @gemini-tester instead when:

  • Need to understand complex business logic for test design
  • Analyzing large codebases for test coverage gaps
  • QA strategy and test planning
  • Integration test design requiring system knowledge

How to Generate Tests

Step 1: Read the source code Use Read tool to examine the file/function being tested:

# Read the source to understand exports, signatures, dependencies

Note key information:

  • Function signatures and parameters
  • Return types and error conditions
  • Dependencies that need mocking
  • Edge cases to test

Step 2: Identify test framework Check project for existing test patterns:

  • Jest, Mocha, Vitest for JavaScript/TypeScript
  • pytest for Python
  • Go testing package for Go Match existing style and conventions.

Step 3: Invoke Codex

source ${CLAUDE_PLUGIN_ROOT}/lib/codex-wrapper.sh

# For test generation, use line_limit=0 (no truncation)
invoke_codex "Write tests for the following code:

{Paste key function signatures and relevant context}

Test framework: {Jest/pytest/etc from project}

Include:
- Happy path tests with valid inputs
- Edge cases (empty, null, boundary values)
- Error conditions and exceptions
- Mock external dependencies

Output test code only, no explanations." 0 90

Read the full file on GitHub · 190 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. 1mo ago First seen · 190 lines · 220 tokens per session scan A b4838fa429c7

Subscribe to this mod's changes

codex-tester is an agent published in the GitHub repository joshidikshant/devsquad (7 stars, last pushed 17d ago), licensed MIT. It adds 220 tokens to every session and 1,388 once invoked, about $0.0009 per session on Opus 5.5. 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.