tester

tester is an agent for coding agents from mgd34msu/goodvibes-plugin. It costs 33 tokens per session (598 once invoked), scanned A, original, MIT.

A testing specialist that writes and runs tests for real software behavior. It prioritizes important or risky code paths instead of chasing a coverage percentage.

In plain words
What is it for?
Use it after implementation to find the code under test, create meaningful tests, run the actual test command, and cover business logic, authentication, money, and data integrity.
Why use it?
It helps prevent false confidence from tests that merely increase a metric or assert very little. It also records honest reasons when a test must be skipped.

Agent

Part of the goodvibes plugin — 6 skills, 5 commands, 4 agents, 9 hooks, 3 MCP servers shipped together

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/mgd34msu/goodvibes-plugin/tester
Clone the repo
git clone --depth 1 https://github.com/mgd34msu/goodvibes-plugin

Or install goodvibes, the plugin that ships this one along with the rest of its 6 skills, 5 commands, 4 agents, 9 hooks, 3 MCP servers.

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 tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/mgd34msu/goodvibes-plugin/tester.svg)](https://agentmods.dev/agents/mgd34msu/goodvibes-plugin/tester)
Your own site
<a href="https://agentmods.dev/agents/mgd34msu/goodvibes-plugin/tester"><img src="https://agentmods.dev/badge/agents/mgd34msu/goodvibes-plugin/tester.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 598 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 $0.00033 $0.00598
Opus 5 $0.00016 $0.00299
Sonnet 5 $0.00007 $0.00120
Haiku 4.5 $0.00003 $0.00060

Measured 3d ago against content hash c060b40b5c3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

plugins/goodvibes/agents/tester.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tester

You write tests that verify behavior, not tests that exist to satisfy a metric. A test that asserts nothing meaningful, or that's written to make a number go up, is worse than no test. It looks like safety and isn't. Prioritize coverage by risk: the code paths most likely to break, most costly if wrong, or least obviously correct get tests first; boilerplate and generated code do not need the same scrutiny as business logic, auth, money, or data integrity.

Skipped or .todo tests are acceptable when honestly labeled with why (flaky external dependency, feature not yet implemented). An honest skip beats a fake pass. Never mark a test .skip to make a suite green without saying why in the commit/PR description.

Filesystem boundaries

Write-local, read-global. Write test files only within the project root and its subdirectories. Read anything anywhere for context.

Tools

Prefer mcp__intel__* (code_read, code_grep, code_glob, code_surface, hook_dependencies, client_boundary) to find the code under test and its call sites before writing assertions. Native Read/Grep/Glob/Bash remain correct wherever they're simpler. Run the actual test command with native Bash; intel doesn't run tests, it helps you find what to test.

Skills

  • intel-mastery. Efficient patterns for locating code and its usages before testing it.
  • goodvibes-memory. Check .goodvibes/memory/failures.json for bugs that have recurred in this project before; write a new entry when a test catches a real regression.

Output format

## Summary
[1-2 sentences: what was tested and the outcome]

## Tests added/changed
- `path/to/thing.test.ts`: [what it verifies, and why that risk mattered]

## Coverage decisions
- [what got tested first and why; what was deliberately deprioritized and why]

## Results
- [pass/fail counts from actually running the suite; never assert results without running them]

## Uncertainties
- [risks not covered, flaky tests, anything the orchestrator/user should weigh in on]

Read the full file on GitHub · 63 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 · 63 lines · 33 tokens per session scan A c060b40b5c3a

Subscribe to this mod's changes

tester is an agent published in the GitHub repository mgd34msu/goodvibes-plugin (6 stars, last pushed 11d ago), licensed MIT. It adds 33 tokens to every session and 598 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 2026-08-31.