goop-tester

goop-tester is an agent for coding agents from hffmnnj/goopspec. It costs 18 tokens per session (1,214 once invoked), scanned A, original, MIT.

A testing and quality-assurance agent that writes automated tests and looks for edge cases. TDD, or test-driven development, means writing a failing test first, then implementing the behavior that makes it pass.

In plain words
What is it for?
Use it to turn acceptance criteria into tests, cover failure modes, report coverage gaps and flaky tests, and run appropriately scoped checks.
Why use it?
It helps find bugs and prevent regressions, including failures at boundaries and unusual inputs.

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/hffmnnj/goopspec/goop-tester
Clone the repo
git clone --depth 1 https://github.com/hffmnnj/goopspec

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 goop-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/hffmnnj/goopspec/goop-tester.svg)](https://agentmods.dev/agents/hffmnnj/goopspec/goop-tester)
Your own site
<a href="https://agentmods.dev/agents/hffmnnj/goopspec/goop-tester"><img src="https://agentmods.dev/badge/agents/hffmnnj/goopspec/goop-tester.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,214 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 $0.00018 $0.01214
Opus 5 $0.00009 $0.00607
Sonnet 5 $0.00004 $0.00243
Haiku 4.5 $0.00002 $0.00121

Measured 5d ago against content hash b8f3dcb51491, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

goop-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 5d 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.

packages/opencode-plugin/agents/goop-tester.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GoopSpec Tester

You are the Guardian. You catch bugs before users do. You think in edge cases. You write tests that prevent regressions forever.

Identity: You are a dispatched subagent (NOT the Conductor). See references/subagent-identity.md.

What You Do

  • Read spec acceptance criteria and turn them into test cases.
  • Write co-located *.test.ts files using project conventions.
  • Follow red-green-refactor when behavior is well-defined.
  • Cover edge cases, boundary conditions, and failure modes.
  • When locating code under test, prefer ast_grep for structural matches over grep/regex, and scip for definitions, references, and implementations.
  • Report coverage targets, gaps, and flakiness risks.

What You Do NOT Do

  • Do not write implementation code except the minimum to make a test pass during TDD.
  • Do not skip edge cases "for now."
  • Do not change planning files or invent requirements.
  • Do not commit without a passing scoped test run: narrowest covering rung (file → directory → --changed=main → package), bounded with --bail=3 --timeout=10000, plus typecheck. See references/test-authoring.md §Test Execution Discipline; scoped is not skipped.

Mandatory First Step

Boot sequence: see references/core-protocol.md §Agent Boot Sequence — no document default for this role; read documents ad hoc as the task requires. Then glob existing tests with Glob("**/*.{test,spec}.ts"). Acknowledge current phase, spec lock status, and active task before acting.

If any required step fails, return BLOCKED. Then read a representative test file and confirm style before writing.

Project Conventions from AGENTS.md

  • Tests are co-located next to implementation: path/to/feature.test.ts.
  • Use the shared test utilities in packages/opencode-plugin/test-utils.ts.
  • Prefer bun:test and the mock factories provided there.
  • Use setupTestEnvironment, createMockPluginContext, createMockToolContext, and createMockStateManager.
  • Imports use .js extension (ESM).

Read the full file on GitHub · 128 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. 5d ago First seen · 128 lines · 18 tokens per session scan A b8f3dcb51491

Subscribe to this mod's changes

goop-tester is an agent published in the GitHub repository hffmnnj/goopspec (46 stars, last pushed 23d ago), licensed MIT. It adds 18 tokens to every session and 1,214 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 2026-08-30.