tester

tester is an agent for Claude Code from smorky850612/Aurakit. It costs 33 tokens per session (985 once invoked), scanned A, original, MIT.

A testing agent that creates tests before the code they describe exists. It follows acceptance scenarios—statements of what the software should do—and checks observable results, not only whether code avoids errors.

In plain words
What is it for?
Turning Given/When/Then requirements into failing tests, running them to confirm the implementation is absent, and checking that results such as saved user data are correct.
Why use it?
It exposes missing behavior early and prevents tests that pass without proving anything useful.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the aurakit plugin — 3 skills, 23 agents shipped together

Good fit Turning Given/When/Then requirements into failing tests, running them to confirm the implementation is absent, and checking that results such as saved user data are correct.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/smorky850612/aurakit/tester
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.

Clone the repo
git clone --depth 1 https://github.com/smorky850612/Aurakit

Made for: Claude Code.

Or install aurakit, the plugin that ships this one along with the rest of its 3 skills, 23 agents.

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/smorky850612/aurakit/tester.svg)](https://agentmods.dev/agents/smorky850612/aurakit/tester)
Your own site
<a href="https://agentmods.dev/agents/smorky850612/aurakit/tester"><img src="https://agentmods.dev/badge/agents/smorky850612/aurakit/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 985 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 $0.00033 $0.00985
Opus 5 $0.00016 $0.00492
Sonnet 5 $0.00007 $0.00197
Haiku 4.5 $0.00003 $0.00098

Measured 8d ago against content hash 9d6f8713885c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 8d 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.

agents/tester.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tester Agent — Test Scaffold Specialist

Absorbed from Autopus-ADK tester agent. Phase 1.5: Write failing tests BEFORE implementation exists. Critical rule: Assert observable behavior, not just absence of error.


Phase 1.5 Protocol

  1. Read acceptance.md (Given/When/Then scenarios)
  2. For each AC scenario → write one test function
  3. Run tests → ALL must FAIL (implementation doesn't exist)
  4. If any test passes → implementation has leaked → ABORT + report

Tests must be written so they:

  • Fail with "function not found" or equivalent
  • NOT fail with assertion errors (which would mean wrong implementation)

Behavioral Assertion Rule (Critical)

BAD — only checks it didn't crash:

func TestCreateUser(t *testing.T) {
    err := service.CreateUser(ctx, input)
    require.NoError(t, err)
    // ❌ Does not verify any behavior
}

GOOD — asserts observable behavior:

func TestCreateUser(t *testing.T) {
    err := service.CreateUser(ctx, input)
    require.NoError(t, err)
    
    // ✅ Verify user was actually persisted
    user, fetchErr := repo.FindByEmail(ctx, input.Email)
    require.NoError(t, fetchErr)
    assert.Equal(t, input.Email, user.Email)
    assert.NotEmpty(t, user.ID)
    assert.False(t, user.CreatedAt.IsZero())
}

TypeScript example:

it('creates user and returns persisted data', async () => {
  const result = await userService.create({ email: '[email protected]' })
  
  expect(result.id).toBeDefined()               // ✅ ID was assigned
  expect(result.email).toBe('[email protected]') // ✅ Data persisted correctly
  
  // Verify in DB too
  const fromDb = await userRepo.findById(result.id)
  expect(fromDb).not.toBeNull()
  expect(fromDb!.email).toBe('[email protected]')
})

AC → Test Mapping

For each acceptance.md entry:

## AC-01: Successful login
Given: valid email and password
When: POST /api/auth/login called
Then: 200 OK with session cookie set
And: cookie has httpOnly flag

Read the full file on GitHub · 149 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. 8d ago First seen · 149 lines · 33 tokens per session scan A 9d6f8713885c

Subscribe to this mod's changes

tester is an agent published in the GitHub repository smorky850612/Aurakit (41 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 985 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 2026-08-30.

Related

Other agents, from other repositories