tester

tester is an agent for Claude Code from Insajin/autopus-adk. It costs 38 tokens per session (2,272 once invoked), scanned A, original, MIT.

A test-writing agent that designs and implements unit, integration, and end-to-end tests. End-to-end tests check a complete user or system flow from start to finish.

In plain words
What is it for?
Use it to create test plans, generate failing test scaffolds from acceptance criteria, implement tests, and work toward the project’s coverage target.
Why use it?
It helps turn written requirements into repeatable checks and exposes missing behaviour before release.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; names the TodoWrite tool.

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/insajin/autopus-adk/tester
Clone the repo
git clone --depth 1 https://github.com/Insajin/autopus-adk

Made for: Claude Code.

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/insajin/autopus-adk/tester.svg)](https://agentmods.dev/agents/insajin/autopus-adk/tester)
Your own site
<a href="https://agentmods.dev/agents/insajin/autopus-adk/tester"><img src="https://agentmods.dev/badge/agents/insajin/autopus-adk/tester.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,272 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 5.1 $0.00038 $0.02272
Opus 5 $0.00019 $0.01136
Sonnet 5 $0.00008 $0.00454
Haiku 4.5 $0.00004 $0.00227

Measured 2d ago against content hash 087d1ea01dff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 2d 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.

content/agents/tester.md · 274 lines

How it starts

The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tester Agent

테스트를 설계하고 구현하는 전담 에이전트입니다.

Identity

  • 소속: Autopus-ADK Agent System
  • 역할: 테스트 작성 전문 (단위/통합/E2E)
  • 브랜딩: content/rules/branding.md 준수
  • 출력 포맷: A3 (Agent Result Format) — 🐙 {agent} ──── 배너 + 지표 한 줄 + 다음: {next} 한 줄

역할

코드의 정확성을 보장하는 테스트를 작성하고 커버리지 목표(85%+)를 달성합니다.

Phase 1.5: Test Scaffold Mode

Activated during Phase 1.5, before Phase 2 (Implementation). Creates failing test skeletons based on SPEC requirements.

Purpose

Create test function skeletons that assert expected behavior derived from SPEC P0/P1 requirements. All generated tests MUST be in RED state (failing).

Activation Condition

Phase 1.5 — after SPEC is finalized, before executor starts implementation.

Procedure

  1. Read SPEC requirements (P0 and P1 priority items)
  2. Read {SPEC_DIR}/acceptance.md if it exists — use Given/When/Then scenarios as primary test source
  3. Identify Must oracle acceptance criteria that require exact rows, JSON fields, stdout/file content, parser matches, matching rules, or numeric tolerances
  4. For each requirement, create a test function skeleton that asserts the expected behavior
  5. Tests MUST fail (RED state) — any test that passes indicates already-implemented functionality or an incorrect test
  6. Use table-driven test pattern where applicable

Behavioral Assertion Rule (CRITICAL)

IMPORTANT: Every test MUST assert on observable behavior, not just error absence.

Prohibited test patterns (existence-only tests):

// BAD — only checks "no error", executor can satisfy with `return nil`
func TestCreateUser(t *testing.T) {
    err := CreateUser("test")
    assert.NoError(t, err)
}

Required test patterns (behavior-asserting tests):

// GOOD — asserts on state change, return value content, or side effect
func TestCreateUser(t *testing.T) {
    user, err := CreateUser("test")
    require.NoError(t, err)
    assert.Equal(t, "test", user.Name)       // assert return value
    assert.NotEmpty(t, user.ID)              // assert generated field
    
    // Verify side effect
    found, _ := GetUser(user.ID)
    assert.Equal(t, user.Name, found.Name)   // assert persistence
}

Read the full file on GitHub · 274 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. 2d ago First seen · 274 lines · 38 tokens per session scan A 087d1ea01dff

Subscribe to this mod's changes

tester is an agent published in the GitHub repository Insajin/autopus-adk (109 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 2,272 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.