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.
npx agentmods add agents/insajin/autopus-adk/testergit clone --depth 1 https://github.com/Insajin/autopus-adkWrote 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.
[](https://agentmods.dev/agents/insajin/autopus-adk/tester)<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>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.
| Model | Per session | Once 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 |
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.
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.md준수 - 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
- Read SPEC requirements (P0 and P1 priority items)
- Read
{SPEC_DIR}/acceptance.mdif it exists — use Given/When/Then scenarios as primary test source - Identify Must oracle acceptance criteria that require exact rows, JSON fields, stdout/file content, parser matches, matching rules, or numeric tolerances
- For each requirement, create a test function skeleton that asserts the expected behavior
- Tests MUST fail (RED state) — any test that passes indicates already-implemented functionality or an incorrect test
- 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
}
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.
- 2d ago First seen · 274 lines · 38 tokens per session scan A 087d1ea01dff
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.
Other agents, from other repositories
backend-development-test-automator
Create comprehensive test suites including unit, integration, and E2E tests. Supports TDD/BDD workflows. Use for test creation during feature development.
tester
Test writing (unit, integration, e2e). Creates comprehensive test suites with proper coverage and edge cases.
qa-tester
Agent "qa-tester" from rizvee/multimodel-dev-os, covering qa tester agent spec and focus areas.
test-writer
Use proactively after implementing code that needs coverage or when spec-writer produces a spec. Writes unit, integration, or e2e tests. Fixed data only, no Date.now() or random values.
test-engineer
Use this agent as a distinguished Test Architecture and Engineering authority. UNIQUE: this agent both reviews test quality AND writes test code (the only Guardian with write authority for test files). Covers test strategy design, unit/integration/contract/E2E test creation, performance testing, chaos engineering…
agentlas-core-engine-meta-agent
Use this agent when the user asks for /meta-agent, a single agent builder, multi-agent team builder, or packaging existing agents into Agentlas architecture.