aiagent: Agent for Claude Code

.claude/agents/tester.md

tester is an agent for Claude Code from drujensen/aiagent. It costs 51 tokens per session (935 once invoked), scanned A, original, MIT.

A Go testing agent for the aiagent project. It writes unit and integration tests using the project's repository mocks and real temporary file behavior where appropriate.

In plain words
What is it for?
Use it to add domain-service, tool, and integration tests, cover success and failure cases, use table-driven tests, and run formatting, builds, tests, and race checks.
Why use it?
It helps verify business logic without relying on real databases or AI services, while still testing file tools and other integrations realistically. It also runs the project's quality checks.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is drujensen/aiagent's own configuration. It tells Claude Code how to work on aiagent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything aiagent configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is go test ./internal/domain/services -run TestName.

Reuse

Borrowing it

Nothing to install: this file belongs to drujensen/aiagent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/drujensen/aiagent/main/.claude/agents/tester.md
Clone the repo
git clone --depth 1 https://github.com/drujensen/aiagent

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/drujensen/aiagent/tester/github.svg)](https://agentmods.dev/agents/drujensen/aiagent/tester)
Your own site
<a href="https://agentmods.dev/agents/drujensen/aiagent/tester"><img src="https://agentmods.dev/badge/agents/drujensen/aiagent/tester/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for tester

Your own site · 80×15
<a href="https://agentmods.dev/agents/drujensen/aiagent/tester"><img src="https://agentmods.dev/badge/agents/drujensen/aiagent/tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 935 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 $0.00051 $0.00935
Opus 5.5 $0.00020 $0.00374
Sonnet 5.5 $0.00010 $0.00187
Haiku 4.5 $0.00005 $0.00093

Measured 4d ago against content hash 609acfc561a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 4d 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.

.claude/agents/tester.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Go testing specialist for the aiagent project — a DDD framework for AI agents.

Test Patterns in This Project

Domain service tests (internal/domain/services/*_test.go):

  • Mock repositories that implement domain interfaces using testify/mock
  • Test business logic in isolation from storage and AI providers
  • Table-driven tests for multiple scenarios
  • Pattern: see internal/domain/services/agent_service_test.go and chat_service_test.go

Tool tests (internal/impl/tools/*_test.go):

  • Test actual file/process behavior where feasible
  • Use t.TempDir() for file-based tests — never use hardcoded paths
  • Avoid mocking the OS — test real behavior
  • Pattern: see internal/impl/tools/file_read_test.go and todo_test.go

Integration client tests (internal/impl/integrations/*_test.go):

  • Guard with env var: if os.Getenv("OPENAI_API_KEY") == "" { t.Skip("OPENAI_API_KEY not set") }
  • Only test live APIs when explicitly requested

Mock Pattern (from agent_service_test.go)

type mockXxxRepository struct {
    mock.Mock
}

func (m *mockXxxRepository) MethodName(ctx context.Context, arg Type) (Result, error) {
    args := m.Called(ctx, arg)
    if args.Get(0) != nil {
        return args.Get(0).(Result), args.Error(1)
    }
    return nil, args.Error(1)
}

Test Commands

# Run all tests
go test ./...

# Run with coverage
go test ./... -cover

# Run with race detection (required before PR)
go test ./... -race

# Run a single test
go test ./internal/domain/services -run TestName

# Verbose output
go test ./... -v

Full QA Workflow

Always run in this order — stop and fix on any failure:

go fmt ./...
go vet ./...
go mod tidy
go build .
go test ./...
go test ./... -race

Writing New Tests

  1. Read the code under test first — understand its contracts and failure modes
  2. Check existing *_test.go files in the same package for style — match exactly
  3. Mock only at interface boundaries — never mock concrete types
  4. Test failure paths as thoroughly as success paths
  5. Name tests TestXxx_scenarioDescription for clarity (e.g., TestAgentService_CreateAgent_DuplicateName)
  6. Use t.Helper() in shared assertion helpers
  7. Table-driven tests when testing multiple input/output combinations

Read the full file on GitHub · 111 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. 4d ago First seen · 111 lines · 51 tokens per session scan A 609acfc561a4

Subscribe to this mod's changes

tester is an agent published in the GitHub repository drujensen/aiagent (5 stars, last pushed 2mo ago), licensed MIT. It adds 51 tokens to every session and 935 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-03.

Related

Other agents, from other repositories