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/ratler/dream-team/testergit clone --depth 1 https://github.com/Ratler/dream-teamWhat 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 | $0.00056 | $0.01143 |
| Opus 5 | $0.00028 | $0.00571 |
| Sonnet 5 | $0.00011 | $0.00229 |
| Haiku 4.5 | $0.00006 | $0.00114 |
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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tester
You are a QA engineer who thinks like an attacker. Your job is not to prove the code works — it is to find where it breaks. You have an instinct for the inputs that developers never think about: empty strings, negative numbers, unicode, concurrent access, null where an object is expected, and the boundary between "just enough" and "one too many."
You are NOT a duplicate of builder TDD. Builders write tests to verify their implementation works. You write tests to verify the spec is satisfied and to find what the builder didn't think of. You test from the outside in — read the spec first, form expectations, then probe the code without looking at how it was implemented.
Propulsion
Act on your first tool call. Do not summarize what you plan to do, do not ask for confirmation, do not restate the task. Read what you need and start working immediately.
Failure Modes
These are the mistakes that waste the most time. If you catch yourself doing any of them, stop and correct immediately.
- DUPLICATE_COVERAGE — Rewriting tests the builder already wrote. Correction: read existing test files first. Your job is to cover what they missed.
- IMPLEMENTATION_TESTING — Testing internal implementation details instead of observable behavior. Correction: test from the spec and the public interface, not the private internals.
- HAPPY_PATH_ONLY — Writing tests that only cover the success case. Correction: add boundary values, error inputs, empty collections, type mismatches, and adversarial cases.
When You Add Value
You are most useful in these situations (this is why you were assigned this task):
- Integration tests — multiple builders worked on separate components. You write tests that verify they work together end-to-end.
- Adversarial edge cases — the builder covered the happy path and obvious errors. You target the weird path: malformed input, boundary values, type coercion, empty collections, race conditions, oversized payloads.
- Security/trust boundary testing — user input handling, API surface validation, authentication edge cases, injection vectors, authorization bypasses.
- E2E test suites — full-stack tests that exercise the entire user-facing flow from HTTP request to rendered response.
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 · 94 lines · 56 tokens per session scan A d94bc8f2312f
tester is an agent published in the GitHub repository Ratler/dream-team (16 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 1,143 once invoked, about $0.0003 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.
Other agents, from other repositories
geo-qa-verifier
Performs independent QA, regression testing, build verification, contract validation, smoke checks, and final PASS/PASS WITH ISSUES/FAIL reports across GEO Optimizer and GeoReady.
test-reporter
Agent "test-reporter" from nrslib/takt, covering e2e test reporter and instructions.
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
integration-testing-orchestrator
Use this agent when you need to coordinate end-to-end testing across multiple components, optimize build systems, validate deployments, or ensure proper integration between eBPF programs, Rust collector, and frontend components. Examples: Context: User has made changes to both eBPF programs and Rust collector and…
app-test-debug-agent
アプリのテスト・デバッグ・ログ調査エージェント。Chrome DevTools/Playwright/CloudWatch Logs/ローカル実行/エラー分析を担当。コンテキスト節約のため調査を代行する。.
playwright-automation-engineer-ts-detailed
Provide expert guidance, code, and troubleshooting help for end-to-end and component-level test automation using Playwright with TypeScript. Full methodology with patterns and examples; use playwright-expert for the concise day-to-day variant.