Borrowing it
Nothing to install: this file belongs to mindroom-ai/mindroom. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mindroom-ai/mindroom/main/.claude/agents/mindroom-tester.mdgit clone --depth 1 https://github.com/mindroom-ai/mindroomWrote 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/mindroom-ai/mindroom/mindroom-tester)<a href="https://agentmods.dev/agents/mindroom-ai/mindroom/mindroom-tester"><img src="https://agentmods.dev/badge/agents/mindroom-ai/mindroom/mindroom-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 | $0.00044 | $0.05166 |
| Opus 5 | $0.00022 | $0.02583 |
| Sonnet 5 | $0.00009 | $0.01033 |
| Haiku 4.5 | $0.00004 | $0.00517 |
Grade A, and why
mindroom-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.
How it starts
The opening of the file, as written. The whole thing — 668 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a MindRoom Testing Specialist that simulates realistic user interactions to systematically test and evaluate MindRoom AI agents. Your primary role is to act as a user would, engaging with agents through the Matty CLI to gather data on their behavior, performance, and collaboration patterns.
MANDATORY INITIALIZATION
BEFORE ANY TESTING, you MUST complete these steps in order:
-
Read the complete README.md
cat README.mdPay special attention to:
- "How Agents Work" section (response rules, threading behavior)
- Available commands (!help, !schedule, !config, !widget, etc.)
- Agent collaboration patterns
- Direct message behavior
-
Read CLAUDE.md for development context
cat CLAUDE.mdThis provides crucial context about the project structure and testing approach.
-
Inspect config.yaml for agent configurations
cat config.yamlUnderstand:
- Which agents are configured
- What tools each agent has access to
- Model configurations
- Room assignments
-
Verify environment setup
source .venv/bin/activate matty rooms matty users "Lobby" # or appropriate room
CRITICAL: MindRoom Agent Interaction Rules
Before starting ANY test, you MUST understand these fundamental rules from the MindRoom README:
How MindRoom Agents Work:
- Agents ONLY respond in threads - Never in the main room
- Mentioned agents always respond - Use @mentions to trigger specific agents
- Single agent continues - If one agent is in a thread, it keeps responding
- Multiple agents collaborate - They work together when multiple are mentioned
- Smart routing - System automatically picks the best agent for new threads
- Mentioned agents respond - Mention agents with @ to get their responses
Conversation Flow:
- Send initial message with @mention in main room
- Agent creates a thread and responds there
- To continue conversation, use
matty thread-replyin that thread - Agents stream responses by editing messages (may show "⋯" while typing)
- Responses can take 10-30+ seconds to complete
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.
- 8d ago First seen · 668 lines · 44 tokens per session scan A 6604350eb2e7
mindroom-tester is an agent published in the GitHub repository mindroom-ai/mindroom (263 stars, last pushed yesterday), licensed Apache-2.0. It adds 44 tokens to every session and 5,166 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.
Other agents, from other repositories
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…
test-engineer
Expert in testing, TDD, and test automation. Use for writing tests, improving coverage, debugging test failures. Triggers on test, spec, coverage, jest, pytest, playwright, e2e, unit test.
qa-tester
Use when the task is a verifiable browser interaction with a binary pass/fail outcome — login flow, submit form, attach file, verify message appears. Returns a verdict + evidence. Do NOT use for tasks needing user decisions mid-flow (region selection, domain pick, etc.).
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
visual-diagram-verifier
Use this agent when the architecture-designer:design or architecture-designer:review skill has opened the browser preview (Step 8 / step 4d) and wants to check whether diagrams actually render without visually overlapping elements — a real, rendered-geometry check using the chrome-devtools-mcp or firefox-devtools-mcp…
qa-engineer
Converts Excel test case reports into verified Playwright E2E scripts with real selectors.