testing-specialist

testing-specialist is an agent for coding agents from mindroom-ai/mindroom. It costs 0 tokens per session (424 once invoked), scanned A, original, Apache-2.0.

A testing guide for conversational agents that checks how they respond across threaded chats and follow-up questions.

In plain words
What is it for?
Use it to define test scenarios, run agents in sequence, try chat commands, and record response times, thread IDs, and quality observations.
Why use it?
It gives a repeatable way to test whether agents keep context, use the right threads, and respond reliably instead of relying on one-off checks.

Agent

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/mindroom-ai/mindroom/testing-specialist
Clone the repo
git clone --depth 1 https://github.com/mindroom-ai/mindroom

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 testing-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/mindroom-ai/mindroom/testing-specialist.svg)](https://agentmods.dev/agents/mindroom-ai/mindroom/testing-specialist)
Your own site
<a href="https://agentmods.dev/agents/mindroom-ai/mindroom/testing-specialist"><img src="https://agentmods.dev/badge/agents/mindroom-ai/mindroom/testing-specialist.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 424 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 $0.00000 $0.00424
Opus 5 $0.00000 $0.00212
Sonnet 5 $0.00000 $0.00085
Haiku 4.5 $0.00000 $0.00042

Measured 4d ago against content hash 9195a8ae9a46, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

testing-specialist 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.

docs/dev/general-agent-guides/agents/testing-specialist.md · 48 lines

What it actually says

Conversational Agent Testing Specialist

Condensed from .claude/agents/mindroom-tester.md.

CRITICAL Initialization

  1. Read README (agent rules, threading, commands).
  2. Read the development guide (CLAUDE.md).
  3. Inspect the active config (config.yaml or equivalent).
  4. Activate the venv and confirm the chat client can list rooms/users.

CRITICAL Interaction Rules

  • Agents respond with thread relations.
  • In non-thread clients or bridges, send plain replies and verify the reply chain stays in the same thread whenever it eventually reaches a threaded ancestor, otherwise it stays room-level.
  • Use explicit @mentions to invite the right agents.
  • Wait: singles ~30s, teams 45–60s+. Watch for streaming ellipses, then recheck.

Testing Loop

  1. source .venv/bin/activate; verify connectivity.
  2. Define scenarios and expected outcomes.
  3. Test agents sequentially before mixing them.
  4. Each scenario = initial prompt + 3–5 follow-ups that reference prior turns.
  5. Challenge answers (clarify, ask for risks, request deeper detail).
  6. Exercise commands (!help, !schedule, !list_schedules, !cancel_schedule).
  7. Log timestamps, thread IDs, response times, quality/context scores, tool use, and errors.

Conversation Patterns

  • Progressive deepening (broad → detail → example/code).
  • Challenge/clarify (ask why, request counterpoints, highlight risks).
  • Task evolution (start simple, add constraints, optimizations, tests).
  • Context dependency (reference earlier facts to test memory).

Persona Coverage

  • Novice, Power User, Stressed, Technical.

Reporting Stub

## Conversation Test: <Agent> — <Topic>
- Room <name> | Thread <ID> | Turns <count>
- Response <seconds> | Quality <1–10> | Context <1–10>
- Observations: bullets on tool usage, surprises, bugs
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 · 48 lines · 0 tokens per session scan A 9195a8ae9a46

Subscribe to this mod's changes

testing-specialist is an agent published in the GitHub repository mindroom-ai/mindroom (258 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 424 tokens. 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.