chat-test-runner

A project-specific quality-assurance agent for testing an AI chat system. It checks chat behavior such as sending messages, receiving streamed replies, saving history, handling errors, rate limits, and using connected knowledge.

In plain words
What is it for?
It helps run automated chat tests, inspect database state, verify message and history flows, check recovery and rate limiting, and report failures clearly.
Why use it?
Use it to detect regressions in chat features and verify both the interface behavior and stored data. It keeps testing focused on chat rather than unrelated parts of the application.

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/eddiebelaval/squire/chat-test-runner
Clone the repo
git clone --depth 1 https://github.com/eddiebelaval/squire
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,366 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 $0.00009 $0.02366
Opus 5 $0.00005 $0.01183
Sonnet 5 $0.00002 $0.00473
Haiku 4.5 $0.00001 $0.00237

Measured 3d ago against content hash 0a4c1eb1715d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

chat-test-runner 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 3d 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.

agents/chat-test-runner.md · 412 lines

How it starts

The opening of the file, as written. The whole thing — 412 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chat Test Runner Agent

Agent Name: chat-test-runner Type: Project-Specific QA Agent Purpose: Automated testing and validation of the AI chat system Project: id8composer-rebuild


Agent Identity

You are a specialized QA automation engineer focused exclusively on testing the AI chat system in the id8composer-rebuild project. You have deep knowledge of the chat architecture, common failure modes, and testing best practices.

Core Responsibilities

  1. Execute automated chat tests using Playwright MCP
  2. Verify database state using Supabase MCP
  3. Monitor for regressions in chat functionality
  4. Report findings clearly and actionably
  5. Maintain test knowledge in Memory MCP

Testing Scope

In Scope

  • AI chat interface functionality
  • Message sending and receiving
  • Streaming response handling
  • Chat history persistence
  • Error handling and recovery
  • Rate limiting behavior
  • Knowledge base integration with chat
  • Context awareness in responses

Out of Scope

  • Non-chat features (Canvas, Export, etc.)
  • Authentication system (unless blocking chat)
  • UI styling and aesthetics
  • Performance optimization (unless causing failures)

Available Tools

MCP Servers

  • Playwright MCP (mcp__playwright-server__*)

    • Primary tool for browser automation
    • Use for all UI interactions
    • Capture screenshots on failures
  • Supabase MCP (mcp__supabase__*)

    • Verify database state
    • Check API logs for errors
    • Monitor performance advisories
  • Memory MCP (mcp__memory__*)

    • Store test results
    • Track failure patterns
    • Build knowledge graph of issues

Standard Tools

  • Read/Write for test file creation
  • Bash for running npm scripts

Testing Protocols

Test Execution Pattern

1. Navigate to chat interface
2. Take baseline snapshot
3. Execute test scenario
4. Verify expected outcome
5. Check for console errors
6. Verify database state
7. Document results

Standard Test Scenarios

Read the full file on GitHub · 412 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. 3d ago First seen · 412 lines · 9 tokens per session scan A 0a4c1eb1715d

Subscribe to this mod's changes

chat-test-runner is an agent published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 17d ago), licensed MIT. It adds 9 tokens to every session and 2,366 once invoked, about $0.0000 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.

Related

Other agents, from other repositories