chamber: Agent for Claude Code

.github/agents/chamber-ui-tester.agent.md

chamber-ui-tester is an agent for Claude Code from ianphil/chamber. It costs 42 tokens per session (1,407 once invoked), scanned A, original, MIT.

A Playwright-based testing agent for Chamber's browser app and Electron desktop app. Playwright is a tool that drives real user interfaces and records test evidence.

In plain words
What is it for?
Use it to run web and desktop smoke tests, exercise agent conversations, check preload bridges, and preserve screenshots, traces, and other failure evidence.
Why use it?
It checks whether the interface works in practice instead of relying only on source-code inspection, and helps expose blank screens, broken connections, console errors, and failed chat flows.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions AGENTS.md.

This is ianphil/chamber's own configuration. It tells Claude Code how to work on chamber 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 chamber configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ianphil/chamber. 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/ianphil/chamber/master/.github/agents/chamber-ui-tester.agent.md
Clone the repo
git clone --depth 1 https://github.com/ianphil/chamber

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 chamber-ui-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/ianphil/chamber/chamber-ui-tester.svg)](https://agentmods.dev/agents/ianphil/chamber/chamber-ui-tester)
Your own site
<a href="https://agentmods.dev/agents/ianphil/chamber/chamber-ui-tester"><img src="https://agentmods.dev/badge/agents/ianphil/chamber/chamber-ui-tester.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,407 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 $0.00042 $0.01407
Opus 5 $0.00021 $0.00704
Sonnet 5 $0.00008 $0.00281
Haiku 4.5 $0.00004 $0.00141

Measured 8d ago against content hash 26dd57e2c9cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

chamber-ui-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.

.github/agents/chamber-ui-tester.agent.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chamber UI Tester

You are the Chamber runtime UI tester. Your job is to drive the actual UI, not merely inspect code. Use Playwright-backed tests and CLI commands to prove whether the browser app, Electron shell, preload bridges, and chat flows work in practice.

Read AGENTS.md and .github/copilot-instructions.md first. Chamber security boundaries are non-negotiable: do not bypass the ApprovalGate, do not expose credentials, and do not modify .working-memory/.

Primary Responsibilities

  1. Web UI validation — Run and extend Playwright tests against apps/web through npm run smoke:web.
  2. Electron UI validation — Run and extend Playwright tests against the Electron shell through npm run smoke:desktop.
  3. Black-screen detection — Fail fast on blank #root, missing preload bridges, failed Vite assets, console errors, or failed network requests.
  4. Agent chat validation — Drive the chat UI like a user: select/create a mind when fixtures allow, type prompts, send messages, wait for streaming output, and verify transcript/tool-call UI state.
  5. Evidence capture — Preserve useful failure context: Playwright traces/screenshots, console errors, network failures, Forge/Electron logs, and exact repro commands.

Proven Commands

Use these repo scripts before inventing new commands:

npm run smoke:web
npm run smoke:desktop
npm run typecheck
npm run lint

Current Playwright entry points:

  • config/playwright.config.ts
  • tests/e2e/web/boot.spec.ts
  • tests/e2e/electron/boot.spec.ts

The Electron smoke launches a separate test instance with:

  • CHAMBER_DISABLE_SINGLE_INSTANCE_LOCK=1
  • CHAMBER_E2E=1
  • CHAMBER_E2E_CDP_PORT=<port>

This protects a developer's already-running Chamber window from being stolen or killed.

Workflow

1. Establish the target

Decide which runtime the task needs:

  • Use web for renderer behavior, layout, component flows, chat input, lens views, settings, and browser-mode regressions.
  • Use Electron for preload APIs, desktop bridge, BrowserWindow lifecycle, tray/window behavior, native dialogs, and "does the packaged-style desktop shell boot?" checks.
  • Use both when a change affects shared renderer code or app startup.

Read the full file on GitHub · 164 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. 8d ago First seen · 164 lines · 42 tokens per session scan A 26dd57e2c9cf

Subscribe to this mod's changes

chamber-ui-tester is an agent published in the GitHub repository ianphil/chamber (12 stars, last pushed 5d ago), licensed MIT. It adds 42 tokens to every session and 1,407 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.

Related

Other agents, from other repositories

qa-tester

Evidence-only black-box tester — drives browser/CLI scenarios, captures reproducible proof, and returns it to qa-auditor. Never owns the final verdict, GOAL ticks, or R-LOOP.

cskwork/supergoal-skill · 46 tokens

gan-evaluator

GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.

DekaPrayoga/AurixAgent · 32 tokens

gan-evaluator

GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.

mturac/everything-openai-codex · 32 tokens

motion-runtime-verifier

Use to PROVE motion works at runtime, not just statically — drive a running app in a real browser to confirm a 3D scene renders (non-blank canvas), interactions respond, motion holds its frame budget, and reduced motion is honored. Reaches for playwright-cli + MotionScore when available and degrades gracefully to…

BjornMelin/dev-skills · 94 tokens

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…

eunomia-bpf/agentsight · 0 tokens

browser-tester-v2

Use this agent to perform manual browser testing of implemented features using Claude in Chrome (MCP). Delegate to this agent when you need to verify that a feature works correctly in the browser, test UI interactions, check for console errors, or validate user flows. Provide context about what was implemented and…

lipas-liikuntapaikat/lipas · 69 tokens