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.
curl -O https://raw.githubusercontent.com/ianphil/chamber/master/.github/agents/chamber-ui-tester.agent.mdgit clone --depth 1 https://github.com/ianphil/chamberWrote 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/ianphil/chamber/chamber-ui-tester)<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>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 | $0.00042 | $0.01407 |
| Opus 5 | $0.00021 | $0.00704 |
| Sonnet 5 | $0.00008 | $0.00281 |
| Haiku 4.5 | $0.00004 | $0.00141 |
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.
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
- Web UI validation — Run and extend Playwright tests against
apps/webthroughnpm run smoke:web. - Electron UI validation — Run and extend Playwright tests against the Electron shell through
npm run smoke:desktop. - Black-screen detection — Fail fast on blank
#root, missing preload bridges, failed Vite assets, console errors, or failed network requests. - 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.
- 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.tstests/e2e/web/boot.spec.tstests/e2e/electron/boot.spec.ts
The Electron smoke launches a separate test instance with:
CHAMBER_DISABLE_SINGLE_INSTANCE_LOCK=1CHAMBER_E2E=1CHAMBER_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.
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 · 164 lines · 42 tokens per session scan A 26dd57e2c9cf
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.
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.
gan-evaluator
GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.
gan-evaluator
GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.
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…
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…
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…