Borrowing it
Nothing to install: this file belongs to band-app/band. 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/band-app/band/main/.claude/skills/band-chat-test/SKILL.mdgit clone --depth 1 https://github.com/band-app/bandWrote 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/skills/band-app/band/band-chat-test)<a href="https://agentmods.dev/skills/band-app/band/band-chat-test"><img src="https://agentmods.dev/badge/skills/band-app/band/band-chat-test/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/band-app/band/band-chat-test"><img src="https://agentmods.dev/badge/skills/band-app/band/band-chat-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00178 | $0.02942 |
| Opus 5.5 | $0.00071 | $0.01177 |
| Sonnet 5.5 | $0.00036 | $0.00588 |
| Haiku 4.5 | $0.00018 | $0.00294 |
Grade A, and why
band-chat-test 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 25d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test a Band Chat via CLI
Drive a coding-agent chat session end-to-end from the terminal — start the dev server, point the CLI at it, kick off a worktree or send a message, watch the streaming NDJSON output, and assert on it. Faster and more scriptable than clicking through the dashboard, and produces structured output you can paste into a PR as evidence.
This skill is for verification, not for ordinary day-to-day work. Day-to-day chat use is documented in the sibling band-chat skill (the global CLI skill auto-generated from the schema). Use this skill when:
- You changed how Band talks to an agent over ACP (
packages/host-local/src/agents/*,agent-session-service.ts) and want to prove it works - A reviewer asked you to demonstrate runtime behaviour
- You need to capture an agent transcript for a PR or bug report
The dev-vs-prod port gotcha
pnpm dev:web runs Vite on port 3456 by default, but if that port is already in use (the production Band server installed via the dashboard is almost always bound to 3456) Vite falls forward to 3457, then 3458, etc. Vite logs the port it actually settles on.
The Band CLI picks its server in this order (see apps/cli/src/api.rs):
$BAND_SERVER_URLenv var — full URL, e.g.http://127.0.0.1:3458- else
settings.web_server_portfrom~/.band/settings.json(default3456)
The CLI does not auto-detect the dev port. Without BAND_SERVER_URL, every band invocation talks to the production server on 3456, which means your test results reflect production state, your kickoff lands in the wrong server's database, and the agent you "fixed" never actually ran with the dev-server code. This is the single most common way to waste 20 minutes on a fake green run. Always export BAND_SERVER_URL for the duration of a test session.
Auth uses the same priority: $BAND_TOKEN else settings.token_secret. Usually you do not need to set this — the dev server reads the same ~/.band/settings.json and runFirstTimeSetup ensures a token exists, so the fallback works. Only set BAND_TOKEN explicitly if the dev server is using a different settings file (rare).
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.
- 25d ago Changed 68669ff356ed
- 26d ago Changed · -1 tokens per session 9c4b6bedec97
- 1mo ago Changed · -7 lines · +4 tokens per session 4a078640b128
- 2mo ago First seen · 180 lines · 175 tokens per session scan A 32ed1c01471d
band-chat-test is a skill published in the GitHub repository band-app/band (5 stars, last pushed today), licensed MIT. It adds 178 tokens to every session and 2,942 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.