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.
npx agentmods add instructions/band-app/band/claude-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/instructions/band-app/band/claude-md)<a href="https://agentmods.dev/instructions/band-app/band/claude-md"><img src="https://agentmods.dev/badge/instructions/band-app/band/claude-md.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 | $0.03304 | $0.03304 |
| Opus 5 | $0.01652 | $0.01652 |
| Sonnet 5 | $0.00661 | $0.00661 |
| Haiku 4.5 | $0.00330 | $0.00330 |
Grade A, and why
band CLAUDE.md scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Production code reads outbound URLs from env vars at request time**, not at module load (`axios.create({ baseURL })` at module top is wrong). Refactoring that pattern is the only allowed production-code change a test How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Band
IDE-agnostic agent orchestrator.
Testing Strategy
This project uses integration tests as the primary testing approach. Do not write unit tests with mocked dependencies.
When writing, adding, or modifying tests — backend OR frontend — invoke the
write-integration-testskill FIRST. It is the canonical reference for this repository: real-server boot, Express stubs for external services, no tRPC mocking, nopage.route()on own routes, Page Object Model for Playwright, locator priority, the universal checklist, and worked examples for both layers. The rules below are the summary; the skill is the source of truth.
Why Integration Tests
Unit tests with heavy mocking verify that your mocks work, not that your system works. Integration tests exercise the real system through its public interfaces — the same way a client or user would interact with it.
Rules
- Never modify production code to make a test pass. No test-only branches, no exporting internals, no
NODE_ENVchecks in business logic. - Black-box testing only. Test through public interfaces: HTTP endpoints, CLI commands, file system outputs, the rendered DOM (frontend).
- Real infrastructure. For databases use test containers, not mocks. For file-based state use temporary directories. Start real servers on random ports.
- External-only stubs at the network boundary. Mock only services your process calls out to (third-party APIs, agent binaries, GitHub, etc.) using an Express stub on a random port + env-var override read at request time. Do NOT use MSW (it misses subprocess-originated traffic, and the env-var indirection is what forces the production code into a testable shape). Do NOT use
page.route()to intercept your own backend routes from a Playwright test. Do NOT add a tRPC mock layer. - Test framework: match the package.
node:testwithnode:assert/strictis the default for new code. The web app (apps/web) is the exception: it already standardised on vitest before this convention was written down (the existing test suite usesdescribe/it/expect/beforeAllfromvitest), so new tests underapps/web/tests/should use vitest too rather than mix runners in one package. Don't add test framework dependencies elsewhere unless already present.
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.
- 5d ago First seen · 116 lines · 3,304 tokens per session scan A 46ee9fa7aa67
band CLAUDE.md is an instructions file published in the GitHub repository band-app/band (5 stars, last pushed yesterday), licensed MIT. It adds 3,304 tokens to every session, about $0.0165 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).