Borrowing it
Nothing to install: this file belongs to borbiuk/band-play. 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/borbiuk/band-play/master/CLAUDE.mdgit clone --depth 1 https://github.com/borbiuk/band-playWrote 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/borbiuk/band-play/claude-md)<a href="https://agentmods.dev/instructions/borbiuk/band-play/claude-md"><img src="https://agentmods.dev/badge/instructions/borbiuk/band-play/claude-md/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/instructions/borbiuk/band-play/claude-md"><img src="https://agentmods.dev/badge/instructions/borbiuk/band-play/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00707 | $0.00707 |
| Opus 5.5 | $0.00283 | $0.00283 |
| Sonnet 5.5 | $0.00141 | $0.00141 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
band-play CLAUDE.md 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 yesterday.
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 — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code — Band Play
@AGENTS.md
Working rules
- Follow existing project conventions (code style, folder structure, naming, dependency management) unless explicitly instructed otherwise.
- Never refactor unless explicitly requested; apply only the changes directly required for the current request. Keep changes minimal, explicit, and localized.
- Always use a block
if-returnstatement (avoid inline one-liners). - All comments and documentation must be in English; answer in the same language as the question.
- Dependencies: only exact versions, never
^or~. Install withnpm install -E <package>@latest, then runnpm run check:versions. - Do not add attribution lines ("generated by", co-author trailers) to code, docs, release notes, commit messages or pull requests.
.claude/settings.jsonturns off Claude Code's own commit and PR attribution. - Git safety: never run
commit,reset,rebase,push,pull --force,checkout --force,clean, orstash dropunless the user explicitly asks; confirm beforegit pull,git merge, orgit stash. The riskiest commands are also blocked or gated in .claude/settings.json.
Agent context
- Rules (
.claude/rules/) load automatically when matching files are touched: architecture, messaging (messages and ports), Bandcamp DOM selectors and page services, batch download, popup, Firefox, npm versions, docs and CI, testing, agent context. - Skill
/verify(.claude/skills/verify/): exact versions, format, both builds, ESLint with the type check,web-ext lint, unit and e2e tests, the docs check and the unused code check. - Skill
/release(.claude/skills/release/, invoked by the user only): version bump, release notes, release commit and zips, then after confirmation push, CI, tag and GitHub Release. The store upload is manual. - Skills for tests:
/playwright(.claude/skills/playwright/: writing, running and debugging the Playwright suite, Chrome extension specifics) and/e2e-review(.claude/skills/e2e-review/: the test standard and the review workflow). Tests follow testing.md. - Subagents (
.claude/agents/):code-reviewer(read-only review),qa-engineer(read-only verification),e2e-reviewer(read-only review of tests with/e2e-review), plus the generated Playwright agentsplaywright-test-planner,-generatorand-healer(regenerate withnpx playwright init-agents --loop=claude --project=e2eafter a Playwright update; their output must pass/e2e-review). - Plugin
modern-web-guidance(enabled in.claude/settings.json) provides the officialchrome-extensionsskill for Chrome APIs. - MCP servers (
.mcp.json):chrome-devtoolsloads the unpacked build into Chrome for in-browser checks;playwright-testserves the Playwright test agents.init-agentsoverwrites.mcp.json, so re-addchrome-devtoolsafter running it.
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.
- yesterday Changed · +321 tokens per session 28618dab9a16
- 1mo ago First seen · 24 lines · 386 tokens per session scan A d63f11d5b68d
band-play CLAUDE.md is an instructions file published in the GitHub repository borbiuk/band-play (21 stars, last pushed today), licensed MIT. It adds 707 tokens to every session, about $0.0028 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 2026-08-30.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.