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/borbiuk/band-play/agents-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/agents-md)<a href="https://agentmods.dev/instructions/borbiuk/band-play/agents-md"><img src="https://agentmods.dev/badge/instructions/borbiuk/band-play/agents-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 | $0.00664 | $0.00664 |
| Opus 5 | $0.00332 | $0.00332 |
| Sonnet 5 | $0.00133 | $0.00133 |
| Haiku 4.5 | $0.00066 | $0.00066 |
Grade A, and why
band-play AGENTS.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 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.
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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository agents (Bandcamp Play)
This file orients human and AI contributors to the Bandcamp Play Chrome extension (Manifest V3). Prefer small, focused changes; do not refactor unless asked.
Product
- Bandcamp Play — browser extension for Bandcamp (playback, UI, batch download, etc.).
- Build output —
dist/(Load unpacked target). - Source manifest —
public/manifest.json(copied intodist/by the build).
Architecture (MV3)
| Area | Path | Role |
|---|---|---|
| Service worker | src/background/background.ts |
Events, coordination, privileged chrome.* APIs. Keep lean and deterministic. |
| Content script | src/content/content.ts |
DOM on matched Bandcamp URLs; limited chrome.*. |
| Options / toolbar UI | src/options/options.tsx |
Extension popup / options UI. |
| Dedicated page | src/downloads/downloads.tsx |
Extension page opened as a tab. |
| Shared code | src/shared/ |
Models, enums, services, utilities — reuse via @shared/* alias. |
See also chrome-extension-architecture.md.
Messaging
- Use typed
MessageModel/MessageCodeas described in messaging-conventions.md. - Background handling:
src/background/services/messages-background-service.ts.
Build and manifest constraints
- No hashed bundle filenames —
manifest.jsonreferences fixed names; webpack uses[name].js. Do not introduce content hashes without updatingpublic/manifest.jsonand tooling. - Cross-import shared code via
@shared/...(seewebpack/webpack.common.js).
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 · 50 lines · 664 tokens per session scan A 117239654826
band-play AGENTS.md is an instructions file published in the GitHub repository borbiuk/band-play (21 stars, last pushed 26d ago), licensed MIT. It adds 664 tokens to every session, about $0.0033 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 instructions, from other repositories
opentabs AGENTS.md
Instructions for opentabs-dev/opentabs, covering project instructions for codex, project overview, architecture, you are connected to this project's mcp server and workflow skills.
vBookmarks AGENTS.md
AGENTS.md instructions for windviki/vBookmarks, covering agents.md, project overview, repository layout, build, test, and development commands and load for development.
opentabs CLAUDE.md
Instructions for opentabs-dev/opentabs, covering project instructions for claude, project overview, architecture, you are connected to this project's mcp server and workflow skills.
lens CLAUDE.md
Instructions for renderdraw/lens, covering renderdraw lens, architecture, build, build system and raf schema.
hanzi-browse CLAUDE.md
Claude Code instructions for hanzili/hanzi-browse, covering hanzi browse — architecture guide, what is hanzi browse?, architecture, key directories and value propositions.
local-lens CLAUDE.md
Instructions for aotakeda/local-lens, covering claude.md, project overview, architecture, high-level structure and key components.