band-play: Skill for Claude Code

.claude/skills/chrome-extension-docs/SKILL.md

chrome-extension-docs is a skill for Claude Code from borbiuk/band-play. It costs 35 tokens per session (699 once invoked), scanned A, original, MIT.

A local reference guide for Chrome browser extension development, including extension APIs, manifests, permissions, background code, content scripts, and messaging. Chrome extensions are small programs that add features to the browser.

In plain words
What is it for?
Building or debugging features that use Chrome APIs such as downloads, storage, or runtime messaging; editing the extension manifest; and checking API types, permissions, or official examples.
Why use it?
It gives the coding agent relevant Chrome documentation without requiring an internet connection or searching through unrelated material. This helps when API behavior or required permissions are unclear.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions AGENTS.md.

This is borbiuk/band-play's own configuration. It tells Claude Code how to work on band-play itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything band-play configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/borbiuk/band-play/master/.claude/skills/chrome-extension-docs/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/borbiuk/band-play

Made for: Claude Code.

Wrote 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.

agentmods badge for chrome-extension-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/borbiuk/band-play/chrome-extension-docs/github.svg)](https://agentmods.dev/skills/borbiuk/band-play/chrome-extension-docs)
Your own site
<a href="https://agentmods.dev/skills/borbiuk/band-play/chrome-extension-docs"><img src="https://agentmods.dev/badge/skills/borbiuk/band-play/chrome-extension-docs/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.

agentmods 80×15 button for chrome-extension-docs

Your own site · 80×15
<a href="https://agentmods.dev/skills/borbiuk/band-play/chrome-extension-docs"><img src="https://agentmods.dev/badge/skills/borbiuk/band-play/chrome-extension-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 699 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.00699
Opus 5 $0.00017 $0.00349
Sonnet 5 $0.00007 $0.00140
Haiku 4.5 $0.00003 $0.00070

Measured 9d ago against content hash ba4b09e56ede, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

chrome-extension-docs 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 9d 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.

.claude/skills/chrome-extension-docs/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chrome Extension API — local docs

Use this skill when the task involves Chrome extension APIs, manifest, permissions, or MV3 behavior. Do not load all doc files: read only the specific API or topic files relevant to the current task.

When to use

  • Implementing or changing code that uses chrome.* APIs (e.g. chrome.downloads, chrome.storage, chrome.runtime).
  • Editing public/manifest.json (permissions, background, manifest keys).
  • Debugging extension behavior, content scripts, or messaging.
  • Checking API types, permissions, or official examples.

Where the docs are

Local offline copies of Chrome extension docs (developer.chrome.com) live next to this file at:

references/developer.chrome.com/docs/extensions/

A full file index is in references/index.md. Path structure mirrors the site, for example:

  • API reference: reference/api/<apiName>.md (e.g. reference/api/downloads.md, reference/api/storage.md).
  • Manifest: reference/manifest/<key>.md (e.g. reference/manifest/background.md, reference/manifest/web-accessible-resources.md).
  • Concepts: develop/concepts/<topic>.md (e.g. develop/concepts/content-scripts.md, develop/concepts/storage-and-cookies.md).
  • How-to: how-to/..., reference/permissions.md, messaging.md, etc.

Instructions

  1. Identify the relevant doc: From the task, determine which API or topic is needed (e.g. downloads → reference/api/downloads.md).
  2. Read only that file (or a small set): Use the Read tool to open the specific .md file under references/developer.chrome.com/docs/extensions/. Do not read the whole directory or many files at once.
  3. Prefer local docs over web search: When the doc exists locally, use it instead of searching the web to avoid wrong or outdated snippets.
  4. Keep architecture rules in mind: Project-specific rules (entry points, manifest constraints, @shared/*) live in .claude/rules/ and AGENTS.md; this skill is only for Chrome API/manifest reference.

Read the full file on GitHub · 49 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 9d ago First seen · 49 lines · 35 tokens per session scan A ba4b09e56ede

Subscribe to this mod's changes

chrome-extension-docs is a skill published in the GitHub repository borbiuk/band-play (21 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 699 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.

Related

Other skills, from other repositories

codex-control-chrome-mcp

Use Codex Control Chrome MCP to control the user's normal Chrome profile through the Codex Chrome extension. Use when a task needs existing Chrome tabs, cookies, logged-in sessions, installed extensions, CDP commands, page inspection, navigation, screenshots, network/console events, or browser automation from an MCP…

iola1999/codex-control-chrome-mcp · 79 tokens

control-chrome-bridge

Drive the user's real Chrome browser — their own profile, tabs, cookies and logged-in sessions — through the chrome-bridge MCP server. Use for tasks that need existing browser state: reading a page behind a login, filling a form on a site the user is signed into, testing a local app in a real browser, or inspecting…

ShalomObongo/chrome-bridge-mcp · 114 tokens

hanzi-browse

Delegates a browsing task to a sub-agent running in the USER'S OWN Chrome — the browser they have open right now, already signed into everything. Give it a task in natural language ("check my LinkedIn DMs", "post this reply on X", "test signup on localhost:3000") and watch the sub-agent with browserstatus, steer it…

hanzili/hanzi-browse · 145 tokens

job-applier

Apply to jobs from your real browser. Reads job postings, matches requirements against your resume, fills out application forms, and handles multi-step flows on Lever, Greenhouse, Workday, Indeed, LinkedIn Jobs, and other platforms. Reviews everything before submitting. Requires the hanzi browser automation MCP server…

hanzili/hanzi-browse · 68 tokens

apartment-finder

Search for apartments across multiple real estate platforms, compare listings side by side, and help submit inquiries or applications. Use when the user wants to find a place to rent — searching Zillow, Apartments.com, Craigslist, and similar sites with their real signed-in browser. Examples: "find me a 1BR in Boston…

hanzili/hanzi-browse · 91 tokens

data-extractor

Extract structured data from websites into CSV or JSON. Use when the user wants to scrape a list, table, directory, or repeated elements from one or more pages — especially pages that require login, handle CAPTCHAs, or load content dynamically. Examples: "pull all company names and emails from this directory", "export…

hanzili/hanzi-browse · 0 tokens