mailnotmilk: Skill for Claude Code

.claude/skills/browser-relay/SKILL.md

browser-relay is a skill for Claude Code from jrb00013/mailnotmilk. It costs 36 tokens per session (195 once invoked), scanned A, original, MIT.

Instructions for controlling an AI chat page opened in Chrome through the mailnotmilk browser extension. The extension connects browser messages to relay and shared-chat tools.

In plain words
What is it for?
Use it to connect to an open AI chat page, read its messages, send replies, and relay conversations through mailnotmilk.
Why use it?
It provides a setup that works with Chrome’s normal launch process and avoids requiring remote debugging or manual extension loading. It also keeps login and browser setup steps out of the workflow.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is jrb00013/mailnotmilk's own configuration. It tells Claude Code how to work on mailnotmilk 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 mailnotmilk configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jrb00013/mailnotmilk. 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/jrb00013/mailnotmilk/main/.claude/skills/browser-relay/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/jrb00013/mailnotmilk

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 browser-relay

README.md
[![agentmods](https://agentmods.dev/badge/skills/jrb00013/mailnotmilk/browser-relay/github.svg)](https://agentmods.dev/skills/jrb00013/mailnotmilk/browser-relay)
Your own site
<a href="https://agentmods.dev/skills/jrb00013/mailnotmilk/browser-relay"><img src="https://agentmods.dev/badge/skills/jrb00013/mailnotmilk/browser-relay/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 browser-relay

Your own site · 80×15
<a href="https://agentmods.dev/skills/jrb00013/mailnotmilk/browser-relay"><img src="https://agentmods.dev/badge/skills/jrb00013/mailnotmilk/browser-relay.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 195 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 $0.00036 $0.00195
Opus 5.5 $0.00014 $0.00078
Sonnet 5.5 $0.00007 $0.00039
Haiku 4.5 $0.00004 $0.00019

Measured 2mo ago against content hash 8745affec10d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

browser-relay 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 2mo 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/browser-relay/SKILL.md · 30 lines

What it actually says

browser-relay

Setup

./install.sh auto-installs the extension (External Extensions + desktop launcher). User fully quits Chrome once, then uses the normal shortcut.

Re-run only: mailnotmilk extension

Flow

  1. Chrome open normally + any AI site
  2. browser_connect { "mode": "extension" }
  3. relay_tick / chat_say / browser_send_message

Rules

  • Never require --remote-debugging-port
  • Never ask for manual Load unpacked (install handles it)
  • Never ask the user to log in
  • Works for any http(s) chat UI
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. 2mo ago First seen · 30 lines · 36 tokens per session scan A 8745affec10d

Subscribe to this mod's changes

browser-relay is a skill published in the GitHub repository jrb00013/mailnotmilk (2 stars, last pushed 8d ago), licensed MIT. It adds 36 tokens to every session and 195 once invoked, about $0.0001 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.

Related

browser-relay compared with skills from other repositories

browser-relay next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
browser-relayjrb00013/mailnotmilkSkill28d agoMITA36Claude Code
interactive-loginyc-software/qmSkill16kyesterdayMITA46Claude Code, Codex
pinchtab-mcppinchtab/pinchtabSkill11k10d agoMITA52Claude Code, Codex
azure-messaging-webpubsub-javamicrosoft/skillsSkill3.2kyesterdayMITA43Claude Code
cua-driverdavidondrej/skillsSkill4.3k3d agoMITA68Claude Code, Codex
open-design-browsercompozy/compozySkill2.8kyesterdayMITA56Claude Code, Codex
southwestborski/travel-hacking-toolkitSkill895yesterdayMITA40Claude Code