agentmods.dev

cocktails-from-my-bar

cocktails-from-my-bar is a skill for Claude Code, Codex from jdevalk/cocktail.glass. It costs 33 tokens per session (506 once invoked), scanned A, original, MIT.

A cocktail finder that uses a photo of a home bar or a typed bottle list to identify drinks that can be made immediately. It matches the available ingredients with recipes from cocktail.glass.

In plain words
What is it for?
Inventorying spirits, liqueurs, mixers, juices, and bitters; finding matching cocktails; and listing recipes that are available or nearly available.
Why use it?
It removes the guesswork from deciding what to mix and shows which drinks require only one additional bottle. Brand names are converted to their general ingredient types.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 7repo 17d ago A scan 33 tokens original MIT

Good fit Inventorying spirits, liqueurs, mixers, juices, and bitters; finding matching cocktails; and listing recipes that are available or nearly available.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jdevalk/cocktail.glass/cocktails-from-my-bar
View source ↗ jdevalk/cocktail.glass cocktail.glass
Install

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.

Any agent
npx skills add jdevalk/cocktail.glass --skill cocktails-from-my-bar
Clone the repo
git clone --depth 1 https://github.com/jdevalk/cocktail.glass

Made for: Claude Code, Codex.

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 cocktails-from-my-bar

README.md
[![agentmods](https://agentmods.dev/badge/skills/jdevalk/cocktail.glass/cocktails-from-my-bar/github.svg)](https://agentmods.dev/skills/jdevalk/cocktail.glass/cocktails-from-my-bar)
Your own site
<a href="https://agentmods.dev/skills/jdevalk/cocktail.glass/cocktails-from-my-bar"><img src="https://agentmods.dev/badge/skills/jdevalk/cocktail.glass/cocktails-from-my-bar/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 cocktails-from-my-bar

Your own site · 80×15
<a href="https://agentmods.dev/skills/jdevalk/cocktail.glass/cocktails-from-my-bar"><img src="https://agentmods.dev/badge/skills/jdevalk/cocktail.glass/cocktails-from-my-bar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 506 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 $0.00033 $0.00506
Opus 5 $0.00016 $0.00253
Sonnet 5 $0.00007 $0.00101
Haiku 4.5 $0.00003 $0.00051

Measured 11d ago against content hash 86a0515c690c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

cocktails-from-my-bar 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 11d 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.

public/.well-known/agent-skills/cocktails-from-my-bar/SKILL.md · 48 lines

What it actually says

Cocktails from my bar

Given a photo of someone's liquor cabinet — or a typed list of what they own — work out which cocktails they can make right now, and which they are one bottle short of.

Steps

  1. Inventory the bottles. From the photo or list, identify every spirit, liqueur, mixer, juice, and bitters. Read labels carefully.

  2. Normalise to generic ingredients. cocktail.glass recipes use generic ingredient names, not brands. Map each bottle to its base type:

    • "Bombay Sapphire" → gin
    • "Cointreau" → triple sec
    • "Martini Rosso" → sweet vermouth
    • "Tanqueray No. Ten" → gin

    Keep distinct products distinct: sloe gin is not gin, and orange bitters is not orange.

  3. Ask cocktail.glass what is makeable. Call the find_makeable_cocktails tool on the MCP server at https://cocktail.glass/mcp, passing the full list of normalised ingredients in a single call. If you cannot reach the MCP server, fetch the whole catalogue from https://cocktail.glass/cocktails.json and match locally: a cocktail is makeable when every one of its ingredients is covered by the list. Garnishes are optional and plain water is assumed on hand.

  4. Report two lists. "Make now" — drinks they have every ingredient for. "One bottle away" — drinks missing exactly one ingredient, naming the missing ingredient for each. Order each list simplest drink first.

  5. Always link the recipe. Every cocktail on cocktail.glass has a page at https://cocktail.glass/<slug>/. Link each suggestion so a person can open the full recipe.

Notes

  • The catalogue is 500 cocktails, read-only and public — no key, no login.
  • find_makeable_cocktails already returns both lists (makeable and almostMakeable), so prefer it over matching ingredients by hand.
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. 11d ago First seen · 48 lines · 33 tokens per session scan A 86a0515c690c

Subscribe to this mod's changes

cocktails-from-my-bar is a skill published in the GitHub repository jdevalk/cocktail.glass (7 stars, last pushed 17d ago), licensed MIT. It adds 33 tokens to every session and 506 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 2026-08-31.

Creative and mediaastrocloudflare-pagescocktail-recipescocktailsllms-txtmcp
Related

Other skills, from other repositories

specification-website

Query and apply The Website Specification — a platform-agnostic specification of what a good website does, with each item tagged required, recommended, optional, or avoid. Use when the user asks what their site should have, whether something is required, how to audit a URL, what's missing for agent readiness, or…

jdevalk/specification.website · 127 tokens

anvil-find-keywords

A research procedure for finding and evaluating game-related search terms across several sources. It checks search results and user intent, then records whether each idea should be pursued, rejected, or reviewed later.

PNGTRID/AnvilWiki · 110 tokens

anvil-new-article

A tool that turns supplied material into MDX article pages for AnvilWiki, a wiki site built from structured content files. It fills in page details and checks that the pages follow the site’s rules.

PNGTRID/AnvilWiki · 111 tokens

anvil-batch-articles

A batch article generator for creating many AnvilWiki MDX pages from a list of keywords. MDX is Markdown with added components and structured fields for a website.

PNGTRID/AnvilWiki · 100 tokens

aov-mingyu-api

An interface to the aov.cc public API for Chinese astrology, divination, tarot, calendars, and related prompt generation.

tradecatlabs/fatecat · 105 tokens

anvil-update-codes

A tool for updating a game wiki’s reward-code page from codes supplied by the user. It keeps working and expired codes in structured page data.

PNGTRID/AnvilWiki · 69 tokens