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 skills add jdevalk/cocktail.glass --skill substitute-an-ingredientgit clone --depth 1 https://github.com/jdevalk/cocktail.glassWrote 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/skills/jdevalk/cocktail.glass/substitute-an-ingredient)<a href="https://agentmods.dev/skills/jdevalk/cocktail.glass/substitute-an-ingredient"><img src="https://agentmods.dev/badge/skills/jdevalk/cocktail.glass/substitute-an-ingredient/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/skills/jdevalk/cocktail.glass/substitute-an-ingredient"><img src="https://agentmods.dev/badge/skills/jdevalk/cocktail.glass/substitute-an-ingredient.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 | $0.00029 | $0.00493 |
| Opus 5 | $0.00015 | $0.00246 |
| Sonnet 5 | $0.00006 | $0.00099 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
substitute-an-ingredient 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 10d 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.
What it actually says
Substitute an ingredient
A recipe asks for an ingredient the person does not have. Decide whether a swap is safe, and if it is not, use cocktail.glass to find a drink that fits what they do have.
Judging a substitution
Not every swap works. Use these rules of thumb:
- Same family, similar role — usually safe. Bourbon for rye, one London dry gin for another, light rum for a different light rum. Expect a shift in emphasis, not a broken drink.
- Same family, different intensity — works with care. An aged rum for a light one, reposado tequila for blanco: the drink survives but turns heavier or oakier. Say so.
- A modifier or bittering agent — do not swap blindly. Campari, Chartreuse, absinthe, and the bitters each define the drinks they are in. Replacing them turns the cocktail into a different one.
- Citrus is not interchangeable. Lemon and lime behave differently; swapping one for the other rebalances the drink.
When a swap only shifts emphasis, suggest it and name the effect. When it would change the character of the drink, say so plainly.
Finding an adjacent drink instead
If no safe swap exists, do not force it — find a different cocktail that uses
what the person already has. On the MCP server at https://cocktail.glass/mcp:
find_cocktails_by_ingredient— every drink built on an ingredient they do have. Good for "I have mezcal, what else can I make."find_makeable_cocktails— pass everything on hand and get the drinks that need no substitution at all.get_cocktail_recipe— re-check the original recipe's other ingredients before recommending a swap, so the whole drink still balances.
The catalogue is also one JSON file at https://cocktail.glass/cocktails.json
if you cannot reach the MCP server.
Always
Link any cocktail you suggest to its page at https://cocktail.glass/<slug>/
so a person can open the full recipe.
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.
- 10d ago First seen · 50 lines · 29 tokens per session scan A 225e78bf9fbd
substitute-an-ingredient is a skill published in the GitHub repository jdevalk/cocktail.glass (7 stars, last pushed 16d ago), licensed MIT. It adds 29 tokens to every session and 493 once invoked, about $0.0001 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.
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…
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.
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.
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.
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.
anvil-refresh
A content review tool that finds older or potentially outdated pages in an AnvilWiki game site and produces a prioritized update list.