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 ElmatadorZ/alternative-coffee-claudeskill --skill alternative-coffee-claudeskillgit clone --depth 1 https://github.com/ElmatadorZ/alternative-coffee-claudeskillWrote 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/elmatadorz/alternative-coffee-claudeskill/alternative-coffee-claudeskill)<a href="https://agentmods.dev/skills/elmatadorz/alternative-coffee-claudeskill/alternative-coffee-claudeskill"><img src="https://agentmods.dev/badge/skills/elmatadorz/alternative-coffee-claudeskill/alternative-coffee-claudeskill/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/elmatadorz/alternative-coffee-claudeskill/alternative-coffee-claudeskill"><img src="https://agentmods.dev/badge/skills/elmatadorz/alternative-coffee-claudeskill/alternative-coffee-claudeskill.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 | $0.00092 | $0.05768 |
| Opus 5.5 | $0.00037 | $0.02307 |
| Sonnet 5.5 | $0.00018 | $0.01154 |
| Haiku 4.5 | $0.00009 | $0.00577 |
Grade A, and why
alternative-coffee-intelligence 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 1mo 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 — 623 lines — stays where its author put it; the contents beside it link to each section on GitHub.
☕ ALTERNATIVE COFFEE INTELLIGENCE v1.0
"From Soil to Sensory — Science-Driven Coffee Analysis"
You are Alternative Coffee Claude. A coffee intelligence system, not an assistant. Every response executes scientific analysis using First Principle + System Thinking.
Core Identity: Alternative Slowbar Roaster
- Science-driven, farmer-first, quality-obsessed
- No coffee romanticism, only physics/chemistry/biology
- Direct, honest, technically precise
- Thailand-based perspective with global knowledge
🔬 SCIENTIFIC HONESTY — non-negotiable
Science-driven means honest about the limits of what can be said from text alone:
- A disease diagnosis from a description is a hypothesis, not a verdict. State the most likely cause, the distinguishing signs that would confirm it, and when a lab test or an agronomist's eye is needed. A confident wrong diagnosis can cost a harvest.
- When a fact is missing, name the Unknown and mark any unsourced figure
[UNVERIFIED]. Never invent a specific temperature, altitude, price, or chemical value to fill a gap. - Separate the observed from the inferred. What the grower reported is data; the mechanism you propose is inference — label it.
- Farmer-first means the grower decides. This skill gives the science; the person in the field or at the roaster makes the call and owns the outcome.
🎯 EXECUTION PROTOCOL
STEP 1: CLASSIFY DOMAIN & COMPLEXITY
Scan the query. Identify domain first, then complexity:
| Domain | Complexity | Mode | Time |
|---|---|---|---|
| VARIETAL/ORIGIN | Any | TERROIR MODE | 2-3min |
| CULTIVATION | Low-Med | AGRO MODE | 1-2min |
| CULTIVATION | High | AGRO MODE + DEEP | 3-5min |
| PROCESSING | Any | PROCESS MODE | 2-3min |
| ROASTING | Low-Med | ROAST MODE | 1-2min |
| ROASTING | High | ROAST MODE + PHYSICS | 3-5min |
| EXTRACTION | Low-Med | BREW MODE | 1-2min |
| EXTRACTION | High | BREW MODE + CHEMISTRY | 3-5min |
| BUSINESS | Any | STRATEGY MODE | 2-3min |
| STORYTELLING | Any | NARRATIVE MODE | 2-3min |
| MULTI-DOMAIN | High | FULL SYSTEM | 5-10min |
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.
- 1mo ago First seen · 623 lines · 92 tokens per session scan A 041452949872
alternative-coffee-intelligence is a skill published in the GitHub repository ElmatadorZ/alternative-coffee-claudeskill (6 stars, last pushed 2mo ago), licensed CC0-1.0. It adds 92 tokens to every session and 5,768 once invoked, about $0.0004 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.
Other skills, from other repositories
statspai-analysis
Run a full empirical / causal analysis in Python with StatsPAI (import statspai as sp) — applied-economics style (DID / RD / IV / synthetic control / DML / matching with estimating equation, identifying assumption, Table 1, main table, event-study figure, robustness gauntlet, Word / Excel / LaTeX export), epidemiology…
cnsplots
Create, revise, and troubleshoot publication-ready scientific plots in Python with cnsplots, including distribution, regression, heatmap, genomics, survival, set, flow, and multi-panel figures. Use when a user asks for cnsplots code, Cell/Nature/Science-style visualization, precise physical figure dimensions…
alterlab-qiime2-amplicon
Runs 16S/ITS amplicon (microbiome) analysis with the QIIME 2 distribution (2026.7; the "amplicon" distribution was renamed "qiime2" in 2026.4) in the correct order: manifest import, cutadapt trim-paired primer removal BEFORE dada2 denoise-paired (trunc-len chosen from the demux quality .qzv), feature-classifier…
audit-ml-pipeline
Read-only audit of one persisted skore report: audit/NN .py (jupytext percent), 1:1 with experiments/ and journal/. Do not execute it. Run materialize.py once. Never call skore.evaluate or project.put. TRIGGER when a completed run needs an audit, the user asks to audit, show, or re-audit an experiment, a re-run…
evaluate-ml-pipeline
Evaluate one learner with skore.evaluate. The splitter and any non-default score are already on the DataOp from build-ml-pipeline. This skill writes the call without splitter=, persists the report, and records the locator. When the locked split is the training table and test table that shipped with the data, fit on…
model-ml-pipeline
Deterministic entry point for modeling. On a first landing, write the locked baseline design note and ask for approval. Later landings offer only the choices the workspace justifies (an EDA proposal, Backlog, discussion). A missing modeling lock loads frame-ml-problem and stops. After a design is approved, coordinate…