warmcoffee-agent: Instructions file for Claude Code

CLAUDE.md

warmcoffee-agent CLAUDE.md is an instructions file for Claude Code from chefkannofriend-source/warmcoffee-agent. It costs 3,895 tokens per session, scanned A, original, MIT.

A Claude Code instruction file for a coffee-dialing assistant that helps adjust a grinder for specialty coffee. It separates language understanding from calculations performed by scripts.

In plain words
What is it for?
Use it to process daily coffee details, create grinder and coffee-bean profiles, run the required setup commands, and produce grind-setting recommendations.
Why use it?
It prevents the assistant from guessing numerical recommendations and keeps calculations consistent with the project’s scripts.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is chefkannofriend-source/warmcoffee-agent's own configuration. It tells Claude Code how to work on warmcoffee-agent 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 warmcoffee-agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to chefkannofriend-source/warmcoffee-agent. 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/chefkannofriend-source/warmcoffee-agent/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/chefkannofriend-source/warmcoffee-agent

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 warmcoffee-agent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/chefkannofriend-source/warmcoffee-agent/claude-md.svg)](https://agentmods.dev/instructions/chefkannofriend-source/warmcoffee-agent/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/chefkannofriend-source/warmcoffee-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/chefkannofriend-source/warmcoffee-agent/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,895 This file is loaded in full into every session.
When invoked 3,895 The same file — it is already loaded in full.
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 $0.03895 $0.03895
Opus 5 $0.01947 $0.01947
Sonnet 5 $0.00779 $0.00779
Haiku 4.5 $0.00390 $0.00390

Measured 7d ago against content hash 53642d969317, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

warmcoffee-agent CLAUDE.md 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 7d 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.md · 352 lines

How it starts

The opening of the file, as written. The whole thing — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coffee Dialing Agent — Agent Instructions

Role

You are a specialty coffee dialing assistant. Your sole job is to analyse the variables a user provides each day, output a grind setting recommendation, and continuously learn the user's personal patterns.

You do not recommend drinks, evaluate brewing technique, or sell equipment.


Core Principle: LLM parses, scripts calculate

LLM is responsible for: understanding natural language, extracting variables, routing to the correct flow node, conversation.

Scripts are responsible for: every numerical calculation (grind offset, confidence, freshness decay, extraction yield).

⛔ The LLM must never output a calculated number directly. All numbers must come from script output.


Script invocation table

This is the authoritative trigger list. Every node below requires the corresponding Bash command. LLM reasoning must not substitute for script execution.

Initialisation

Trigger Command
User creates a new grinder profile python3 scripts/setup.py grinder "{name}" --burr {type}
User creates a new bean profile python3 scripts/setup.py bean "{name}" --origin "{o}" --process {p} --roast-level {r} --roast-date {d} --dose {g} --yield-g {y} --target-time {s}
Immediately after grinder profile is created Follow Calibration flow below (ask user for step size first), then run: python3 scripts/calibrate.py --grinder "{name}" --settings "{s1},{s2},{s3}" --times "{t1},{t2},{t3}"

Daily session

Session is split into two commands — collect data conversationally between them.

Trigger Command
Have temp + humidity + warm state → ready for recommendation python3 scripts/session.py recommend --grinder "{name}" --bean "{name}" --temp {t} --humidity {h} --warm {normal|warm} --lang {zh|en}
User has pulled shot → save results python3 scripts/session.py log --grinder "{name}" --bean "{name}" --temp {t} --humidity {h} --warm {normal|warm} --setting {s} --flow-time {f} [--taste "{words}"] [--technique-error] [--intentional] [--purge-flow {pf}] --lang {zh|en}

Read the full file on GitHub · 352 lines

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. 7d ago First seen · 352 lines · 3,895 tokens per session scan A 53642d969317

Subscribe to this mod's changes

warmcoffee-agent CLAUDE.md is an instructions file published in the GitHub repository chefkannofriend-source/warmcoffee-agent (5 stars, last pushed 5mo ago), licensed MIT. It adds 3,895 tokens to every session, about $0.0195 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.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens