coffee-roaster-mcp: Skill for Claude Code

.claude/skills/release-registry/SKILL.md

release-registry is a skill for Claude Code from syamaner/coffee-roaster-mcp. It costs 22 tokens per session (607 once invoked), scanned A, original, Apache-2.0.

A review checklist for preparing RoastPilot, a coffee-roasting control service, for distribution through PyPI and the MCP Registry. It describes a planned release process and is currently for readiness review, not a fully runnable workflow.

In plain words
What is it for?
Use it to review package artifacts, README and registry metadata, clean-environment installation, mock-based smoke checks, and the final PyPI and MCP Registry publication steps.
Why use it?
It gathers the version, package, registry, installation, and verification checks in one place. This helps reveal missing release files or unfinished project stories before publishing.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is syamaner/coffee-roaster-mcp's own configuration. It tells Claude Code how to work on coffee-roaster-mcp 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 coffee-roaster-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to syamaner/coffee-roaster-mcp. 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/syamaner/coffee-roaster-mcp/main/.claude/skills/release-registry/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/syamaner/coffee-roaster-mcp

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 release-registry

README.md
[![agentmods](https://agentmods.dev/badge/skills/syamaner/coffee-roaster-mcp/release-registry/github.svg)](https://agentmods.dev/skills/syamaner/coffee-roaster-mcp/release-registry)
Your own site
<a href="https://agentmods.dev/skills/syamaner/coffee-roaster-mcp/release-registry"><img src="https://agentmods.dev/badge/skills/syamaner/coffee-roaster-mcp/release-registry/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 release-registry

Your own site · 80×15
<a href="https://agentmods.dev/skills/syamaner/coffee-roaster-mcp/release-registry"><img src="https://agentmods.dev/badge/skills/syamaner/coffee-roaster-mcp/release-registry.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 607 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 $0.00022 $0.00607
Opus 5 $0.00011 $0.00303
Sonnet 5 $0.00004 $0.00121
Haiku 4.5 $0.00002 $0.00061

Measured 8d ago against content hash 51c09aa45a22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

release-registry 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 8d 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/release-registry/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Registry - RoastPilot

Use this skill only for read-only package and registry release preparation or audit. Agents do not tag, approve environments, publish, or perform live verification.

Current Scope

  • v0.1.16 is published on PyPI and in the MCP Registry.
  • docs/release.md is the current release authority and preserves historical outcomes.
  • Tags, release-environment approval, publication, and live verification are human-operator-only. The intended future 0.2.0 line is not authority to tag or publish.

Release Targets

  • Package name: coffee-roaster-mcp
  • MCP Registry name: io.github.syamaner/coffee-roaster-mcp
  • Display title: RoastPilot

Human-Owned Release Flow

  1. Confirm the package version is intentional.
  2. Build and validate sdist plus wheel artifacts.
  3. Confirm README contains the MCP verification string when the release story adds it.
  4. Confirm server.json exists and matches the package version when the registry metadata story lands.
  5. The human operator publishes the package to PyPI.
  6. The human operator verifies it in a clean environment.
  7. The human operator runs published-package mock-safe smoke checks.
  8. The human operator publishes MCP Registry metadata.
  9. The human operator verifies the registry listing.

Current Review Checklist

Use this skill to review readiness only:

  • package name is still coffee-roaster-mcp
  • registry name is still io.github.syamaner/coffee-roaster-mcp
  • release docs do not imply hardware-ready support without Hottop validation
  • default first-crack mode remains disabled so package install smoke does not require audio or model download
  • version alignment across package metadata, tags, and server.json remains part of the release plan

Mock-Safe Published Smoke Target

For a human-owned published-package verification, the minimum smoke target is:

coffee-roaster-mcp --help
coffee-roaster-mcp --version
python -c "import os, tempfile; from coffee_roaster_mcp.config import load_config; tmp = tempfile.TemporaryDirectory(); os.chdir(tmp.name); c = load_config(environ={}); print(c.roaster.driver, c.first_crack.mode, c.first_crack.precision); tmp.cleanup()"

Read the full file on GitHub · 71 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. 8d ago Changed · +6 lines · -12 tokens per session 51c09aa45a22
  2. 11d ago First seen · 65 lines · 34 tokens per session scan A a7ac97a81f9b

Subscribe to this mod's changes

release-registry is a skill published in the GitHub repository syamaner/coffee-roaster-mcp (0 stars, last pushed 7d ago), licensed Apache-2.0. It adds 22 tokens to every session and 607 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.

Related

Other skills, from other repositories

memory-commit

Use when the user explicitly says "remember this", "save this", "ghi nho", "luu lai", "save for next time", or otherwise asks to persist the immediately preceding context. Captures with the appropriate contexttype (decision, preference, fact, skill, task, conversation) so future sessions can retrieve it accurately.

n24q02m/mnemo-mcp · 72 tokens

metagit-cli

CLI-only shortcuts for metagit agents — workspace catalog, discovery, prompts, sync, layout, and config. Use instead of MCP or HTTP API when operating from a shell or agentmode session.

metagit-ai/metagit-cli · 43 tokens

python-release

Handle Python SDK release, build, bump, packaging metadata, PyPI client pin, uv.lock, nox/build workflow, and publish verification changes. Use for Python release process work or dependency pin bumps; do not use for ordinary Python feature implementation.

ComposioHQ/composio · 53 tokens

polish-docs-meta

Finalize documentation and project metadata for a ship-ready release. Use after implementation is complete, tests pass, and devcheck is clean. Safe to run at any stage — each step checks current state and only acts on what still needs work.

cyanheads/git-mcp-server · 53 tokens

cortex-profile

View and manage your cognitive profile — how you think, work patterns, blind spots, and cross-domain connections. Use when the user says 'show my profile', 'how do I work', 'what are my patterns', 'cognitive style', 'blind spots', 'methodology', or at the start of a session to load context. Also use 'rebuild profile'…

cdeust/Cortex · 98 tokens

perseus

Use when you need a bounded, local Perseus context render before an assistant reads project state. Perseus resolves selected workspace inputs such as git, services, sessions, and task notes into markdown. Use for deterministic session starts, workspace audits, and explicit context handoffs.

Perseus-Computing-LLC/perseus · 58 tokens