coffee-roaster-mcp: Skill for Codex

.agents/skills/pi5-validation/SKILL.md

pi5-validation is a skill for Codex from syamaner/coffee-roaster-mcp. It costs 47 tokens per session (776 once invoked), scanned A, original, Apache-2.0.

A runbook for a human-supervised Raspberry Pi 5 test of coffee-roasting software. It documents read-only data capture, acceptance checks, and limits on private evidence without controlling the hardware.

In plain words
What is it for?
Planning or auditing a Pi 5 characterisation session, checking audio and telemetry thresholds, and reviewing whether supplied evidence meets acceptance rules.
Why use it?
It keeps validation sessions within agreed safety, privacy, and evidence boundaries. It also makes clear which actions require a human operator.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

This is syamaner/coffee-roaster-mcp's own configuration. It tells Codex 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 →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/sertanyamaner/Documents/RoastPilot/validation-evidence/pi5/<run-id>/.

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/.agents/skills/pi5-validation/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/syamaner/coffee-roaster-mcp

Made for: 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 pi5-validation

README.md
[![agentmods](https://agentmods.dev/badge/skills/syamaner/coffee-roaster-mcp/pi5-validation/github.svg)](https://agentmods.dev/skills/syamaner/coffee-roaster-mcp/pi5-validation)
Your own site
<a href="https://agentmods.dev/skills/syamaner/coffee-roaster-mcp/pi5-validation"><img src="https://agentmods.dev/badge/skills/syamaner/coffee-roaster-mcp/pi5-validation/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 pi5-validation

Your own site · 80×15
<a href="https://agentmods.dev/skills/syamaner/coffee-roaster-mcp/pi5-validation"><img src="https://agentmods.dev/badge/skills/syamaner/coffee-roaster-mcp/pi5-validation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 776 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 $0.00047 $0.00776
Opus 5 $0.00023 $0.00388
Sonnet 5 $0.00009 $0.00155
Haiku 4.5 $0.00005 $0.00078

Measured 6d ago against content hash a242ee4df61b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pi5-validation 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 6d 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.

.agents/skills/pi5-validation/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pi 5 Validation

Prepare a human-owned D183 plan or audit supplied evidence. This skill never operates a Pi, recording device, microphone, Hottop, serial device, or MCP server: the collector is read-only and no hardware action is authorised. Multi-stream Pi capture is out of #157/#194 and requires a later decision. Any collector alarm requires human-operator action; the collector and this skill do not actuate or direct a response.

Characterise before accepting

One supervised, no-actuation 60-minute characterisation session is required: the first 30 minutes run real ONNX inference with recording off; the next 30 minutes enable primary recording against the warmer system. Hottop serial telemetry is read-only. Recording is default-off; validation explicitly sets recording.enabled and recording.autocapture true, uses exactly one primary stream, and configures no additional recording device.

Only after characterisation may the human ratify N and X, which both lock before final acceptance. N is the non-negative permitted maximum consecutive audio-overflow count and is below the unchanged fatal streak limit of 30. X is permitted peak trailing-60-second lost-audio milliseconds. They are not valid-observation or exception counts and cannot be loosened from the run outcome.

Freeze this D183 identity set; any material change restarts characterisation: Pi board/RAM; 64-bit OS/kernel/firmware; PSU/cooling; storage; Python; candidate wheel SHA-256; dependency inventory; ONNX/model/config hashes; ALSA primary-device identity; and Hottop serial identity.

Accept separately and fail closed

Final acceptance is a separate supervised live session of at least 20 continuous minutes, not an interval inside characterisation. It is all-or-nothing for separate #157/#194 matrices: one immutable run may evidence both only when both pass; failure of either closes neither.

Evidence must include capture-run-lifetime max_consecutive_overflow_count, aggregated with max() across active inputs and reset with total overflow count; a frozen final snapshot; no unexpected capture restart; and monotonic last/max inference duration plus inference-overrun count. Acceptance requires:

Read the full file on GitHub · 68 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 68 lines · 47 tokens per session scan A a242ee4df61b

Subscribe to this mod's changes

pi5-validation is a skill published in the GitHub repository syamaner/coffee-roaster-mcp (0 stars, last pushed 5d ago), licensed Apache-2.0. It adds 47 tokens to every session and 776 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 2026-09-04.

Related

Other skills, from other repositories

testing-python

Write and evaluate effective Python tests using pytest. Use when writing tests, reviewing test code, debugging test failures, or improving test coverage. Covers test design, fixtures, parameterization, mocking, async testing, and CI integration.

AI-Riksarkivet/ra-mcp · 48 tokens

scrape-batch

Extract many known URLs in one polite, rate-limited pass. Use when the user hands over a list of links, a set of search hits to read in full, or asks to "scrape these pages" / "pull the content from all of them". Drives extract(action="batch"), which fans out with per-domain rate limiting and returns partial results…

n24q02m/wet-mcp · 84 tokens

compare

Structured comparison of 2+ alternatives with consistent criteria and decision matrix.

n24q02m/wet-mcp · 15 tokens

knowledge-audit

Review and clean up stored memories — find duplicates, contradictions, stale entries, and consolidate.

n24q02m/mnemo-mcp · 21 tokens

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

recall-context

Use at session start, before significant decisions, or when a new task references a known project to recall mnemo memories matching the current working directory, recently edited files, or topic keywords. Helps maintain continuity across sessions and avoid redoing past research.

n24q02m/mnemo-mcp · 53 tokens