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.
curl -O https://raw.githubusercontent.com/syamaner/coffee-roaster-mcp/main/.agents/skills/pi5-validation/SKILL.mdgit clone --depth 1 https://github.com/syamaner/coffee-roaster-mcpWrote 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/syamaner/coffee-roaster-mcp/pi5-validation)<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.
<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>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 | $0.00047 | $0.00776 |
| Opus 5 | $0.00023 | $0.00388 |
| Sonnet 5 | $0.00009 | $0.00155 |
| Haiku 4.5 | $0.00005 | $0.00078 |
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.
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:
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.
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.
- 6d ago First seen · 68 lines · 47 tokens per session scan A a242ee4df61b
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.
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.
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…
compare
Structured comparison of 2+ alternatives with consistent criteria and decision matrix.
knowledge-audit
Review and clean up stored memories — find duplicates, contradictions, stale entries, and consolidate.
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.
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.