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/.claude/skills/hottop-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/hottop-validation)<a href="https://agentmods.dev/skills/syamaner/coffee-roaster-mcp/hottop-validation"><img src="https://agentmods.dev/badge/skills/syamaner/coffee-roaster-mcp/hottop-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/hottop-validation"><img src="https://agentmods.dev/badge/skills/syamaner/coffee-roaster-mcp/hottop-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 | $0.00027 | $0.02813 |
| Opus 5 | $0.00014 | $0.01406 |
| Sonnet 5 | $0.00005 | $0.00563 |
| Haiku 4.5 | $0.00003 | $0.00281 |
Grade A, and why
hottop-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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hottop Validation - RoastPilot
Agents use this skill only to prepare or audit a human-owned plan or evidence. Only a named human operator may execute commands or touch a Pi, serial device, microphone, or Hottop. Agents must never execute commands or recommend proceeding autonomously.
Root AGENTS.md is the current hardware-free gate authority and supersedes any
stale gate wording in this skill.
Current Scope
- Hottop lifecycle, command-loop streaming, packet build/parse, control command state, and temperature-unit handling exist behind the
HottopRoasterDriverboundary. - The MCP roast-session tools call the configured
RoasterDriverboundary while preserving the one-session store semantics and fail-closed behavior. - The runnable validation entrypoint is
coffee-roaster-mcp hottop-validate. - Hardware stories are not complete from mock tests alone.
- For operator setup details, including the Hottop config block and log output
paths, use
docs/install-and-hardware-setup.md.
Pre-Validation Gates
The named human operator completes these gates before any Hottop hardware session; an agent may only audit the plan or resulting evidence.
1. Story And Source Readiness
- The named human operator confirms durable E3 history in
docs/state/epics/coffee-roaster-mcp-v0.1.mdand the current human-owned validation task; no E3 story is implied active. - The named human operator confirms unit and integration coverage exists in
tests/test_drivers.pyandtests/test_hottop_validation.py. - The named human operator confirms fail-closed behavior in
src/coffee_roaster_mcp/drivers.py.
2. Operator And Hardware Readiness
- The named human operator confirms the roaster is supervised for the full run.
- The named human operator confirms understanding of emergency stop, bean drop, cooling, and physical power-off expectations.
- The named human operator confirms the serial port is known and the config
explicitly sets
roaster.driver: hottop_kn8828b_2k_plus. - The named human operator confirms that
--include-dropis irreversible for loaded beans.
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 Changed · +31 lines · -9 tokens per session 8a1114786d66
- 9d ago First seen · 230 lines · 36 tokens per session scan A 399a67b66039
hottop-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 27 tokens to every session and 2,813 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.
Other skills, from other repositories
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.
research-topic
Multi-step research orchestration. Use when user asks "research X", "summarize current state of Y", "what's the latest on Z", or compares approaches. Calls extract(action="agent") which searches the web, extracts top results, then synthesises a citation-preserving Markdown answer with one configured LLM.
knowledge-audit
Review and clean up stored memories — find duplicates, contradictions, stale entries, and consolidate.
temporal-query
Answer time-travel questions over stored memory — what was believed at a past point in time, when a belief changed, and what replaced it. Use when the user says "as of", "back in", "at the time", "history of", "timeline", "what did I think then", or asks why a current memory contradicts an older one.
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.