Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add slavins-co/cellartracker-mcp --skill cellartracker-datagit clone --depth 1 https://github.com/slavins-co/cellartracker-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/slavins-co/cellartracker-mcp/cellartracker-data)<a href="https://agentmods.dev/skills/slavins-co/cellartracker-mcp/cellartracker-data"><img src="https://agentmods.dev/badge/skills/slavins-co/cellartracker-mcp/cellartracker-data/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/slavins-co/cellartracker-mcp/cellartracker-data"><img src="https://agentmods.dev/badge/skills/slavins-co/cellartracker-mcp/cellartracker-data.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 123 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 | $0.00171 | $0.03105 |
| Opus 5.5 | $0.00068 | $0.01242 |
| Sonnet 5.5 | $0.00034 | $0.00621 |
| Haiku 4.5 | $0.00017 | $0.00311 |
Grade A, and why
cellartracker-data 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 20d 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CellarTracker Data Parser
This skill enables Claude to parse, query, and cross-reference CellarTracker data for cellar management, purchase decisions, and drinking window guidance.
Data Source
When MCP tools are available (Claude Code or Claude Desktop), use the following tools for live data:
search-cellar— query current inventory by wine name, region, varietal, producer, etc.drinking-recommendations— get maturity-aware suggestions for what to drinkcellar-stats— overview of cellar composition (counts, categories, regions)purchase-history— full buy history with pricing and retailer inforecent-deliveries— wines actually received in a date range, by delivery dateincoming-orders— wines ordered but not yet received, from the Pending tableget-wishlist— current wishlist with notes on why each wine was addedconsumption-history— wines you've opened, with tasting contexttasting-notes— your tasting notes and reviews with ratings and scoresbottle-details— individual bottles (cellar + consumed) by wine name, location, bin, size, or barcoderefresh-data— force a fresh pull from CellarTracker
For bulk or SQL-style analysis (Claude Code), MCP resources expose the same cached CSVs directly — no per-tool result caps, and no need to hunt for the cache path:
cellartracker://tables/<Table>— the full raw CSV for one of the 8 tables (e.g.cellartracker://tables/List),text/csv, refreshed via the same cache the tools usecellartracker://meta/cache— JSON with per-table freshness timestamps and server version, useful to check before treating a resource read as current
When MCP is not available (Claude.ai Projects), look for uploaded CSV files:
- Individual
*_latest.csvfiles (most common) - Timestamped files like
List_20260313_015000.csv - Or attached directly in conversation
Table Overview
Eight tables are exported from CellarTracker. Not all will always be available — work with what's present.
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.
- 20d ago Changed · -4 lines 5f08a720b65f
- 1mo ago First seen · 226 lines · 171 tokens per session scan A fd771dae1d49
cellartracker-data is a skill published in the GitHub repository slavins-co/cellartracker-mcp (7 stars, last pushed 3d ago), licensed MIT. It adds 171 tokens to every session and 3,105 once invoked, about $0.0007 per session on Opus 5.5. 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
add-cloud-flow
Integrates Power Automate cloud flows into a Power Pages site. Lists available flows, suggests relevant ones based on intent, identifies scenarios and web roles, creates metadata files, and generates client-side code to call flows. Handles both new flow registration and adding already-registered flows to additional…
configure-env-variables
Configures environment variables for Power Pages site settings to support ALM across environments. Creates environment variable definitions in Dataverse, guides the user through linking site settings to those variables via the Power Pages Management app, adds the variables to the solution, and generates a…
edit-site
Plans, coordinates and customizes PAC CLI-downloaded Standard or Enhanced data model non-SPA Power Pages sites created from Microsoft templates or manually in Design Studio. Use for requests involving pages, localized content, navigation, assets, snippets, site markers, Liquid/web templates, page layouts, or styling.…
deploy-site
Deploys an existing Power Pages site to a Power Pages environment using PAC CLI. Routes SPA sites to the existing build and upload-code-site workflow, and PAC-downloaded non-SPA (classic) sites to an isolated upload workflow with explicit data-model and website-identity checks. Handles tooling verification…
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.