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 cablate/mcp-google-map --skill google-mapsgit clone --depth 1 https://github.com/cablate/mcp-google-mapWrote 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/cablate/mcp-google-map/google-maps)<a href="https://agentmods.dev/skills/cablate/mcp-google-map/google-maps"><img src="https://agentmods.dev/badge/skills/cablate/mcp-google-map/google-maps/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/cablate/mcp-google-map/google-maps"><img src="https://agentmods.dev/badge/skills/cablate/mcp-google-map/google-maps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, 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 Rogue Agent · line 105 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium MCP Rug Pull · line 94 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Agent Snooping · line 123 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00055 | $0.00781 |
| Opus 5.5 | $0.00022 | $0.00312 |
| Sonnet 5.5 | $0.00011 | $0.00156 |
| Haiku 4.5 | $0.00006 | $0.00078 |
Grade A, and why
google-maps 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 28d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Maps
Answer real-world location questions with the package's standalone exec CLI. Do not start or configure an MCP server for this workflow.
Before calling the CLI
- On the first call in a session, or after an execution failure, read
../_shared/setup-and-diagnostics.mdand run the non-billable local preflight. - The user must supply
GOOGLE_MAPS_API_KEY. Never print it or place it in a command unless the user explicitly accepts shell-history and process-list exposure. - Before presenting Places reviews, photos, or AI summaries, read
../_shared/content-attribution.md.
Workflow
- Identify the concrete location outcome and missing inputs. Do not request details that can be resolved by geocoding or place search.
- Read
references/tools-api.mdwhen exact parameters, response fields, or a multi-tool recipe are needed. - Prefer coordinates over ambiguous addresses and
place_idover repeated name searches. - Chain only the calls needed for the outcome. Reuse returned identifiers and coordinates.
- Treat nonzero exit status or
{ "success": false }as a failure, not as geographic data. - Summarize the useful result rather than returning raw JSON. Preserve source and attribution metadata where required.
Tool selection
| Outcome | Preferred tools |
|---|---|
| Address or landmark to coordinates | maps_geocode |
| Coordinates to address | maps_reverse_geocode |
| Nearby discovery | maps_search_nearby, then maps_place_details |
| Natural-language place search | maps_search_places, then maps_place_details |
| Compare candidate places | maps_compare_places or search → details → distance matrix |
| Route or travel-mode comparison | maps_directions, maps_distance_matrix |
| Multi-stop route without a broader itinerary | maps_plan_route |
| Things along a route | maps_search_along_route |
| Neighborhood facts | maps_explore_area plus targeted nearby searches |
| Elevation, timezone, weather, or air quality | corresponding environment tool; geocode first when needed |
| Visual map | maps_static_map after locations or a route are known |
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.
- 28d ago Changed · -53 lines · +9 tokens per session 80f3cf405ba1
- 1mo ago Changed · -8 lines · -34 tokens per session 26a4af221d3a
- 1mo ago First seen · 124 lines · 80 tokens per session scan A 6c0ab3bdb768
google-maps is a skill published in the GitHub repository cablate/mcp-google-map (479 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 781 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
yahoo-finance2
Use when building with the yahoo-finance2 TypeScript/Deno/npm library, using its Yahoo Finance data modules, CLI, or MCP server, or contributing to the yahoo-finance2 repository including modules, validation schemas, cached fixtures, and npm/JSR build output.
x-twitter-scraper
Use Xquik to fetch X (Twitter) data or act through a connected account. It covers search, profiles, followers, replies, threads, timelines, media downloads, bulk exports, trends, monitors, signed webhooks, draws, posts, likes, follows, DMs, and AI analysis of posts (sentiment, brand mentions, news, market signals…
xquik-mcp
Connect, verify, and troubleshoot Xquik's remote MCP server. Use when a user needs MCP setup, OAuth recovery, tool discovery, endpoint execution, or a connection check in ChatGPT, Claude, Codex, Cursor, VS Code, or another compatible client. Covers the endpoint, OAuth and the API key fallback, the docs, search, and…
xquik-social-research
Research X data with Xquik, the world's fastest and cheapest X Twitter scraper service with the most complete X data. Use only when the request or active context identifies X or Twitter. Use for tweet search, tweet lookup, user discovery, profile timelines, threads, followers, trends, exports, or monitoring plans. Do…
tgcli
Telegram CLI for reading/searching messages, syncing archives, and sending or downloading files. Use when the user asks about Telegram chats, messages, contacts, groups, or files.
kolmopdf
A workflow for using KolmoPDF, a paid cloud service, to process PDFs or Markdown files. It supports PDF parsing, translation, export to common document formats, and reading aids such as outlines and summaries.