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 agentmods add skills/oakley7247/google-maps-harness/google-mapsnpx skills add oakley7247/google-maps-harness --skill google-mapsgit clone --depth 1 https://github.com/oakley7247/google-maps-harnessWrote 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/oakley7247/google-maps-harness/google-maps)<a href="https://agentmods.dev/skills/oakley7247/google-maps-harness/google-maps"><img src="https://agentmods.dev/badge/skills/oakley7247/google-maps-harness/google-maps.svg" alt="Measured on agentmods" 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 | $0.00188 | $0.02175 |
| Opus 5 | $0.00094 | $0.01087 |
| Sonnet 5 | $0.00038 | $0.00435 |
| Haiku 4.5 | $0.00019 | $0.00217 |
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 5d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Maps
Thirteen commands over six Google Maps Platform APIs, all read-only. One script does the work: scripts/maps.py. Run it with bash and read the JSON it prints — its code never needs to enter your context.
Before the first call
Two things make this work, and both fail loudly rather than silently, so check them once at the start of a conversation rather than debugging mid-answer.
1. The API key. The script looks in this order and never accepts a key as a command-line argument:
- the
GOOGLE_MAPS_API_KEYenvironment variable - a file named with
--key-file - a file called
google-maps-key.txtor.envin the working directory or the usual upload locations
If no key is found, the script says so and names what it looked for. Ask the user to upload a small text file containing just the key rather than pasting the key into the chat — a pasted key lives in the conversation transcript for good, while an uploaded file does not. If they paste it anyway, write it to a file and use --key-file; don't repeat it back.
2. Network access. This is the one that blocks people, and it is never the key. A sandbox reaches the internet through a managed proxy that allows only listed domains, and googleapis.com is not on the default list — so every call fails identically, and no retry changes that.
check prints a PROXY line that says which of the two causes you have:
- a proxy is named but requests go direct → re-run with
--use-proxy - requests already go through it, or there is none → the domains are not allowlisted. The user has to add them under Settings → Capabilities → Code execution. The six hosts are in
references/setup.md.
Report which one it is and stop. Looping on this wastes the conversation.
Check both at once, before promising results. One command separates the three failures that look identical from the outside — no key, no network, and an API switched off:
python3 scripts/maps.py check
It reports where it looked for the key, whether Google is reachable, and which APIs answer. Add --all to probe all seven rather than one. It spends one request, or seven with --all, and prints no part of the key.
What ships with it
3 files 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.
- 5d ago First seen · 128 lines · 188 tokens per session scan A 20d6f092cd7f
google-maps is a skill published in the GitHub repository oakley7247/google-maps-harness (0 stars, last pushed 4d ago), licensed MIT. It adds 188 tokens to every session and 2,175 once invoked, about $0.0009 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…