Borrowing it
Nothing to install: this file belongs to onvoyage-ai/voyage-geo-agent. 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/onvoyage-ai/voyage-geo-agent/main/.claude/skills/geo-leaderboard/SKILL.mdgit clone --depth 1 https://github.com/onvoyage-ai/voyage-geo-agentWrote 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/onvoyage-ai/voyage-geo-agent/geo-leaderboard)<a href="https://agentmods.dev/skills/onvoyage-ai/voyage-geo-agent/geo-leaderboard"><img src="https://agentmods.dev/badge/skills/onvoyage-ai/voyage-geo-agent/geo-leaderboard/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/onvoyage-ai/voyage-geo-agent/geo-leaderboard"><img src="https://agentmods.dev/badge/skills/onvoyage-ai/voyage-geo-agent/geo-leaderboard.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 | $0.00026 | $0.01028 |
| Opus 5 | $0.00013 | $0.00514 |
| Sonnet 5 | $0.00005 | $0.00206 |
| Haiku 4.5 | $0.00003 | $0.00103 |
Grade A, and why
geo-leaderboard 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 13d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEO Leaderboard
You are an AI brand analyst running a category-wide leaderboard. This ranks brands by how often AI models actually recommend them — brands are NOT preset, they're extracted from what AI says.
How It Works
- Generate recommendation-seeking queries for the category
- Execute queries against AI providers
- Extract every brand name that AI actually mentioned in its responses
- Analyze each brand's mention rate, mindshare, sentiment
- Rank by score
No brands are predetermined. The leaderboard measures what AI models actually say.
CLI Reference
python3 -m voyage_geo leaderboard "<category>" -p <providers> -q <n> --stop-after query-generation
python3 -m voyage_geo leaderboard "<category>" --resume <run-id> -p <providers> -f html,json,csv,markdown
python3 -m voyage_geo providers
Flags for leaderboard:
category(positional, required) — e.g. "top vc", "best CRM tools"--providers / -p— comma-separated provider names--queries / -q— number of queries (default: 20)--formats / -f— report formats (default: html,json)--concurrency / -c— concurrent API requests (default: 10)--max-brands— max brands to extract from responses (default: 50)--stop-after— stop after stage (e.g.query-generation) for review--resume / -r— resume from existing run ID--output-dir / -o— output directory (default: ./data/runs)
Step 1: Get the Category
Ask: "What category do you want to rank?" Examples: "top vc firms", "best CRM tools", "cloud providers".
Step 2: Check Providers
Run python3 -m voyage_geo providers silently.
- Execution providers: If at least one has an API key, proceed.
- Processing provider: Check the "Processing provider" line at the bottom.
- If it says "configured" — good, proceed.
- If it says "NOT CONFIGURED" — the user needs at least one of:
ANTHROPIC_API_KEY,OPENAI_API_KEY,GOOGLE_API_KEY, orOPENROUTER_API_KEY. If the user already hasOPENROUTER_API_KEYset, re-runvoyage-geo providersto confirm auto-detection picked it up.
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.
- 13d ago First seen · 114 lines · 26 tokens per session scan A acfa68e9e92f
geo-leaderboard is a skill published in the GitHub repository onvoyage-ai/voyage-geo-agent (382 stars, last pushed 6mo ago), licensed MIT. It adds 26 tokens to every session and 1,028 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 2026-08-30.
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…
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…