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 Abhinavbwj/Skills-Architects --skill geographic-foundationsgit clone --depth 1 https://github.com/Abhinavbwj/Skills-ArchitectsWrote 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/abhinavbwj/skills-architects/geographic-foundations)<a href="https://agentmods.dev/skills/abhinavbwj/skills-architects/geographic-foundations"><img src="https://agentmods.dev/badge/skills/abhinavbwj/skills-architects/geographic-foundations/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/abhinavbwj/skills-architects/geographic-foundations"><img src="https://agentmods.dev/badge/skills/abhinavbwj/skills-architects/geographic-foundations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to critical
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 →
- critical YARA Match · line 319 YARA rule matched a known webshell pattern (PHP, Python, JSP, or ASPX webshell).Fix: Remove the webshell code immediately. Webshells provide unauthorized remote command execution. Audit the skill for additional backdoors or persistence mechanisms.
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 | $0.00204 | $0.09232 |
| Opus 5 | $0.00102 | $0.04616 |
| Sonnet 5 | $0.00041 | $0.01846 |
| Haiku 4.5 | $0.00020 | $0.00923 |
Grade A, and why
geographic-foundations 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 12d 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 — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Geographic Foundations
Auto-activated layer that detects geographic context and routes architectural queries to the correct country-specific regulatory dossier. Loads before any code, life-safety, structural, or planning analysis.
1. Geographic Context Detection
When a user query includes any of the following signals, route to the named country skill before applying generic content from building-codes, fire-life-safety, or accessibility-design.
1.1 Direct Detection Triggers
| Signal Class | Examples | Route To |
|---|---|---|
| Country name | "India", "Bharat", "Republic of India" | country-india |
| Country name | "UAE", "Emirates", "Dubai", "Abu Dhabi" | country-uae |
| Country name | "Saudi", "KSA", "Kingdom of Saudi Arabia", "Riyadh" | country-saudi-arabia |
| Country name | "USA", "United States", "America" | country-usa |
| Country name | "UK", "Britain", "England", "Scotland", "Wales", "Northern Ireland" | country-uk |
| Country name | "Germany", "Deutschland", "DE" | country-germany |
| Country name | "Singapore", "SG" | country-singapore |
| Country name | "Japan", "Nippon", "JP" | country-japan |
| Country name | "China", "PRC", "Zhongguo" | country-china |
| Country name | "Australia", "AU", "Oz" | country-australia |
| Code reference | "IBC", "IRC", "IECC", "ASCE 7" | country-usa (then building-codes for IBC depth) |
| Code reference | "NBC India", "ECBC", "IS 1893", "IS 875" | country-india |
| Code reference | "NBC 2016" | country-india (disambiguate from "NBC Canada") |
| Code reference | "Approved Document", "AD-B", "Part L", "Part M" | country-uk |
| Code reference | "GEG", "DIN 18040", "LBO", "MBO" | country-germany |
| Code reference | "SBC 201", "SBC 301", "SBC 601", "SBC 801" | country-saudi-arabia |
| Code reference | "Dubai Building Code", "DBC", "ADIBC", "Estidama" | country-uae |
| Code reference | "NCC", "BCA Vol 1", "AS 1428", "AS/NZS 1170" | country-australia |
| Code reference | "Building Standards Act", "Kenchiku Kijun Hou" | country-japan |
| Code reference | "GB 50016", "GB 50352", "GB 50011", "JGJ" | country-china |
| Code reference | "BCA Singapore", "URA", "SCDF Fire Code" | country-singapore |
| City name | "Mumbai", "Delhi", "Bangalore", "Chennai", "Hyderabad", "Kolkata", "Pune", "Ahmedabad" | country-india |
| City name | "Dubai", "Abu Dhabi", "Sharjah", "Ajman" | country-uae |
| City name | "Riyadh", "Jeddah", "Mecca", "Medina", "Dammam", "NEOM" | country-saudi-arabia |
| City name | "New York", "Los Angeles", "Chicago", "San Francisco", "Boston", "Seattle", "Miami", "Houston" | country-usa |
| City name | "London", "Manchester", "Birmingham", "Edinburgh", "Glasgow", "Cardiff", "Belfast" | country-uk |
| City name | "Berlin", "Munich", "Hamburg", "Frankfurt", "Cologne", "Stuttgart" | country-germany |
| City name | "Tokyo", "Osaka", "Yokohama", "Kyoto", "Sapporo", "Fukuoka" | country-japan |
| City name | "Beijing", "Shanghai", "Guangzhou", "Shenzhen", "Chengdu", "Chongqing", "Hong Kong" | country-china (HK = SAR but follows BD Hong Kong codes; flag) |
| City name | "Sydney", "Melbourne", "Brisbane", "Perth", "Adelaide", "Canberra", "Hobart" | country-australia |
| Currency cue | "USD" (with site/cost) | country-usa (probable) |
| Currency cue | "INR", "Lakh", "Crore" | country-india |
| Currency cue | "AED", "Dirham" | country-uae |
| Currency cue | "SAR", "Riyal" | country-saudi-arabia |
| Currency cue | "GBP", "Pound" | country-uk |
| Currency cue | "EUR" (with EU country context) | route to relevant country (country-germany if no other cue) |
| Currency cue | "SGD" | country-singapore |
| Currency cue | "JPY", "Yen" | country-japan |
| Currency cue | "CNY", "RMB", "Yuan" | country-china |
| Currency cue | "AUD" | country-australia |
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.
- 12d ago First seen · 413 lines · 204 tokens per session scan A 7d54f85c3332
geographic-foundations is a skill published in the GitHub repository Abhinavbwj/Skills-Architects (285 stars, last pushed 3mo ago), licensed MIT. It adds 204 tokens to every session and 9,232 once invoked, about $0.0010 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…