Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/nguyenthienthanh/aura-frognpx agentmods add skills/nguyenthienthanh/aura-frog/scalable-thinkingWrote 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/nguyenthienthanh/aura-frog/scalable-thinking)<a href="https://agentmods.dev/skills/nguyenthienthanh/aura-frog/scalable-thinking"><img src="https://agentmods.dev/badge/skills/nguyenthienthanh/aura-frog/scalable-thinking.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00015 | $0.00578 |
| Opus 5 | $0.00008 | $0.00289 |
| Sonnet 5 | $0.00003 | $0.00116 |
| Haiku 4.5 | $0.00002 | $0.00058 |
Grade A, and why
scalable-thinking 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 4d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI-consumed reference. Optimized for Claude to read during execution. Human-readable explanation: see docs/architecture/HIERARCHICAL_PLANNING.md or docs/getting-started/ depending on topic.
Skill: Scalable Thinking
Principle: Think Scalable, Build Simple.
| Aspect | Scalable Thinking (WHAT) | KISS (HOW) |
|---|---|---|
| Data Model | Normalized, indexed | Simple queries |
| API | Versioned, RESTful | Standard CRUD |
| Code Structure | Feature-based | Flat hierarchy |
| Config | Centralized | Single file |
Where to Apply
Data Models
Separate related data into proper tables (not JSON strings). Enables querying, indexing, partitioning.
APIs
RESTful resource paths with versioning: /api/v1/users/:userId/processes. Cacheable, evolvable.
Database
Normalized tables with foreign keys and indexes. Not JSON blobs that can't be filtered.
File Structure
Feature-based: src/features/{feature}/{hooks,components,api}/ + src/shared/.
Scalable Patterns
- Pagination: Cursor-based
?limit=20&cursor=abcwith{ nextCursor, hasMore } - Centralized config: Single config object with env-based values
- Structured errors:
AppErrorwith code + statusCode
Anti-Patterns
| Anti-Pattern | Instead |
|---|---|
| Build for hypothetical 1M users | Simple monolith first |
| Pre-optimize with Redis | In-memory cache, add Redis when measured |
| Abstract for 1 use case | Direct impl, abstract at 2-3 examples |
| Microservices from day 1 | Monolith, split when team/features grow |
Checklist
Before designing: Can model support 10x? Can I query needed data? Natural partition keys? API versioned? Pagination for lists?
During: Standard patterns? Simplest solution? Junior dev understandable? No abstractions until 3+ examples?
When to Scale Up
Add complexity when: DB queries > 2s, API p95 > 500ms, error rate > 1%, 10x growth in 3 months, team > 5. Until then: keep simple, measure everything.
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.
- 4d ago First seen · 80 lines · 15 tokens per session scan A 8cfcdbf90bd9
scalable-thinking is a skill published in the GitHub repository nguyenthienthanh/aura-frog (24 stars, last pushed 3d ago), licensed MIT. It adds 15 tokens to every session and 578 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 2026-09-03.
Other skills, from other repositories
draper-decorators
This skill should be used when the user asks to "create a decorator", "write a decorator", "move logic into decorator", "clean logic out of the view", "isn't it decorator logic", "test a decorator", or mentions Draper, keeping views clean, or representation logic in decorators. Should also be used when editing…
workers-best-practices
(APPLICATION CODE ONLY) Reviews and authors Cloudflare Workers code against production best practices. Use ONLY when writing or reviewing Worker code, configuring wrangler.jsonc, or checking for anti-patterns. Do NOT use for general Cloudflare product discovery (use cloudflare instead) or CLI management (use wrangler…
hono
Hono framework best practices. Use when building, reviewing, or debugging Hono applications, especially on Cloudflare Workers. Covers routing, middleware, context (c), and RPC patterns. Do NOT trigger for generic 'build a server' requests unless Hono or Cloudflare Workers is explicitly requested.
nodejs
Node.js core runtime standards. Use when working with native Node.js APIs like streams, buffers, childprocess, workerthreads, filesystem, or event loop tuning. Do NOT trigger for generic 'build a server' requests unless the platform/language is explicitly specified.
trpc
Skill "trpc" from neverinfamous/memory-journal-mcp, covering trpc guidelines, 1. routers and procedures, 2. context and middleware and 3. client integration.
zod
Zod schema validation standards. Use when defining schemas, parsing user input, transforming data, or integrating type-safe boundaries in API endpoints and configurations. SECURITY: Zod schemas are your primary security boundary. Ensure they are strict and handle all edge cases.