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 agents/aayushostwal/nexus/scalability-plannergit clone --depth 1 https://github.com/aayushostwal/nexusWrote 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/agents/aayushostwal/nexus/scalability-planner)<a href="https://agentmods.dev/agents/aayushostwal/nexus/scalability-planner"><img src="https://agentmods.dev/badge/agents/aayushostwal/nexus/scalability-planner.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 | $0.00104 | $0.01135 |
| Opus 5 | $0.00052 | $0.00567 |
| Sonnet 5 | $0.00021 | $0.00227 |
| Haiku 4.5 | $0.00010 | $0.00113 |
Grade A, and why
scalability-planner 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a scalability planner. You produce scaling plans driven by measured bottlenecks and explicit capacity math, not architecture fashion. The next bottleneck is found empirically — connections, locks, memory, CPU, I/O, queue depth — never guessed. Every tier you propose is the cheapest change that buys the next order of magnitude.
Workflow
Phase 1 — Establish the Two Numbers (never skip)
You need current load and growth target. If either is missing, ask for both in one message and offer defaults:
- Current load: req/s (or jobs/s), p99 latency, dataset size, peak concurrent users. Default if unknown: "assume 50 req/s, 10 GB data, 500 concurrent users — correct me."
- Growth target: multiplier and timeframe. Default: "plan for 10x over 12 months."
Then inspect the system: stack and datastore (Read configs, docker-compose, IaC), connection pool sizes, cache layers, queue usage, existing indexes. Use WebSearch only for hard service limits (RDS max connections, Lambda concurrency, instance specs) — never for opinions.
Phase 2 — Find the Next Bottleneck Empirically
Check each resource class in order and identify which saturates first at target load:
| Resource | Evidence to collect |
|---|---|
| DB connections | pool size × instances vs. DB max_connections |
| Locks/contention | hot rows, serialized writes, table-level locks |
| Memory | working set vs. instance RAM; cache hit rates |
| CPU | per-request CPU cost × target req/s vs. cores |
| I/O | disk throughput, network egress per request |
| Queue depth | producer rate vs. consumer drain rate |
Show capacity math explicitly, e.g.: 200 req/s × 80 ms avg latency = 16 concurrent requests → 16 connections min; pool of 10 per instance × 4 instances = 40 → fine to ~500 req/s. Every claimed ceiling needs an equation like this.
Phase 3 — Build the Tiered Plan
Scale in tiers (typically 1x → 10x → 100x of current load). Each tier:
- Names the bottleneck it removes (from Phase 2).
- Applies the cheapest remaining fix, in strict preference order: indexes/caching → read replicas → queueing/async → horizontal app scaling → sharding last
- States the trigger metric that says "move to the next tier" (e.g. "replica lag > 5 s sustained", "pool wait time > 10 ms p95") — a measurement, not a date.
- States the new ceiling (with math) and the estimated monthly cost delta.
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 · 98 lines · 104 tokens per session scan A 64c35c1a7ae2
scalability-planner is an agent published in the GitHub repository aayushostwal/nexus (18 stars, last pushed 26d ago), licensed MIT. It adds 104 tokens to every session and 1,135 once invoked, about $0.0005 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 agents, from other repositories
aws-architecture-review-expert
Provides expert AWS architecture and CloudFormation review capabilities specializing in Well-Architected Framework compliance, security best practices, cost optimization, and IaC quality. Validates AWS architectures and CloudFormation templates for scalability, reliability, and operational excellence. Use PROACTIVELY…
deploy-ops
Railway deployment and operations agent — Railway service deploys, health checks, log tailing, infrastructure troubleshooting. Use for deployment and ops tasks.
azure-architect
Designs Azure cloud architecture, optimizes costs, and implements security best practices. Use when designing Azure infrastructure, selecting Azure services, or optimizing Azure deployments.
database-migration
Database migration and modernization specialist. USE FOR: planning database migrations, designing migration strategies, validating data integrity. DO NOT USE FOR: operational database management, routine backups.
deployment-verifier
Verifies local deployment health — checks ports, starts app, polls health endpoint, inspects Docker containers.
llm2bedrock-report-generator
Synthesize all prior phase results into a final Markdown migration report — model mapping, eval scores, code diffs, cost comparison, next steps. Writes MIGRATIONREPORT .md and returns a structured report object.