estimate-cost

A command that estimates infrastructure and API spending for a feature or an existing project. It compares projected costs for startup, growth, and large-scale usage and uses provider pricing references.

In plain words
What is it for?
Use it to price a proposed feature, estimate costs for different user volumes, or inspect a project to identify infrastructure expenses.
Why use it?
It helps reveal the likely cost of databases, cloud services, and APIs before a feature is built. This supports budgeting and choosing between cheaper and recommended options.

Command

Install

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.

agentmods
npx agentmods add commands/alphaaiservice/cortex/estimate-cost
Clone the repo
git clone --depth 1 https://github.com/alphaaiservice/cortex
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,130 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00037 $0.04130
Opus 5 $0.00018 $0.02065
Sonnet 5 $0.00007 $0.00826
Haiku 4.5 $0.00004 $0.00413

Measured yesterday against content hash 83a0d023012b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

estimate-cost 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 yesterday.

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.

commands/estimate-cost.md · 345 lines

How it starts

The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Estimate Cost — Infrastructure & API Cost Projection

Estimate costs for: $ARGUMENTS (default: analyze current project)

Calculate realistic infrastructure, API, and operational costs for features at three scales: Startup (100 users), Growth (10K users), and Scale (100K users). Works for ANY stack.

KEY PRINCIPLE: Use real pricing data, not guesses. Every estimate should reference actual provider pricing tiers. Always show the cheapest viable option alongside the recommended option.


Step 1: Identify Features to Cost

If $ARGUMENTS describes a specific feature:

Parse the feature description and identify all infrastructure components needed.

If $ARGUMENTS is empty (analyze current project):

Scan the codebase to detect all infrastructure dependencies:

# Detect cloud services
grep -ri "aws\|gcp\|azure\|vercel\|netlify\|railway\|render\|fly\.io\|supabase\|firebase\|heroku" . --include="*.json" --include="*.yml" --include="*.yaml" --include="*.toml" --include="*.env*" --include="*.tf" -l 2>/dev/null

# Detect databases
grep -ri "mysql\|postgres\|mongodb\|redis\|sqlite\|dynamodb\|firestore\|supabase" . --include="*.py" --include="*.ts" --include="*.js" --include="*.java" --include="*.json" --include="*.yml" -l 2>/dev/null

# Detect APIs and services
grep -ri "openai\|anthropic\|stripe\|razorpay\|twilio\|sendgrid\|mailgun\|algolia\|pinecone\|qdrant\|weaviate\|elasticsearch\|sentry\|posthog\|datadog\|newrelic" . --include="*.py" --include="*.ts" --include="*.js" --include="*.java" --include="*.json" --include="*.env*" -l 2>/dev/null

# Detect storage
grep -ri "s3\|minio\|cloudinary\|uploadthing\|cloudflare\|r2\|gcs\|blob" . --include="*.py" --include="*.ts" --include="*.js" --include="*.java" --include="*.json" -l 2>/dev/null

Build a component list:

INFRASTRUCTURE COMPONENTS DETECTED
═══════════════════════════════════
1. [Component] — [provider] — [purpose in the app]
2. [Component] — [provider] — [purpose in the app]
...

Read the full file on GitHub · 345 lines

Changes

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.

  1. yesterday First seen · 345 lines · 37 tokens per session scan A 83a0d023012b

Subscribe to this mod's changes

estimate-cost is a command published in the GitHub repository alphaaiservice/cortex (1 stars, last pushed 26d ago), licensed MIT. It adds 37 tokens to every session and 4,130 once invoked, about $0.0002 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.