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 skills/floomhq/moto/costnpx skills add floomhq/moto --skill costgit clone --depth 1 https://github.com/floomhq/motoWrote 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/floomhq/moto/cost)<a href="https://agentmods.dev/skills/floomhq/moto/cost"><img src="https://agentmods.dev/badge/skills/floomhq/moto/cost.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 5.1 | $0.00073 | $0.00913 |
| Opus 5 | $0.00036 | $0.00456 |
| Sonnet 5 | $0.00015 | $0.00183 |
| Haiku 4.5 | $0.00007 | $0.00091 |
Grade A, and why
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 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cost Skill
LLM API Pricing (as of early 2026)
Always verify current prices at the provider's pricing page - these change frequently.
Anthropic Claude
| Model | Input (per 1M tokens) | Output (per 1M tokens) |
|---|---|---|
| Claude Opus 4 | ~$15 | ~$75 |
| Claude Sonnet 4 | ~$3 | ~$15 |
| Claude Haiku 3.5 | ~$0.80 | ~$4 |
OpenAI
| Model | Input (per 1M tokens) | Output (per 1M tokens) |
|---|---|---|
| GPT-4o | ~$2.50 | ~$10 |
| GPT-4o mini | ~$0.15 | ~$0.60 |
Google Gemini
| Model | Input (per 1M tokens) | Output (per 1M tokens) |
|---|---|---|
| Gemini 2.5 Pro | ~$1.25 | ~$10 |
| Gemini 2.5 Flash | ~$0.15 | ~$0.60 |
Token Estimation
Rough approximations:
- 1 token ≈ 4 characters ≈ 0.75 words
- 1 page of text ≈ 750 tokens
- Average email ≈ 200-400 tokens
- Short code file ≈ 500-2000 tokens
Cost Calculation
def estimate_cost(
input_tokens: int,
output_tokens: int,
input_price_per_million: float,
output_price_per_million: float
) -> float:
input_cost = (input_tokens / 1_000_000) * input_price_per_million
output_cost = (output_tokens / 1_000_000) * output_price_per_million
return input_cost + output_cost
# Example: 1000 requests with 500 input tokens, 200 output tokens each
# Using Claude Sonnet ($3 in, $15 out per 1M)
total_input = 1000 * 500 # 500K tokens
total_output = 1000 * 200 # 200K tokens
cost = estimate_cost(total_input, total_output, 3, 15)
# = $0.15 + $3.00 = $3.15 for 1000 requests
Cloud Hosting (rough estimates)
| Service | Small | Medium | Large |
|---|---|---|---|
| Vercel (hobby) | Free | $20/mo | $150+/mo |
| Render (web service) | $7/mo | $25/mo | $85+/mo |
| Hetzner VPS | €5/mo | €20/mo | €80+/mo |
| AWS EC2 (t3) | $15/mo | $60/mo | $250+/mo |
Analysis Framework
When asked to estimate costs:
- Identify usage patterns: How many requests/day? Batch or real-time?
- Estimate token counts: Input context size + expected output size
- Calculate monthly volume: requests/day × 30
- Apply pricing: Use the table above or current pricing page
- Add buffer: Add 20-30% for variance and growth
- Compare alternatives: Show cost at different models/providers
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 · 104 lines · 73 tokens per session scan A 66d267d7ad73
cost is a skill published in the GitHub repository floomhq/moto (32 stars, last pushed 2mo ago), licensed MIT. It adds 73 tokens to every session and 913 once invoked, about $0.0004 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
churn-prevention
When the user wants to reduce churn or build retention systems — 'cancel flow,' 'save offer,' 'dunning,' 'failed payment recovery,' 'win-back,' 'exit survey,' 'pause subscription,' 'involuntary churn,' 'customers are leaving.' For post-cancel win-back sequences, see email-sequence. For in-app upgrade paywalls, see…
issue-triage
Issue triage: audit open issues, categorize, detect duplicates, cross-ref PRs, risk assessment, post comments. Args: "all" for deep analysis of all, issue numbers to focus (e.g. "42 57"), "en"/"fr" for language, no arg = audit only in French.
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…
moai-workflow-worktree
Git worktree management for parallel SPEC development with isolated workspaces, automatic branch registration, and seamless MoAI-ADK integration. Use when setting up parallel development environments.
moai-kanban-foreman
One unattended kanban foreman iteration: watch the backlog queue, dispatch the next operator-picked card to an isolated worker, collect completion evidence on read (not on claims), and report. This is the body the project's loop.md driver invokes each iteration of a bare /loop; it can also be invoked directly to test…
moai-workflow-thinking
Sequential Thinking MCP for structured step-by-step analysis via --deepthink flag. Separate from UltraThink which is Claude's native extended reasoning mode. Use for multi-step analysis or architecture decisions.