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 alexclowe/awesome-copilot-cowork-plugins --skill ai-billing-modelsgit clone --depth 1 https://github.com/alexclowe/awesome-copilot-cowork-pluginsWrote 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/alexclowe/awesome-copilot-cowork-plugins/ai-billing-models)<a href="https://agentmods.dev/skills/alexclowe/awesome-copilot-cowork-plugins/ai-billing-models"><img src="https://agentmods.dev/badge/skills/alexclowe/awesome-copilot-cowork-plugins/ai-billing-models/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/alexclowe/awesome-copilot-cowork-plugins/ai-billing-models"><img src="https://agentmods.dev/badge/skills/alexclowe/awesome-copilot-cowork-plugins/ai-billing-models.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00037 | $0.00549 |
| Opus 5 | $0.00018 | $0.00275 |
| Sonnet 5 | $0.00007 | $0.00110 |
| Haiku 4.5 | $0.00004 | $0.00055 |
Grade A, and why
ai-billing-models 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 11d 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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You have deep fluency in how AI products bill. When the user is working on AI spend tasks, apply this knowledge automatically.
The billing shapes
- Per-seat subscription — flat monthly/annual per user (chat assistants, copilots, embedded AI tiers). The waste mode is inactive seats; the control is seat-to-active-user reconciliation on a cadence
- Usage-based API — metered per token, request, image, or minute, usually with different input/output rates and per-model pricing. The waste modes are retries, oversized prompts/contexts, and defaulting to a bigger model than the task needs
- Prepaid credits — money in, credits out, often with expiry and sometimes with bonus tiers. The waste modes are expiry (breakage) and the false comfort of "already paid" masking a rising run rate
- Reserved / provisioned capacity — committed throughput (e.g., provisioned units) billed whether used or not. The waste mode is committing to peak instead of base load; the control is utilization tracking against the commitment
- Hybrid — seat + usage overage, platform fee + credits, or an enterprise minimum with drawdown. Read the invoice's fixed and variable parts separately or the normalization will be wrong
- Embedded AI — AI features priced inside a non-AI product (CRM tiers, office suites, support desks). Frequently invisible in an "AI spend" search because the line item doesn't say AI
Normalization rules
- Amortize annual prepay to monthly (÷12) and SAY it's amortized — cash timing and run rate are different questions
- Convert credit purchases to run rate from actual burn (credits used per month × price per credit), not from the purchase amount
- Count reserved capacity at commitment, with a utilization percentage alongside — 40% utilization of a committed pool is the finding, not a lower cost
- Keep one currency and one period; label estimates as estimates every time
Contract mechanics worth flagging
- Auto-renewal windows and notice periods (the negotiation clock starts at notice-minus-30, not at renewal)
- True-up clauses on seat growth; whether unused seats true DOWN
- Credit rollover and expiry terms
- Rate-lock or price-protection language, and what happens to grandfathered pricing at renewal
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.
- 11d ago First seen · 32 lines · 37 tokens per session scan A 10fd519e64cd
ai-billing-models is a skill published in the GitHub repository alexclowe/awesome-copilot-cowork-plugins (17 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 549 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 2026-08-30.
Other skills, from other repositories
cfo-reviewer
Reviews a proposal, business case, deck or plan in character as a Chief Financial Officer archetype, then saves a structured review document with a verdict, findings that cite the artifact, finance risks and five interrogation questions. Use when the user asks for a CFO review, a finance-lens pressure-test of a…
investor-reviewer
Reviews a proposal, business case, deck or plan in character as an Investor archetype, then saves a structured review document with a verdict, findings that cite the artifact, capital-allocation risks and five interrogation questions. Use when the user asks for an investor review, a capital-lens pressure-test of a…
apify-x402-agentic-wallet
Discover, pay for, and run any Apify Actor by paying USDC on Base over the x402 protocol with a Coinbase Agentic Wallet (awal) — no Apify account or API key. You buy one small, spend-capped prepaid Apify token, then run as many Actors as the request needs with it. Use when the user wants to use Apify tools without…
sprr
Single PR reviewer for awesome-quant. Use when the user asks to review, validate, comment on, label, close, or merge one specific pull request that adds README.md entries. Triggers include "sprr", "review PR", "check PR", and "validate contribution".
bprr
Bulk PR reviewer for awesome-quant. Use when the user asks to review all open PRs, review unreviewed PRs, bulk review, or mentions "bprr". Reviews open PRs lacking the reviewed label and presents a summary before any merge/comment/label action.
update-pypi-dates
Refresh tracked PyPI last-updated dates in awesome-quant README.md. Use when the user asks to update PyPI dates, refresh PyPI metadata, or run update-pypi-dates.