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 randommonicle/claude-skills --skill price-the-spendgit clone --depth 1 https://github.com/randommonicle/claude-skillsWrote 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/randommonicle/claude-skills/price-the-spend)<a href="https://agentmods.dev/skills/randommonicle/claude-skills/price-the-spend"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/price-the-spend/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/randommonicle/claude-skills/price-the-spend"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/price-the-spend.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 | $0.00132 | $0.02575 |
| Opus 5 | $0.00066 | $0.01288 |
| Sonnet 5 | $0.00026 | $0.00515 |
| Haiku 4.5 | $0.00013 | $0.00258 |
Grade A, and why
price-the-spend 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 12d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Price the spend
A smoke-ui nightly on a private repo ran 25m10s a day. GitHub rounds up per job, so it billed
26 minutes, about 780 minutes a month, roughly 40% of a 2,000-minute allowance, spent before a
single commit was pushed. It exhausted the spending limit and the merge queue died mid-session.
The job was continue-on-error: true and schedule-only, so it could not fail a PR or its own
workflow. Its own header called it "never a trusted gate". Nobody had ever priced it. For scale,
the entire remaining four-PR merge queue was costed at about 226 billed minutes, one third of
what the nightly burned doing nothing.
The two halves, and the one everybody forgets
Per-action spend is the half people think about: a subagent batch, a workflow run, an LLM API call, a one-off cloud job. It is visible, attributable, and it ends.
Recurring spend is the half that actually eats budgets: anything on a schedule or a subscription. It is invisible precisely because it is working. Nobody reviews a job that has not failed. If you only ever price actions, you will be surprised by a bill you authorised months ago and never saw again.
Both halves feed the same question: what does this thing cost per month, and against what allowance.
Rule 1: price recurring spend before it ships
For anything on a schedule, a timer, a poll, or a subscription, state the arithmetic out loud before it merges:
billed units per run x runs per month = monthly cost
then as a % of the allowance
- Bill the unit the vendor bills, not the unit you observe. A 25m10s run is 26 billed minutes. Read the rounding rule before doing the multiplication.
- State it as a percentage of the allowance, not just an absolute. "780 minutes" sounds small; "40% of the monthly allowance" is a decision.
- The allowance is shared. Standing spend crowds out the interactive spend you actually need. The nightly did not just cost money, it stopped merges.
- Re-price when runtime or volume grows. A job priced at 8 minutes that drifts to 25 is a new decision that nobody made. Re-price on any runtime, matrix, dataset, or frequency change.
- A free tier is a bill with a threshold. Know the threshold, know where you sit, and know what the first paid unit costs. One project needed a second sender domain and the free tier allowed one, which silently converted into a paid plan.
- Frequency is the cheapest lever. Nightly to weekly is a 7x cut with no loss of coverage for a safety net. Take that before cutting the check itself.
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.
- 12d ago First seen · 185 lines · 132 tokens per session scan A ab15486c4212
price-the-spend is a skill published in the GitHub repository randommonicle/claude-skills (23 stars, last pushed 6d ago), licensed Apache-2.0. It adds 132 tokens to every session and 2,575 once invoked, about $0.0007 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…