Borrowing it
Nothing to install: this file belongs to lglucas/ai-dev-operating-system. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/lglucas/ai-dev-operating-system/main/.claude/skills/cost-watchdog/SKILL.mdgit clone --depth 1 https://github.com/lglucas/ai-dev-operating-systemWrote 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/lglucas/ai-dev-operating-system/cost-watchdog)<a href="https://agentmods.dev/skills/lglucas/ai-dev-operating-system/cost-watchdog"><img src="https://agentmods.dev/badge/skills/lglucas/ai-dev-operating-system/cost-watchdog/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/lglucas/ai-dev-operating-system/cost-watchdog"><img src="https://agentmods.dev/badge/skills/lglucas/ai-dev-operating-system/cost-watchdog.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 | $0.00104 | $0.00755 |
| Opus 5 | $0.00052 | $0.00378 |
| Sonnet 5 | $0.00021 | $0.00151 |
| Haiku 4.5 | $0.00010 | $0.00076 |
Grade A, and why
cost-watchdog 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 10d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cost Watchdog
When to run this skill
- Before introducing any third-party service (LLM provider, DB, queue, monitoring, search, image, email).
- Before suggesting a paid tier of any service the user is currently on free tier of.
- When proposing model selection (Claude Opus vs Sonnet vs Haiku, GPT-4 vs 4o-mini, etc.).
- When implementing patterns that scale poorly: N+1 queries, polling loops, full-text scans, unbounded retries.
- When the user says "está caro" / "está cobrando demais" / "fiquei sem créditos".
Cost flags to watch
LLM costs
- Default to Claude Haiku 4.5 or Sonnet 4.6 for routine work. Use Opus only for tasks that justify it (deep reasoning, business strategy, architecture).
- Always cache prompts that have a stable system prefix (saves up to 90% of input tokens).
- Loops are dangerous. If a feature calls the LLM in a loop, calculate worst case before shipping.
- Streaming + early termination when user might stop reading.
Hosting
- Vercel Hobby (free) is fine until ~100 users. Pro ($20/mo) only when you hit limits.
- Supabase Free tier: 500 MB DB, 1 GB storage, 50K monthly active users. Plenty for prototypes.
- Don't enable database point-in-time recovery before paying users exist.
Database patterns
- Unbounded SELECT without pagination → flag.
- Realtime subscriptions on noisy tables → flag.
- Full-table scans in serverless functions → flag (cold-start tax + bandwidth).
Third-party services
- Stripe: percentage-based, no flag below revenue.
- Resend: 3K emails/month free. Flag transactional volume design.
- PostHog free tier: 1M events/mo. Flag if event firing in loops.
- Sentry free: 5K errors/mo. Flag noisy retry catch blocks.
Vibe coder explanation
Cloud services are like a cab meter. Some run flat-rate (you pay even idle), some run per-trip (per request), some are free up to a limit then suddenly expensive. Before you ship, I'll show you which meter is running and what the worst-case bill looks like if your idea goes viral.
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.
- 10d ago First seen · 64 lines · 104 tokens per session scan A 3bd82e33c7f8
cost-watchdog is a skill published in the GitHub repository lglucas/ai-dev-operating-system (11 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 755 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 skills, from other repositories
daily-market-review
A daily review workflow for China’s A-share stock market. It combines index prices, limit-up data, sector money flows, and market sentiment—investor optimism or fear—to assess the day and possible future directions.
portfolio-diagnosis
A diagnosis process for Chinese stock portfolios that combines the holdings, current market prices, industry information, recent events, money flows, and market sentiment. It can use a screenshot, text list, or spoken description of the holdings.
capital-injection-bank-insurance
A research and monitoring guide for capital injections, share offerings, and other capital-raising events at Chinese banks and insurance companies. It explains why these events happen, who funds them, and how they affect regulatory capital.
next-round-baotuan
A framework for studying periods when investors concentrate around the same stocks or market theme, and for watching for signs that this concentration may break down. It combines market conditions, industry trends, policy, valuation, and warning indicators.
serenity-stock-choke
A stock-screening workflow for China’s A-share market, based on supply-chain bottlenecks. A bottleneck is a part, material, or process that can stop a larger industry if its supply is interrupted.
german-elster-tax-filing
Use this skill to run a complete intake for a german personal income tax return in elster for tax years 2024 onward, estimate the tax result, and map the final values into the correct official forms and fields.