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 luanpdd/kit-mcp --skill burn-rate-alertinggit clone --depth 1 https://github.com/luanpdd/kit-mcpWrote 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/luanpdd/kit-mcp/burn-rate-alerting)<a href="https://agentmods.dev/skills/luanpdd/kit-mcp/burn-rate-alerting"><img src="https://agentmods.dev/badge/skills/luanpdd/kit-mcp/burn-rate-alerting/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/luanpdd/kit-mcp/burn-rate-alerting"><img src="https://agentmods.dev/badge/skills/luanpdd/kit-mcp/burn-rate-alerting.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 | $0.00056 | $0.02733 |
| Opus 5 | $0.00028 | $0.01367 |
| Sonnet 5 | $0.00011 | $0.00547 |
| Haiku 4.5 | $0.00006 | $0.00273 |
Grade A, and why
burn-rate-alerting 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 6d 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Observabilidade — Burn Rate Alerting
Quando usar
LLM carrega esta skill ao configurar alertas SLO ou avaliar burn rate. Trigger phrases:
- "burn rate alert", "burn rate forecast"
- "lookahead window", "baseline window"
- "predictive vs context-aware"
- "quando paginar vs quando criar ticket"
- "extrapolar exhaustão de budget"
Fórmula canônica
burn_rate = error_rate / (1 - SLO_target)
| Burn rate | Significado |
|---|---|
| 1× | Budget durará exatamente a janela do SLO |
| 2× | Budget acabará em metade da janela |
| 10× | Budget acabará em 1/10 da janela |
| 100× | Budget esgotado em horas, não dias |
Predictive forecast (Cap 13 p145):
projected_remaining_at_lookahead = current_remaining - (burn_rate_now × lookahead_window)
ALERT iff projected_remaining_at_lookahead < 0
Regras absolutas
- Lookahead ≤ 4× baseline — extrapolar 4 horas a partir de baseline 1h é confiável; extrapolar 1 dia a partir de 1h é flappy. (Sem ajuste de seasonality)
- Sliding window 30d para o SLO — alinha com customer memory (skill
event-based-slos) - 2 alertas por SLO — short-term (page) + long-term (ticket). Não 1 só, não 5+.
- Short-term: lookahead 4h, baseline 1h — paga on-call em horas
- Long-term: lookahead 3d, baseline 18h — abre ticket, não acorda alguém
- Context-aware vs short-term — escolher por trade-off de custo vs sensibilidade. Default short-term para a maioria; context-aware se "10% restante = mais urgente que 90%".
- Não alertar zero-level — se você só alerta quando budget = 0, não há tempo de reagir. Use predictive sempre.
Patterns canônicos
Pattern: 2 alertas canônicos por SLO
# PT-BR: para SLO 99.9% checkout_success com window 30d
slo: checkout_success
target: 0.999
window: 30d_sliding
alerts:
# PT-BR: PAGE — paginar on-call (urgent)
- name: short_term_burn
type: predictive
lookahead: 4h # PT-BR: forecast 4h à frente
baseline: 1h # PT-BR: 4× regra (4h ≤ 4× 1h ✓)
severity: page
threshold_burn_rate: 14.4 # PT-BR: 4h × 14.4 = ~58h, esgota budget de 30d×0.001 = 43.2min em <4h
routing: pagerduty:on-call
# PT-BR: TICKET — criar ticket Jira/Linear (não-urgent)
- name: long_term_burn
type: predictive
lookahead: 3d
baseline: 18h # PT-BR: 4× regra (3d ≤ 4× 18h = 72h ✓)
severity: ticket
threshold_burn_rate: 1.0 # PT-BR: 1× = vai esgotar em 30d se continuar
routing: jira:engineering
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.
- 6d ago First seen · 260 lines · 56 tokens per session scan A 94840523f96d
burn-rate-alerting is a skill published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 3d ago), licensed MIT. It adds 56 tokens to every session and 2,733 once invoked, about $0.0003 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 2026-09-03.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…