risk-budget

risk-budget is a command for Claude Code from luanpdd/kit-mcp. It costs 55 tokens per session (2,925 once invoked), scanned A, original, MIT.

A read-only reliability report that compares service error budgets with SLO targets. An error budget is the amount of failure a service can tolerate while meeting its reliability goal.

In plain words
What is it for?
Use it to inspect SLO status, compare targets from 99% to 99.999%, and view the result as a table or JSON.
Why use it?
It helps teams judge whether a reliability target is appropriate for users and whether its operational cost is justified.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

Good fit Use it to inspect SLO status, compare targets from 99% to 99.999%, and view the result as a table or JSON.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/luanpdd/kit-mcp/risk-budget
Install

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.

Clone the repo
git clone --depth 1 https://github.com/luanpdd/kit-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for risk-budget

README.md
[![agentmods](https://agentmods.dev/badge/commands/luanpdd/kit-mcp/risk-budget.svg)](https://agentmods.dev/commands/luanpdd/kit-mcp/risk-budget)
Your own site
<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/risk-budget"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/risk-budget.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,925 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.02925
Opus 5 $0.00028 $0.01463
Sonnet 5 $0.00011 $0.00585
Haiku 4.5 $0.00006 $0.00293

Measured 4d ago against content hash 57602c042447, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

risk-budget 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 4d 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.

kit/commands/risk-budget.md · 221 lines

How it starts

The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lê SLOs definidos em event-based-slos (v1.9) — .planning/slos/*.md. Complementa burn-rate-status (v1.9 — burn rate forecast) com decisão estratégica sobre target apropriado.

Cria/Atualiza: nada — comando read-only.

Após: o user vê posição de cada SLO no continuum, % budget gasto, custo relativo (1× → 100×+), e recomendação de tier (free/paid/enterprise) consistente com user-perception.

Flags:

  • --format <table|json> — output format (default: table)
  • --explain — incluir bloco "sabedoria 99.99%" + anti-patterns inline (verbose)

Pré-requisito: SLOs definidos em .planning/slos/*.md (v1.9 — comando /observabilidade slo ou /definir-slo).

Risk continuum canônico (cap 3, aplicado inline pela skill):

Target Tolerância 30d User-perceptible? Recomendação Custo relativo
99% 7.2 h Sim Tier free, beta, internal
99.5% 3.6 h Notável Tier free de produção
99.9% 43.2 min Aceitável para UX Tier paid default
99.95% 21.6 min Quase imperceptível Tier enterprise / mission-critical 10×
99.99% 4.3 min Imperceptível em smartphone Apenas se justificado (raro) 50×+
99.999% 26 s NÃO perceptível NUNCA para user-facing 100×+

Loop pattern: rodar via skill loop para monitoramento contínuo.

/loop 1h /risk-budget

Exemplos:

/risk-budget                              # todos SLOs, formato table
/risk-budget checkout_success             # 1 SLO específico
/risk-budget --format json                # output estruturado
/risk-budget login_success --explain      # com sabedoria 99.99% + anti-patterns inline

1. Parsear argumentos

SLO_NAME=$(echo "$ARGUMENTS" | awk '{print $1}' | grep -v '^--' || true)
FORMAT=$(echo "$ARGUMENTS" | grep -oE -- '--format [^ ]+' | awk '{print $2}')
EXPLAIN=$(echo "$ARGUMENTS" | grep -c -- '--explain' || echo 0)

[ -z "$FORMAT" ] && FORMAT="table"

Read the full file on GitHub · 221 lines

Changes

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.

  1. 4d ago First seen · 221 lines · 55 tokens per session scan A 57602c042447

Subscribe to this mod's changes

risk-budget is a command published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 2,925 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.