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.
git 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/commands/luanpdd/kit-mcp/risk-budget)<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>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 | $0.00055 | $0.02925 |
| Opus 5 | $0.00028 | $0.01463 |
| Sonnet 5 | $0.00011 | $0.00585 |
| Haiku 4.5 | $0.00006 | $0.00293 |
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.
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 | 1× |
| 99.5% | 3.6 h | Notável | Tier free de produção | 2× |
| 99.9% | 43.2 min | Aceitável para UX | Tier paid default | 5× |
| 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"
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.
- 4d ago First seen · 221 lines · 55 tokens per session scan A 57602c042447
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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.