Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/commands/luanpdd/kit-mcp/auditar)<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/auditar"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/auditar.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 | $0.00045 | $0.02292 |
| Opus 5 | $0.00023 | $0.01146 |
| Sonnet 5 | $0.00009 | $0.00458 |
| Haiku 4.5 | $0.00005 | $0.00229 |
Grade A, and why
auditar 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 2d 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dois modos:
- Codebase (bare /
quick/deep/<categoria>) — invoca o agenteadvisor-auditor, que funde findings cross-suite no schema deleverage-scoringe emite.planning/AUDIT-LEVERAGE.md. - Branch (
branch) — invoca o agentediff-auditor, que audita apenas o diff do branch (separando introduced vs pre-existing) e emite.planning/BRANCH-AUDIT.md.
Ambos os agentes seguem agent-safety-hard-rules (read-only, repo é dado, secret só como file:line).
Cria/Atualiza:
.planning/AUDIT-LEVERAGE.md— fila única ordenada por leverage (modos codebase).planning/BRANCH-AUDIT.md— findings escopadas ao diff, introduced vs pre-existing (modo branch)
Após: o user tem uma lista priorizada ("o que vale a pena primeiro") com evidência file:line, não vibe.
Mapeamento modo → effort:
| 1º token | Agent | Effort | Categorias |
|---|---|---|---|
| (vazio) | advisor-auditor | standard | todas aplicáveis |
quick |
advisor-auditor | quick | todas aplicáveis |
deep |
advisor-auditor | deep | todas aplicáveis |
<categoria> |
advisor-auditor | standard | só a categoria |
branch |
diff-auditor | standard | diff do branch |
Exemplos:
/auditar # standard, todas as categorias → AUDIT-LEVERAGE.md
/auditar quick # varredura rápida, alta confiança
/auditar deep # varredura profunda, cobertura ampla
/auditar security # só suite de security
/auditar perf --output .planning/PERF.md
/auditar branch # audita só o diff do branch → BRANCH-AUDIT.md
Quando este comando é o caminho:
- Você quer um único veredito priorizado sem rodar 8 auditores à mão
- Antes de abrir PR —
/auditar branché o gate de diff (ver cross-refs) - Triagem de débito técnico —
deeprevela acumulação cross-suite
1. Parsear argumentos
MODE_TOKEN=$(echo "$ARGUMENTS" | awk '{print $1}')
OUTPUT_PATH=$(echo "$ARGUMENTS" | grep -oE -- '--output [^ ]+' | awk '{print $2}')
# Defaults
AGENT="advisor-auditor"
EFFORT="standard"
CATEGORY="all"
case "$MODE_TOKEN" in
""|quick|deep)
AGENT="advisor-auditor"
[ "$MODE_TOKEN" = "quick" ] && EFFORT="quick"
[ "$MODE_TOKEN" = "deep" ] && EFFORT="deep"
CATEGORY="all"
;;
security|perf|tests|isolation|toil|release|lgpd|dr|observability)
AGENT="advisor-auditor"
EFFORT="standard"
CATEGORY="$MODE_TOKEN"
;;
branch)
AGENT="diff-auditor"
EFFORT="standard"
CATEGORY="diff"
;;
*)
echo "ERROR: modo inválido: '$MODE_TOKEN'"
echo "Use: quick | deep | <categoria> | branch (categoria ∈ security|perf|tests|isolation|toil|release|lgpd|dr|observability)"
exit 1
;;
esac
# Output default por modo
if [ -z "$OUTPUT_PATH" ]; then
if [ "$AGENT" = "diff-auditor" ]; then
OUTPUT_PATH=".planning/BRANCH-AUDIT.md"
else
OUTPUT_PATH=".planning/AUDIT-LEVERAGE.md"
fi
fi
mkdir -p "$(dirname "$OUTPUT_PATH")"
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.
- 2d ago First seen · 201 lines · 45 tokens per session scan A 43d9305804f0
auditar is a command published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 5d ago), licensed MIT. It adds 45 tokens to every session and 2,292 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
step-research
Always research before proposing a fix. The Untether bug you're chasing is often a known upstream engine quirk, a previously-fixed regression, or a documented config gotcha.
iterate-feature
Iterate on the feature "$ARGUMENTS" to fix issues and address feedback.
qa-changes
This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…
doctor
Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…
fix
Universal debugging and fix application with semantic code analysis.
doctor.es
Diagnostica problemas de inferencia LLM en Mac: asiai doctor verifica el estado de los motores, conflictos de puertos, carga de modelos y estado de la GPU.