prospectar-direcao

prospectar-direcao is a command for Claude Code from luanpdd/kit-mcp. It costs 46 tokens per session (1,814 once invoked), scanned A, original, MIT.

A command that examines a project and proposes four to six ranked directions for future work, with evidence, expected impact, effort, and confidence.

In plain words
What is it for?
Use it to choose the next milestone or add a lower-priority idea to the backlog, including in a monorepo, which is one repository containing multiple projects.
Why use it?
It helps when the current milestone is finished or no clear objective exists, so planning starts from evidence instead of guesswork.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; positional $N argument.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is /prospectar-direcao ./apps/web # sub-projeto monorepo.

Good fit Use it to choose the next milestone or add a lower-priority idea to the backlog, including in a monorepo, which is one repository containing multiple projects.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/luanpdd/kit-mcp
agentmods
npx agentmods add commands/luanpdd/kit-mcp/prospectar-direcao

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 prospectar-direcao

README.md
[![agentmods](https://agentmods.dev/badge/commands/luanpdd/kit-mcp/prospectar-direcao/github.svg)](https://agentmods.dev/commands/luanpdd/kit-mcp/prospectar-direcao)
Your own site
<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/prospectar-direcao"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/prospectar-direcao/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.

agentmods 80×15 button for prospectar-direcao

Your own site · 80×15
<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/prospectar-direcao"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/prospectar-direcao.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,814 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 $0.00046 $0.01814
Opus 5 $0.00023 $0.00907
Sonnet 5 $0.00009 $0.00363
Haiku 4.5 $0.00005 $0.00181

Measured 5d ago against content hash 4fa0cd432bb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

prospectar-direcao 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 5d 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/prospectar-direcao.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Invoca o agente direction-prospector que aplica a skill leverage-scoring — cada sugestão carrega evidence (file:line ou commit), impact, effort, confidence e o leverage derivado, ordenadas pela fórmula Leverage = (Impact / Effort) × Confidence.

Cria/Atualiza:

  • DIRECTION.md (default .planning/DIRECTION.md) — 4-6 sugestões priorizadas com evidência

Após: o user tem uma carteira acionável. Cada sugestão pode ser:

  • promovida a backlog via /adicionar-backlog "<sugestão>" (estaciona em 999.x sem comprometer)
  • adotada como objetivo do milestone via /novo-marco "<sugestão>" (vira o foco ativo)

Exemplos:

/prospectar-direcao                                  # raiz atual, output default
/prospectar-direcao .                                # explícito
/prospectar-direcao ./apps/web                       # sub-projeto monorepo
/prospectar-direcao . --output .planning/NEXT.md     # output custom

Quando este comando é o caminho:

  • O milestone atual fechou e o próximo objetivo está "A definir" — você não sabe o que atacar
  • /novo-marco foi disparado sem nome e você quer candidatos com evidência antes de comprometer
  • Acúmulo de TODOs/débito/gaps e você quer uma leitura priorizada do que rende mais
  • Antes de uma sessão de planejamento de roadmap, para ancorar a discussão em sinais reais

Pré-requisitos:

  • .planning/ existe (STATE.md, ROADMAP.md ajudam o sinal; o agente degrada se ausentes)
  • Repositório git inicializado (git log é uma das fontes de sinal)

1. Parsear argumentos

PROJECT_ROOT=$(echo "$ARGUMENTS" | awk '{print $1}')
OUTPUT_PATH=$(echo "$ARGUMENTS" | grep -oE -- '--output [^ ]+' | awk '{print $2}')

# se o primeiro token for uma flag, não é project_root
case "$PROJECT_ROOT" in
  --*) PROJECT_ROOT="" ;;
esac

[ -z "$PROJECT_ROOT" ] && PROJECT_ROOT="."
[ -z "$OUTPUT_PATH" ]  && OUTPUT_PATH=".planning/DIRECTION.md"

if [ ! -d "$PROJECT_ROOT" ]; then
  echo "ERROR: project_root não encontrado: $PROJECT_ROOT"
  exit 1
fi

mkdir -p "$(dirname "$OUTPUT_PATH")"

Read the full file on GitHub · 172 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. 5d ago First seen · 172 lines · 46 tokens per session scan A 4fa0cd432bb8

Subscribe to this mod's changes

prospectar-direcao is a command published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 1,814 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.