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.
git clone --depth 1 https://github.com/luanpdd/kit-mcpnpx agentmods add commands/luanpdd/kit-mcp/prospectar-direcaoWrote 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/prospectar-direcao)<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.
<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>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 | $0.00046 | $0.01814 |
| Opus 5 | $0.00023 | $0.00907 |
| Sonnet 5 | $0.00009 | $0.00363 |
| Haiku 4.5 | $0.00005 | $0.00181 |
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.
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-marcofoi 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")"
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.
- 5d ago First seen · 172 lines · 46 tokens per session scan A 4fa0cd432bb8
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.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.