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/detectar-duplicacao)<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/detectar-duplicacao"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/detectar-duplicacao/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/detectar-duplicacao"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/detectar-duplicacao.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 | $0.00049 | $0.02179 |
| Opus 5 | $0.00024 | $0.01090 |
| Sonnet 5 | $0.00010 | $0.00436 |
| Haiku 4.5 | $0.00005 | $0.00218 |
Grade A, and why
detectar-duplicacao 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 6d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Invoca o agente shotgun-surgery-detector que aplica a skill legacy-shotgun-surgery. Output: clusters priorizados por (size × frequency × extract feasibility).
Cria/Atualiza:
.planning/SHOTGUN-SURGERY.md— clusters detectados, top 10 priorizados, sugestões extract
Após: o user tem lista acionável de candidates a extract method/class para reduzir change points. PR sequence canônica: extract first → modify second.
Exemplos:
/detectar-duplicacao src/ # both modes, defaults
/detectar-duplicacao . --mode=syntactic # só Feathers original (sem custo IA)
/detectar-duplicacao src/ --threshold 0.90 # mais conservador
/detectar-duplicacao src/ --min-cluster-size 5 # só clusters grandes
/detectar-duplicacao src/ --provider=pgvector # forçar self-hosted
Pré-requisitos:
- jscpd disponível para sintática (
npm install -g jscpdse não) - OPENAI_API_KEY OR pgvector setup para semântica (auto-detect)
- Node.js 20+ no path para chamadas embeddings
Quando este comando é o caminho:
- Você sente "estou mudando isso em N lugares" — use detector pra confirmar/quantificar
- Refactor proposto inclui extract method/class — detector confirma 3+ ocorrências
- Code review onde reviewer suspeita de DRY violations
- Pré-requisito para
/legacy refactorquando shotgun é a real causa raiz
1. Parsear argumentos
ROOT_DIR=$(echo "$ARGUMENTS" | awk '{print $1}')
THRESHOLD=$(echo "$ARGUMENTS" | grep -oE -- '--threshold [0-9.]+' | awk '{print $2}')
MIN_CLUSTER=$(echo "$ARGUMENTS" | grep -oE -- '--min-cluster-size [0-9]+' | awk '{print $2}')
MIN_BLOCK=$(echo "$ARGUMENTS" | grep -oE -- '--min-block-lines [0-9]+' | awk '{print $2}')
MODE=$(echo "$ARGUMENTS" | grep -oE -- '--mode[= ][^ ]+' | sed 's/--mode[= ]//')
PROVIDER=$(echo "$ARGUMENTS" | grep -oE -- '--provider[= ][^ ]+' | sed 's/--provider[= ]//')
OUTPUT_PATH=$(echo "$ARGUMENTS" | grep -oE -- '--output [^ ]+' | awk '{print $2}')
[ -z "$ROOT_DIR" ] && ROOT_DIR="."
[ -z "$THRESHOLD" ] && THRESHOLD="0.85"
[ -z "$MIN_CLUSTER" ] && MIN_CLUSTER=3
[ -z "$MIN_BLOCK" ] && MIN_BLOCK=10
[ -z "$MODE" ] && MODE="both"
[ -z "$PROVIDER" ] && PROVIDER="auto"
[ -z "$OUTPUT_PATH" ] && OUTPUT_PATH=".planning/SHOTGUN-SURGERY.md"
if [ ! -d "$ROOT_DIR" ]; then
echo "ERROR: root_dir não encontrado: $ROOT_DIR"
exit 1
fi
mkdir -p "$(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.
- 6d ago First seen · 198 lines · 49 tokens per session scan A 069c00548ff9
detectar-duplicacao is a command published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 2,179 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.