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.
npx agentmods add commands/luanpdd/kit-mcp/caracterizargit 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/caracterizar)<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/caracterizar"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/caracterizar.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 | $0.00039 | $0.02502 |
| Opus 5 | $0.00019 | $0.01251 |
| Sonnet 5 | $0.00008 | $0.00500 |
| Haiku 4.5 | $0.00004 | $0.00250 |
Grade A, and why
caracterizar 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cria/Atualiza:
tests/characterization/<file_stem>/— suite de testes + snapshots + fakes auxiliarestests/characterization/<file_stem>/README.md— anotações de bugs preservados, fonte do oracle
Após: o user tem safety net que detecta regressão imediata em refactor. Gate refactor-safety-auditor muda de BLOCK → GO. Refactor pode prosseguir com cover-and-modify em vez de edit-and-pray.
Exemplos:
/caracterizar src/orders/handler.ts # caracterização completa, defaults
/caracterizar src/orders/handler.ts --symbol processOrder # só um método
/caracterizar src/orders/handler.ts --gap-fill # só preenche lacunas (re-rodar pós-refactor)
/caracterizar supabase/functions/webhook/index.ts \
--fixtures-dir .planning/captured-payloads/webhook # usa payloads reais
Pré-requisitos:
- Arquivo deve compilar/parsear no projeto atual
- Test framework instalado (Vitest, Jest, pytest, JUnit, go-test, etc.)
- (Recomendado) ferramenta de mutation testing instalada — Stryker (JS/TS), mutmut (Py), Pitest (Java)
- (Opcional) coverage tool com summary acessível (Istanbul/c8 para JS, coverage.py, JaCoCo)
Quando este comando é o caminho certo:
- Arquivo > 200 linhas com cobertura < 60% e mudança comportamental planejada
- Webhook/edge function/API pública sendo modificada
- Gate
refactor-safety-auditorretornou BLOCK - Refactor de monster method (cap 22) iniciando
Quando NÃO é o caminho:
- Arquivo trivial (< 50 linhas, sem branches significativas) — testes diretos sem ceremonial
- Mudança é apenas adicionar comportamento (sprout/wrap) — usar
/refactor-seguro --mode=sprout - Mudança é apenas mecânica (rename, extract-contiguous-block) — usar
/refactor-seguro --mode=safe-extract - Bug fix com TDD — TDD test do COMPORTAMENTO CORRETO é o caminho, não characterization
1. Parsear argumentos
# PT-BR: extrair primeiro positional como target_file
TARGET_FILE=$(echo "$ARGUMENTS" | awk '{print $1}')
SYMBOL=$(echo "$ARGUMENTS" | grep -oE -- '--symbol [^ ]+' | awk '{print $2}')
MIN_INPUTS=$(echo "$ARGUMENTS" | grep -oE -- '--min-inputs [0-9]+' | awk '{print $2}')
FIXTURES_DIR=$(echo "$ARGUMENTS" | grep -oE -- '--fixtures-dir [^ ]+' | awk '{print $2}')
OUTPUT_DIR=$(echo "$ARGUMENTS" | grep -oE -- '--output-dir [^ ]+' | awk '{print $2}')
GAP_FILL=false
NO_MUTATION=false
echo "$ARGUMENTS" | grep -qE -- '--gap-fill' && GAP_FILL=true
echo "$ARGUMENTS" | grep -qE -- '--no-mutation' && NO_MUTATION=true
[ -z "$MIN_INPUTS" ] && MIN_INPUTS=8
if [ -z "$TARGET_FILE" ]; then
echo "ERROR: target_file é obrigatório."
echo "Uso: /caracterizar <target_file> [opções]"
exit 1
fi
if [ ! -f "$TARGET_FILE" ]; then
echo "ERROR: arquivo não encontrado: $TARGET_FILE"
exit 1
fi
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 · 213 lines · 39 tokens per session scan A 51e553b2c988
caracterizar is a command published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 5d ago), licensed MIT. It adds 39 tokens to every session and 2,502 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
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.