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/caracterizar-prompt)<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/caracterizar-prompt"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/caracterizar-prompt/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/caracterizar-prompt"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/caracterizar-prompt.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 | $0.02131 |
| Opus 5 | $0.00023 | $0.01066 |
| Sonnet 5 | $0.00009 | $0.00426 |
| Haiku 4.5 | $0.00005 | $0.00213 |
Grade A, and why
caracterizar-prompt 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cria/Atualiza:
tests/characterization/prompts/<prompt-stem>.test.ts(ou.py/.goconforme runtime)tests/characterization/prompts/__snapshots__/<prompt-stem>.test.ts.snaptests/characterization/prompts/<prompt-stem>/inputs/<intent>.json— inputs canônicos por intent
Após: mudança em prompt deve manter snapshot diff = 0 (ou mudança documentada). Detecta drift de model upstream automaticamente.
Exemplos:
/caracterizar-prompt prompts/generate-summary.md
/caracterizar-prompt prompts/code-reviewer.md --num-intents 7 --max-tokens 1000
/caracterizar-prompt prompts/intent-classifier.md --inputs-dir test-data/classifier-intents
/caracterizar-prompt prompts/customer-support.md --provider anthropic --seed 123
Pré-requisitos:
- ANTHROPIC_API_KEY ou OPENAI_API_KEY em env
- Test framework (Vitest, Jest, pytest, ...)
- Provider escolhido suporta
temperature=0+seed
Quando este comando é o caminho:
- Prompt em produção > 50 linhas
- Mudanças em prompt quebraram silenciosamente no passado
- Equipe quer baseline antes de refactor de prompt
- CI deve detectar drift de model upstream (Claude 4.7 → 4.8)
1. Parsear argumentos
PROMPT_FILE=$(echo "$ARGUMENTS" | awk '{print $1}')
INPUTS_DIR=$(echo "$ARGUMENTS" | grep -oE -- '--inputs-dir [^ ]+' | awk '{print $2}')
PROVIDER=$(echo "$ARGUMENTS" | grep -oE -- '--provider [^ ]+' | awk '{print $2}')
SEED=$(echo "$ARGUMENTS" | grep -oE -- '--seed [0-9]+' | awk '{print $2}')
MAX_TOKENS=$(echo "$ARGUMENTS" | grep -oE -- '--max-tokens [0-9]+' | awk '{print $2}')
NUM_INTENTS=$(echo "$ARGUMENTS" | grep -oE -- '--num-intents [0-9]+' | awk '{print $2}')
[ -z "$SEED" ] && SEED=42
[ -z "$MAX_TOKENS" ] && MAX_TOKENS=500
[ -z "$NUM_INTENTS" ] && NUM_INTENTS=5
if [ -z "$PROMPT_FILE" ]; then
echo "ERROR: prompt_file obrigatório"
exit 1
fi
if [ ! -f "$PROMPT_FILE" ]; then
echo "ERROR: arquivo não encontrado: $PROMPT_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.
- 5d ago First seen · 196 lines · 46 tokens per session scan A 996b923d6c80
caracterizar-prompt is a command published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 46 tokens to every session and 2,131 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
test-prompt
Test an AI prompt against multiple scenarios to verify consistent, quality output.
prompt-eval-debug
Debug any prompt with a tiny eval suite (control, edge, boundary), failure diagnosis, and smallest next change, no blind rewrite.
prompt-tuner
Improve embedded LLM system prompt based on evaluation test failures.
run-prompt-unit-test
A command that runs unit tests for a prompt, meaning instructions given to an AI, using Vitest, a JavaScript testing tool, and creates a structured test report.
test-prompt
Test an AI prompt against multiple scenarios to verify consistent, quality output.
prompt
System instructions for writing effective prompts. Apply when generating commands, skills, agents, or any LLM instructions.