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/thebeardedbearsas/claude-craft/generate-commandgit clone --depth 1 https://github.com/TheBeardedBearSAS/claude-craftWrote 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/thebeardedbearsas/claude-craft/generate-command)<a href="https://agentmods.dev/commands/thebeardedbearsas/claude-craft/generate-command"><img src="https://agentmods.dev/badge/commands/thebeardedbearsas/claude-craft/generate-command.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 | $0.00006 | $0.02132 |
| Opus 5 | $0.00003 | $0.01066 |
| Sonnet 5 | $0.00001 | $0.00426 |
| Haiku 4.5 | $0.00001 | $0.00213 |
Grade A, and why
generate-command 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 yesterday.
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 — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Génération Commande Symfony
Tu es un développeur Symfony senior. Tu dois générer une commande console Symfony complète avec les bonnes pratiques.
Arguments
$ARGUMENTS
Arguments :
- Nom de la commande (ex:
app:users:import,app:cache:warmup) - (Optionnel) Description courte
Exemple : /symfony:generate-command app:users:import "Import users from CSV file"
MISSION
Étape 1 : Créer la Commande
Structure du fichier
src/
└── Command/
└── {CommandName}Command.php
Template de Commande
<?php
declare(strict_types=1);
namespace App\Command;
use Symfony\Component\Console\Attribute\AsCommand;
use Symfony\Component\Console\Command\Command;
use Symfony\Component\Console\Input\InputArgument;
use Symfony\Component\Console\Input\InputInterface;
use Symfony\Component\Console\Input\InputOption;
use Symfony\Component\Console\Output\OutputInterface;
use Symfony\Component\Console\Style\SymfonyStyle;
use Symfony\Component\Console\Helper\ProgressBar;
#[AsCommand(
name: '{command:name}',
description: '{Description de la commande}',
)]
class {CommandName}Command extends Command
{
public function __construct(
// Injecter les dépendances nécessaires
private readonly SomeService $service,
) {
parent::__construct();
}
protected function configure(): void
{
$this
->addArgument(
'arg1',
InputArgument::REQUIRED,
'Description de l\'argument'
)
->addArgument(
'arg2',
InputArgument::OPTIONAL,
'Argument optionnel',
'valeur_defaut'
)
->addOption(
'option1',
'o',
InputOption::VALUE_REQUIRED,
'Description de l\'option'
)
->addOption(
'dry-run',
null,
InputOption::VALUE_NONE,
'Exécuter sans modifier les données'
)
->addOption(
'force',
'f',
InputOption::VALUE_NONE,
'Forcer l\'exécution sans confirmation'
)
->setHelp(<<<'HELP'
La commande <info>%command.name%</info> permet de {description détaillée}.
Exemples d'utilisation :
<info>php %command.full_name% fichier.csv</info>
Import le fichier CSV
<info>php %command.full_name% fichier.csv --dry-run</info>
Simule l'import sans modifier les données
<info>php %command.full_name% fichier.csv -o valeur --force</info>
Import forcé avec option
HELP
);
}
protected function execute(InputInterface $input, OutputInterface $output): int
{
$io = new SymfonyStyle($input, $output);
// Récupérer les arguments et options
$arg1 = $input->getArgument('arg1');
$isDryRun = $input->getOption('dry-run');
$force = $input->getOption('force');
// Afficher le header
$io->title('{Command Name}');
// Demander confirmation si pas --force
if (!$force && !$io->confirm('Voulez-vous continuer ?', false)) {
$io->warning('Opération annulée.');
return Command::SUCCESS;
}
if ($isDryRun) {
$io->note('Mode dry-run activé - aucune modification ne sera effectuée.');
}
try {
// Logique principale
$items = $this->getItemsToProcess($arg1);
// Progress bar
$progressBar = new ProgressBar($output, count($items));
$progressBar->setFormat('debug');
$progressBar->start();
$processed = 0;
$errors = [];
foreach ($items as $item) {
try {
if (!$isDryRun) {
$this->service->process($item);
}
$processed++;
} catch (\Exception $e) {
$errors[] = ['item' => $item, 'error' => $e->getMessage()];
}
$progressBar->advance();
}
$progressBar->finish();
$io->newLine(2);
// Résumé
$io->success(sprintf('%d éléments traités avec succès.', $processed));
if (!empty($errors)) {
$io->warning(sprintf('%d erreurs rencontrées.', count($errors)));
$io->table(
['Item', 'Erreur'],
array_map(fn($e) => [$e['item'], $e['error']], $errors)
);
}
return Command::SUCCESS;
} catch (\Exception $e) {
$io->error($e->getMessage());
return Command::FAILURE;
}
}
private function getItemsToProcess(string $source): array
{
// Implémentation selon le besoin
return [];
}
}
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.
- yesterday First seen · 351 lines · 6 tokens per session scan A c9e77894d355
generate-command is a command published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed 2d ago), licensed MIT. It adds 6 tokens to every session and 2,132 once invoked, about $0.0000 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
context-stats
Display context window usage and token statistics.
run
Execute prompt(s) from ./prompts/ with automatic archiving - for structured prompt-based work.
help
Explain Ralph Wiggum technique and available commands.
cancel-ralph
Cancel active Ralph Wiggum loop.
backup-config
Backup Claude Code configuration files.
session-log
View and analyze the Claude Code session log.