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/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/architecture-decision)<a href="https://agentmods.dev/commands/thebeardedbearsas/claude-craft/architecture-decision"><img src="https://agentmods.dev/badge/commands/thebeardedbearsas/claude-craft/architecture-decision/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/thebeardedbearsas/claude-craft/architecture-decision"><img src="https://agentmods.dev/badge/commands/thebeardedbearsas/claude-craft/architecture-decision.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 | $0.00006 | $0.02411 |
| Opus 5 | $0.00003 | $0.01205 |
| Sonnet 5 | $0.00001 | $0.00482 |
| Haiku 4.5 | $0.00001 | $0.00241 |
Grade A, and why
architecture-decision 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 9d 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 — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Decision Record (ADR)
Tu es un architecte logiciel senior. Tu dois créer un Architecture Decision Record (ADR) pour documenter une décision technique importante.
Arguments
$ARGUMENTS
Arguments :
- Titre de la décision
- (Optionnel) Numéro ADR
Exemple : /common:architecture-decision "Choix de PostgreSQL pour la base de données principale"
MISSION
Étape 1 : Collecter les Informations
Poser les questions clés :
- Quel problème essayons-nous de résoudre ?
- Quelles sont les contraintes ?
- Quelles options avons-nous considérées ?
- Pourquoi cette option plutôt qu'une autre ?
Étape 2 : Créer le Fichier ADR
Emplacement : docs/architecture/decisions/ ou docs/adr/
Nommage : NNNN-titre-en-kebab-case.md
Étape 3 : Rédiger l'ADR
Template ADR (format Michael Nygard) :
# ADR-{NNNN}: {Titre}
**Date**: {YYYY-MM-DD}
**Statut**: {Proposé | Accepté | Déprécié | Remplacé par ADR-XXXX}
**Décideurs**: {Noms des personnes impliquées}
## Contexte
{Décrire les forces en jeu, incluant les forces technologiques, politiques,
sociales et liées au projet. Ces forces sont probablement en tension, et
doivent être appelées comme telles. Le langage dans cette section est
neutre sur la valeur - on décrit simplement les faits.}
### Situation actuelle
{Description de l'état actuel du système/projet}
### Problème
{Description claire du problème à résoudre}
### Contraintes
- {Contrainte 1}
- {Contrainte 2}
- {Contrainte 3}
## Options Considérées
### Option 1: {Nom}
{Description de l'option}
**Avantages**:
- {Avantage 1}
- {Avantage 2}
**Inconvénients**:
- {Inconvénient 1}
- {Inconvénient 2}
**Effort estimé**: {Faible | Moyen | Élevé}
### Option 2: {Nom}
{Description de l'option}
**Avantages**:
- {Avantage 1}
- {Avantage 2}
**Inconvénients**:
- {Inconvénient 1}
- {Inconvénient 2}
**Effort estimé**: {Faible | Moyen | Élevé}
### Option 3: {Nom}
{Description de l'option}
**Avantages**:
- {Avantage 1}
- {Avantage 2}
**Inconvénients**:
- {Inconvénient 1}
- {Inconvénient 2}
**Effort estimé**: {Faible | Moyen | Élevé}
## Décision
{Nous avons décidé d'utiliser **Option X** parce que...}
### Justification
{Explication détaillée de pourquoi cette option a été choisie par rapport
aux autres. Inclure les compromis acceptés.}
## Conséquences
### Positives
- {Conséquence positive 1}
- {Conséquence positive 2}
### Négatives
- {Conséquence négative 1}
- {Conséquence négative 2}
### Risques
| Risque | Probabilité | Impact | Mitigation |
|--------|-------------|--------|------------|
| {Risque 1} | Faible/Moyenne/Haute | Faible/Moyen/Haut | {Action} |
| {Risque 2} | Faible/Moyenne/Haute | Faible/Moyen/Haut | {Action} |
## Plan d'Implémentation
### Phase 1: {Titre}
- [ ] {Tâche 1}
- [ ] {Tâche 2}
### Phase 2: {Titre}
- [ ] {Tâche 3}
- [ ] {Tâche 4}
## Métriques de Succès
- {Métrique 1}: {Valeur cible}
- {Métrique 2}: {Valeur cible}
## Références
- {Lien vers documentation}
- {Lien vers étude comparative}
- {ADR liés}
---
## Historique
| Date | Action | Par |
|------|--------|-----|
| {YYYY-MM-DD} | Créé | {Nom} |
| {YYYY-MM-DD} | Accepté | {Équipe} |
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.
- 9d ago First seen · 367 lines · 6 tokens per session scan A de0ebeac4907
architecture-decision is a command published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed 6d ago), licensed MIT. It adds 6 tokens to every session and 2,411 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 2026-08-30.
Other commands, from other repositories
assemble-team
Assemble a pre-built agent team for parallel work - review, feature, debug, cross-platform, full-stack, or research.
standardize-claude-md
Add missing toolkit sections (Related Global Rules, Quick Start) to existing CLAUDE.md.
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.