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/implementgit 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/implement)<a href="https://agentmods.dev/commands/thebeardedbearsas/claude-craft/implement"><img src="https://agentmods.dev/badge/commands/thebeardedbearsas/claude-craft/implement.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 | $0.00022 | $0.02489 |
| Opus 5 | $0.00011 | $0.01244 |
| Sonnet 5 | $0.00004 | $0.00498 |
| Haiku 4.5 | $0.00002 | $0.00249 |
Grade A, and why
workflow-implement 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 today.
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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/workflow:implement
Mission
Exécuter la phase d'Implémentation du workflow de développement. Cette phase se concentre sur le développement sprint par sprint en utilisant les pratiques TDD/BDD, en suivant la conception technique établie dans les phases précédentes.
Quand utiliser
- Après la complétion de
/workflow:design(tracks Standard/Enterprise) - Après
/workflow:initpour le track Quick Flow - Quand on est prêt à coder
Prérequis
Pour les tracks Standard/Enterprise :
- La Spécification Technique existe dans
project-management/tech-spec.md - Le backlog existe dans
project-management/backlog/ - La structure de sprint est définie dans
project-management/sprints/
Pour le Quick Flow :
- Compréhension claire du bug/fonctionnalité à implémenter
Mode Plan
Le mode plan est obligatoire. Avant l'exécution, Claude active le mode plan pour analyser le code impacté, proposer un plan d'implémentation et attendre votre validation avant toute modification.
Workflow
Étape 1 : Mise en place de l'implémentation
╔══════════════════════════════════════════════════════════╗
║ PHASE D'IMPLÉMENTATION - DÉMARRAGE ║
╠══════════════════════════════════════════════════════════╣
║ Track: Standard ║
║ Phase: 4 sur 4 - Implémentation ║
║ ║
║ Objectifs : ║
║ • Exécuter le développement sprint avec TDD/BDD ║
║ • Implémenter les user stories selon la spécification ║
║ • Maintenir la qualité du code et la couverture de tests ║
║ • Valider la Definition of Done pour chaque story ║
╚══════════════════════════════════════════════════════════╝
Étape 2 : Sélection du sprint
╔══════════════════════════════════════════════════════════╗
║ APERÇU DES SPRINTS ║
╠══════════════════════════════════════════════════════════╣
║ ║
║ Sprints disponibles : ║
║ ║
║ ┌─────────────────────────────────────────────────────┐ ║
║ │ Sprint 1 : Walking Skeleton │ ║
║ │ Statut : Prêt à démarrer │ ║
║ │ Stories : 5 | Points : 21 │ ║
║ │ Focus : Infrastructure + première fonctionnalité │ ║
║ │ bout en bout │ ║
║ └─────────────────────────────────────────────────────┘ ║
║ ║
║ ┌─────────────────────────────────────────────────────┐ ║
║ │ Sprint 2 : Fonctionnalités principales │ ║
║ │ Statut : Planifié │ ║
║ │ Stories : 6 | Points : 28 │ ║
║ │ Focus : Gestion utilisateurs, authentification │ ║
║ └─────────────────────────────────────────────────────┘ ║
║ ║
║ ┌─────────────────────────────────────────────────────┐ ║
║ │ Sprint 3 : Intégration paiement │ ║
║ │ Statut : Planifié │ ║
║ │ Stories : 4 | Points : 24 │ ║
║ │ Focus : Intégration Stripe, parcours de paiement │ ║
║ └─────────────────────────────────────────────────────┘ ║
║ ║
║ Sélectionner le sprint à travailler (défaut : Sprint 1) ║
╚══════════════════════════════════════════════════════════╝
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.
- today First seen · 248 lines · 22 tokens per session scan A d703cea1e439
workflow-implement is a command published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 2,489 once invoked, about $0.0001 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
paul:add-phase
Add a new phase to current milestone.
plan
Decompose specs into small, verifiable tasks with dependency ordering.
manage-changes
Analyze and integrate PRD changes mid-development.
jira-discover-project
Discover JIRA project context for intelligent defaults and usage patterns.
set
Create or update a long-horizon goal for this project.
setup
接入 Workflow（workflow.games）：注册引导、配置 API token、验证连接.