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/ralph-run)<a href="https://agentmods.dev/commands/thebeardedbearsas/claude-craft/ralph-run"><img src="https://agentmods.dev/badge/commands/thebeardedbearsas/claude-craft/ralph-run/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/ralph-run"><img src="https://agentmods.dev/badge/commands/thebeardedbearsas/claude-craft/ralph-run.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 | $0.00024 | $0.02312 |
| Opus 5 | $0.00012 | $0.01156 |
| Sonnet 5 | $0.00005 | $0.00462 |
| Haiku 4.5 | $0.00002 | $0.00231 |
Grade A, and why
ralph-run 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ralph Run - Boucle Continue d'Agent IA v2.0
Execute Claude en boucle continue jusqu'a ce que la tache soit terminee ou que les criteres Definition of Done (DoD) soient satisfaits.
Arguments
$ARGUMENTS
<description-tache>: La tache a accomplir par Claude--auto-detect: Detection automatique du type de projet et configuration DoD--init: Generer la configuration sans executer--interactive: Assistant de configuration interactif
Nouvelles fonctionnalites v2.0
| Fonctionnalite | Description |
|---|---|
| Integration Hooks | Integration bidirectionnelle avec Claude Code 2.1.23+ |
| Auto-Detection | Detection automatique du type de projet (Symfony, Flutter, React, etc.) |
| Dashboard | Affichage temps reel avec barre de progression |
| Export Metriques | Metriques au format JSON et Prometheus |
| Circuit Breaker Adaptatif | 5 profils avec apprentissage historique |
| Moniteur de Sante | Detection blocage, spirale d'erreurs, gonflement contexte |
| Templates DoD | Templates preconfigures pour 8 technologies |
Processus
1. Initialisation de session
-
Verifier prerequis:
- Verifier disponibilite de Claude
- Chercher configuration
ralph.yml - Initialiser repertoire session (
.ralph/)
-
Detection automatique (si
--auto-detect):- Detecter type de projet (Symfony, Flutter, React, Python, .NET, Go, Rust)
- Charger template DoD approprie
- Configurer commandes test et lint
-
Charger configuration:
- Lire
ralph.ymlou.claude/ralph.yml - Definir iterations max, timeouts, criteres DoD
- Initialiser hooks si actives
- Lire
2. Boucle principale avec Dashboard
╔═══════════════════════════════════════════════════════════════╗
║ RALPH WIGGUM - Session: ralph-xxx PHASE: GREEN ║
╠═══════════════════════════════════════════════════════════════╣
║ ITERATION 8/25 ECOULE: 12:34 ║
║ PROGRES ████████████████░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 32% ║
║ ║
║ Circuit Breaker: ░░ (0/4) Contexte: ████████░░ 78% ║
╚═══════════════════════════════════════════════════════════════╝
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 · 249 lines · 24 tokens per session scan A 881cb9303d55
ralph-run is a command published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed 6d ago), licensed MIT. It adds 24 tokens to every session and 2,312 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 2026-08-30.
Other commands, from other repositories
test-suite
Run comprehensive test suite with coverage analysis.
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.