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/recette)<a href="https://agentmods.dev/commands/thebeardedbearsas/claude-craft/recette"><img src="https://agentmods.dev/badge/commands/thebeardedbearsas/claude-craft/recette.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 5.1 | $0.00011 | $0.01950 |
| Opus 5 | $0.00005 | $0.00975 |
| Sonnet 5 | $0.00002 | $0.00390 |
| Haiku 4.5 | $0.00001 | $0.00195 |
Grade A, and why
recette 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 4d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Recette - Tests d'Acceptance Automatises
Execute des tests d'acceptance automatises (recette) sur les applications web en utilisant Claude in Chrome pour l'automatisation navigateur. Ce systeme implemente la Regle d'Or : Un bug corrige ne doit JAMAIS reapparaitre.
Arguments
$ARGUMENTS
--scope=<type>: Perimetre de test (story, epic, sprint, task)--id=<target-id>: Identifiant cible (ex: US-001, EPIC-01, Sprint-3)--resume=<session-id>: Reprendre depuis une session precedente--record-gif: Enregistrer un GIF de l'execution--dry-run: Generer le plan sans executer les tests--base-url=<url>: Surcharger l'URL de base
Fonctionnalites Cles
| Fonctionnalite | Description |
|---|---|
| Plans Exhaustifs | Genere des plans de test exhaustifs depuis les criteres d'acceptance |
| Automatisation Navigateur | Utilise Claude in Chrome pour des tests navigateur reels |
| Reprise de Session | Resume base sur des checkpoints pour les sessions interrompues |
| Regle d'Or | Generation automatique de tests de regression pour toutes les erreurs |
| Documentation Vivante | Maintient la documentation de test avec tracabilite |
| Detection de Regressions | Compare les executions pour detecter les regressions |
Prerequis
- Extension Claude in Chrome : Version 1.0.36 ou superieure
- Navigateur Chrome : Ouvert avec l'extension active
- Claude Code : Demarre avec le flag
--chromeou la commande/chrome
# Demarrer Claude Code avec support Chrome
claude --chrome
# Ou activer Chrome dans une session existante
/chrome
Processus
1. Verification
La commande verifie d'abord que le MCP Chrome est disponible :
┌─────────────────────────────────────────┐
│ 1. check_chrome_mcp() │
│ - MCP claude-in-chrome present ? │
│ - Extension connectee ? │
│ - Permissions site OK ? │
└─────────────────────────────────────────┘
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.
- 4d ago First seen · 246 lines · 11 tokens per session scan A a589d2a502d4
recette is a command published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed 5d ago), licensed MIT. It adds 11 tokens to every session and 1,950 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
ui-test.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
run-test
Execute AI agent test script in real browser.
qa
Dispatch a verifiable browser task to the qa-tester subagent. Use for regression checks, smoke tests, and any task with a clean pass/fail outcome. Supports an EXHAUSTIVE mode that verifies every control behind an honesty gate.
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.