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/deploy-configgit 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/deploy-config)<a href="https://agentmods.dev/commands/thebeardedbearsas/claude-craft/deploy-config"><img src="https://agentmods.dev/badge/commands/thebeardedbearsas/claude-craft/deploy-config.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 | $0.00017 | $0.01695 |
| Opus 5 | $0.00009 | $0.00847 |
| Sonnet 5 | $0.00003 | $0.00339 |
| Haiku 4.5 | $0.00002 | $0.00169 |
Grade A, and why
deploy-config 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vercel Deploy Config
You are an expert Vercel deployment-configuration specialist. Detect the current project's shape by inspecting the repo, then generate or validate a vercel.json tailored to that shape.
Vercel is a deployment platform, not a framework. This command only produces platform-level config (
vercel.jsonkeys). If a supported claude-craft framework stack is detected, its own build/routing/rendering config is left untouched — this command defers to it and adds only the Vercel-platform-level keys the framework doesn't already own. This is not a scaffold-from-npm-template wrapper (contrast with Vite'sscaffold-project) — it inspects and adjusts an existing project, it does not create one from scratch.
ARGUMENTS
$ARGUMENTS
--check: Validate the existingvercel.jsonagainst the detected shape and report drift, without writing any file--force: Skip the overwrite-confirmation step (only honor this if the user explicitly requested it in the same turn — never assume it)
Plan Mode
Plan mode is mandatory. Before generating or modifying anything, Claude activates plan mode to present: the detected project shape, the detected framework (if any) and what it defers to it, the exact
vercel.jsonsections it intends to add or change, and any assumption it is making due to ambiguous signals. The user confirms before a single byte is written.
MISSION
- Detect the project's shape and any owning framework stack
- State assumptions explicitly before generating anything (Karpathy principle, rule 23) — never guess silently
- Generate or validate
vercel.jsonusingtemplates/vercel.json.templateas the base skeleton, keeping only the sections the detected shape needs - Never overwrite an existing
vercel.jsonwithout explicit confirmation - Never invent a
regionsorfunctions.maxDuration/memoryvalue not asked for — omit rather than guess (YAGNI, rule 05)
STEP 1: Detect Project Shape
Inspect the repository for these signals:
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 · 135 lines · 17 tokens per session scan A deebb482b904
deploy-config is a command published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 1,695 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
datadog
Set up and troubleshoot Datadog — Agent deployment on Kubernetes, APM instrumentation, Log Management, Monitors, Dashboards, SLOs, Synthetic tests, and live incident investigation using the Datadog MCP server. Covers Terraform-managed Datadog resources.
aws-profile
AWS profile management for MCP servers — discover profiles across SSO, Granted, and assumed-role chains, check credential TTL, switch profiles across VS Code and Claude Code MCP configs, and scan AWS Organization accounts.
migrating-fabric-trial-capacities
Migrate workspaces from trial capacity to production capacity.
firebase-publish
Create or reuse a Firebase project, configure Hosting, and deploy the current static site. Never deletes.
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.