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 skills/teddy563/mcwrench/new-server-bootstrapnpx skills add Teddy563/mcwrench --skill new-server-bootstrapgit clone --depth 1 https://github.com/Teddy563/mcwrenchWrote 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/skills/teddy563/mcwrench/new-server-bootstrap)<a href="https://agentmods.dev/skills/teddy563/mcwrench/new-server-bootstrap"><img src="https://agentmods.dev/badge/skills/teddy563/mcwrench/new-server-bootstrap.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 | $0.00170 | $0.01197 |
| Opus 5 | $0.00085 | $0.00598 |
| Sonnet 5 | $0.00034 | $0.00239 |
| Haiku 4.5 | $0.00017 | $0.00120 |
Grade A, and why
new-server-bootstrap scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New Server Bootstrap
Stand up a working base server, then layer the gamemode stack on top.
Current facts (verified 2026-06-07): Minecraft is 26.1.x. Latest Paper is 26.1.2 build 69. Paper 26.1+ requires Java 25. Velocity is 3.5.0-SNAPSHOT (needs Java 21+). Always re-query the API for the live latest build at setup time.
Steps
- Scope. Single server or a network? Gamemode? Host (self-hosted, Pterodactyl/Pelican, other)? Player count? → recommend Paper by default (see Folia note below).
- Download the latest Paper build — use the Fill v3 API (the old v2 API stopped builds
2025-12-31). Do NOT hand-construct download URLs; read the URL from the API response. Helper:
Manually:node "${CLAUDE_PLUGIN_ROOT}/skills/new-server-bootstrap/scripts/fetch-paper.mjs" 26.1.2 # prints the resolved STABLE build + download URL (and --download to fetch it)GET https://fill.papermc.io/v3/projects/paper/versions/{MC}/builds, pick the newestchannel: STABLE, downloaddownloads."server:default".url. A descriptiveUser-Agentis required by the API. - Install Java 25 (Paper 26.1+ will not start on older Java). Verify
java -version. - EULA + first run. Run once:
java -jar paper.jar --nogui→ it writeseula.txtand stops. Seteula=true(or pass-Dcom.mojang.eula.agree=true). Restart → it generatesserver.properties+ the world and comes online. - Startup script. Use the template
assets/startup.sh.tmpl(Java 25 + Aikar's/G1 flags +--nogui). KeepXms == Xmxwith host headroom (leave ~1–1.5 GB; on a panel keepXmxbelow the container limit — seepterodactyl-ops). Aikar's flags are PaperMC's documented default; only consider Generational ZGC as a Java-25 alternative, never mixed. - server.properties starter values — see
assets/the table below. Setonline-mode,view-distance,simulation-distance,max-players,motd,difficulty,gamemode. - Network? If multiple servers, set up Velocity (
assets/velocity.example.toml): first run generatesvelocity.toml+forwarding.secret; setplayer-info-forwarding-mode = "modern", put the secret into each backend'spaper-global.yml(assets/paper-global.example.yml), set each backendonline-mode=false, and firewall backend ports. Full detail:proxy-network. - Gamemode stack → hand off to
gamemode-stacksfor the archetype's plugins. - Review → run
audit-configon the finished tree; tune withperformance-tuning.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 75 lines · 170 tokens per session scan A 6f1f3feda309
new-server-bootstrap is a skill published in the GitHub repository Teddy563/mcwrench (1 stars, last pushed 5d ago), licensed MIT. It adds 170 tokens to every session and 1,197 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
aws-serverless-eda
AWS serverless and event-driven architecture expert based on Well-Architected Framework. Use when building serverless APIs, Lambda functions, REST APIs, microservices, or async workflows. Covers Lambda with TypeScript/Python, API Gateway (REST/HTTP), DynamoDB, Step Functions,...
aws-cdk-development
AWS Cloud Development Kit (CDK) expert for building cloud infrastructure with TypeScript/Python. Use when creating CDK stacks, defining CDK constructs, implementing infrastructure as code, or when the user mentions CDK, CloudFormation, IaC, cdk synth, cdk deploy, or wants to define AWS...
aws-cost-cleanup
Automated cleanup of unused AWS resources to reduce costs.
aws-cost-optimizer
Comprehensive AWS cost analysis and optimization recommendations using AWS CLI and Cost Explorer.
azd-deployment
Deploy containerized frontend + backend applications to Azure Container Apps with remote builds, managed identity, and idempotent infrastructure.
aegisops-ai
Autonomous DevSecOps & FinOps Guardrails. Orchestrates Gemini 3 Flash to audit Linux Kernel patches, Terraform cost drifts, and K8s compliance.