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/proxy-networknpx skills add Teddy563/mcwrench --skill proxy-networkgit clone --depth 1 https://github.com/Teddy563/mcwrenchWhat 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 | $0.00155 | $0.00846 |
| Opus 5 | $0.00077 | $0.00423 |
| Sonnet 5 | $0.00031 | $0.00169 |
| Haiku 4.5 | $0.00015 | $0.00085 |
Grade A, and why
proxy-network 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 2d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proxy / Network
Default proxy: Velocity (by the Paper team; TOML config, modern forwarding). Waterfall is in
maintenance mode; BungeeCord is legacy. See references/velocity-modern-forwarding.md for the
exact forwarding handshake — getting it wrong is the #1 network setup failure.
The forwarding contract (must all line up)
For a Velocity network with modern forwarding:
- Proxy
velocity.toml:player-info-forwarding-mode = "modern"andforwarding-secret-file = "forwarding.secret". - Secret: the proxy's
forwarding.secretfile contents must exactly equal each backend'spaper-global.yml: proxies.velocity.secret. - Backend
paper-global.yml:proxies.velocity.enabled: true, matchingsecret, andproxies.velocity.online-modeequal to the proxy'sonline-mode. - Backend
server.properties:online-mode=false(the proxy handles authentication). - Never also set
spigot.yml: settings.bungeecord: true— Velocity + BungeeCord forwarding enabled together stops the backend from starting.
velocity.toml essentials
bind = "0.0.0.0:25565"
online-mode = true
player-info-forwarding-mode = "modern"
forwarding-secret-file = "forwarding.secret"
[servers]
lobby = "127.0.0.1:30066"
survival = "127.0.0.1:30067"
try = ["lobby"]
[forced-hosts]
"play.example.net" = ["lobby"]
[advanced]
compression-threshold = 256
login-ratelimit = 3000
- Backends bind to internal/loopback ports; only the proxy port is public. Firewall the
backend ports so players can't bypass the proxy (which would hit
online-mode=falsedirectly — a security hole). trysets the initial-connect order;forced-hostsroutes by hostname.
Troubleshooting map
| Symptom | Cause → fix |
|---|---|
| "Unable to connect you… invalid forwarding" | secret mismatch or wrong forwarding mode → align secret + set modern both sides |
| Players join as offline UUID / skins broken | backend online-mode=true, or proxies.velocity.online-mode mismatch → set backend online-mode=false, match proxy |
| Backend won't start | BungeeCord and Velocity forwarding both enabled → disable one |
| Anyone can join backend directly as op | backend port exposed publicly with online-mode=false → firewall to proxy only |
| Legacy BungeeCord network | use ip_forward: true + bungeecord: true; do NOT also enable Velocity |
What ships with it
1 file 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.
- 2d ago First seen · 78 lines · 155 tokens per session scan A 90cd23d4f435
proxy-network is a skill published in the GitHub repository Teddy563/mcwrench (1 stars, last pushed 9d ago), licensed MIT. It adds 155 tokens to every session and 846 once invoked, about $0.0008 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
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.
roblox-studio
Build and edit in Roblox Studio via the Roblox Studio MCP the RIGHT way - preflight the Studio connection, do the whole build in a few big executeluau scripts (not dozens of tiny calls), make REALISTIC terrain with the Terrain VOXEL api driven by Perlin noise (NEVER stacked Parts or concentric layers - those give ugly…
threejs-animation
Three.js animation - keyframe animation, skeletal animation, morph targets, animation mixing. Use when animating objects, playing GLTF animations, creating procedural motion, or blending animations.
domain-glossary
Extract a DDD-style ubiquitous language glossary from the current conversation.
spec-to-plan
Turn a PRD into a multi-phase implementation plan using tracer-bullet vertical slices.
code-review
Performs a thorough code review of the current changes or a specified file / pull request. Covers correctness, security, performance, readability, and adherence to project conventions. Outputs prioritised, actionable feedback. TRIGGER when the user writes /code-review or asks for a code review, PR review, or feedback…