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 skills add Teddy563/mcwrench --skill gamemode-designergit 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/gamemode-designer)<a href="https://agentmods.dev/skills/teddy563/mcwrench/gamemode-designer"><img src="https://agentmods.dev/badge/skills/teddy563/mcwrench/gamemode-designer/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/skills/teddy563/mcwrench/gamemode-designer"><img src="https://agentmods.dev/badge/skills/teddy563/mcwrench/gamemode-designer.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 | $0.00185 | $0.01169 |
| Opus 5.5 | $0.00074 | $0.00468 |
| Sonnet 5.5 | $0.00037 | $0.00234 |
| Haiku 4.5 | $0.00018 | $0.00117 |
Grade A, and why
gamemode-designer 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 2mo 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.
Gamemode Designer (the foundry)
Take an idea all the way to a fun, re-engaging server. One command, /mcwrench:create, runs three
internal phases. Plan and write locally only. Never run live server commands, RCON, or panel
writes — that is a future operator mode, out of scope here. Never invent plugin config keys; map
every mechanic to a real plugin or flag it as custom, and fetch exact keys with learn-plugin-docs.
How fun works (bake this in)
A gamemode is fun when it has a clear Challenge → Action → Reward core loop, a nested or escalating loop for retention (prestige, seasons, a ladder to climb), and a twist on a familiar base rather than a clone. Originality comes from combining existing archetypes + exactly one bending twist + a theme — evolve, do not copy.
Phase 1 — IMAGINE (only when the input is vague)
If the user gives nothing, a vibe, or "something fun", generate 3 to 5 original concepts. For
each, fill: name, one-line pitch, base archetype(s) fused, the one twist, core loop, progression,
conflict + stakes, target audience, fun score, feasibility verdict + the plugin stack, and a
novelty note. Build concepts from references/mechanic-taxonomy.md (the 9 axes + twist bank). Score
with references/fun-feasibility-rubric.md. Propose the top 1 to 3 and let the user pick, or crown
the highest fun among the buildable-now options.
If the user already has a concrete idea ("a server where you age and die of old age", or a concept from a previous IMAGINE), skip to DESIGN.
Phase 2 — DESIGN the chosen concept
Lock it down: the core loop in one sentence, the single twist, the full plugin stack (each mechanic mapped to a real plugin), and the glue the twist needs (a config setting, a Skript, or a custom plugin). Sanity-check feasibility: stack exists, performance risk, abuse surface (alt-farming, grief, combat-logging, dupes), EULA pressure. Give a verdict: Config-only, Skript-glue, or Needs a custom plugin (park the last for later). Prefer the highest-fun idea that is Config-only or Skript-glue — that is one that "could actually work".
What ships with it
3 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.
- 2mo ago First seen · 75 lines · 185 tokens per session scan A d15d33be28a4
gamemode-designer is a skill published in the GitHub repository Teddy563/mcwrench (1 stars, last pushed 4d ago), licensed MIT. It adds 185 tokens to every session and 1,169 once invoked, about $0.0007 per session on Opus 5.5. 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.
gamemode-designer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gamemode-designerTeddy563/mcwrench | Skill | 1 | 4d ago | MIT | A | 185 | Claude Code |
| develop-web-gamenetease-youdao/LobsterAI | Skill | 6.2k | today | MIT | A | 64 | Codex |
| sable-game-art-getting-startedmakecindy/cindy | Skill | 9.4k | today | Apache-2.0 | A | 44 | Claude Code, Codex |
| sable-game-art-opsmakecindy/cindy | Skill | 9.4k | today | Apache-2.0 | A | 89 | Claude Code, Codex |
| sable-game-art-evidencemakecindy/cindy | Skill | 9.4k | today | Apache-2.0 | A | 58 | Claude Code, Codex |
| minecraft-bukkit-prormyndharis/antigravity-skills | Skill | 2.0k | 23d ago | MIT | A | 61 | Claude Code, Codex |
| godot-gdscript-patternsrmyndharis/antigravity-skills | Skill | 2.0k | 23d ago | MIT | A | 47 | Claude Code, Codex |