gantry: Skill for Claude Code

.claude/skills/add-v2-action/SKILL.md

add-v2-action is a skill for Claude Code from geleynse/gantry. It costs 78 tokens per session (3,623 once invoked), scanned A, original, MIT.

A guide for adding a new action to the version-2 command interface of the SpaceMolt game server. The interface uses a small set of named tools and an action value to select a behavior, instead of separate tools for every game operation.

In plain words
What is it for?
Use it when exposing a new game action, helper, or cached-data query through the v2 SpaceMolt interface.
Why use it?
It explains where a new action belongs and how it should connect with older version-1 commands and cached or computed data. This reduces the chance of adding an action to the wrong dispatch path.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions AGENTS.md; mentions Codex.

This is geleynse/gantry's own configuration. It tells Claude Code how to work on gantry itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gantry configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { getStationsForItem } from "../services/market-history.js";.

Reuse

Borrowing it

Nothing to install: this file belongs to geleynse/gantry. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/geleynse/gantry/main/.claude/skills/add-v2-action/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/geleynse/gantry

Made for: Claude Code.

Wrote 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.

agentmods badge for add-v2-action

README.md
[![agentmods](https://agentmods.dev/badge/skills/geleynse/gantry/add-v2-action/github.svg)](https://agentmods.dev/skills/geleynse/gantry/add-v2-action)
Your own site
<a href="https://agentmods.dev/skills/geleynse/gantry/add-v2-action"><img src="https://agentmods.dev/badge/skills/geleynse/gantry/add-v2-action/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.

agentmods 80×15 button for add-v2-action

Your own site · 80×15
<a href="https://agentmods.dev/skills/geleynse/gantry/add-v2-action"><img src="https://agentmods.dev/badge/skills/geleynse/gantry/add-v2-action.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,623 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00078 $0.03623
Opus 5 $0.00039 $0.01811
Sonnet 5 $0.00016 $0.00725
Haiku 4.5 $0.00008 $0.00362

Measured 10d ago against content hash 1497806b9468, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

add-v2-action 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 10d 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.

.claude/skills/add-v2-action/SKILL.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adding a v2 Action — Gantry Server

1. The dispatch model

v2 consolidates the game's tools into a handful of namespaced MCP tools — spacemolt (default/core gameplay), spacemolt_market, spacemolt_catalog, spacemolt_storage, spacemolt_battle, spacemolt_salvage, spacemolt_ship, spacemolt_social, spacemolt_facility, spacemolt_faction, spacemolt_auth (login/logout only, intercepted separately) — instead of 60+ individually named v1 tools. Each namespaced tool takes an action string param (or, for spacemolt_catalog, a type param) that selects the behavior: spacemolt(action="jump", id="sirius"), spacemolt_storage(action="deposit", item_id="iron_ore", qty=10).

Stale doc warning: AGENTS.md says "6 namespaces." The actual v1→v2 alias table (V1_TO_V2_DISPATCH in server/src/proxy/dispatch-v1-to-v2.ts) covers 9 distinct spacemolt_* tool names, and the live namespace count isn't fixed by gantry code at all — createGantryServerV2() registers whatever tool names the live game server advertises (shared.v2Tools, fetched per-preset in schema.ts). Don't cite a namespace count — grep V1_TO_V2_DISPATCH, or check the running server's GET /health (tools_v2 count, v2_presets list) for the live figures.

Most namespaced tools' action param is a bare string with no enumwithPrayerScriptSchema() in gantry-v2.ts notes this explicitly for spacemolt: "client-side Zod accepts any string... proxy actions validate without enum injection." That means adding a new action usually requires zero schema changes, just a dispatch branch. The one namespace that does enum-constrain its dispatch key is spacemolt_catalog (type has a real enum) — see §5.

2. Which of three categories are you adding?

A. Proxy-computed helper action (no game-server round trip). The action is answered entirely from gantry's own state (SQLite, in-memory caches, computed from existing data) — e.g. find_local_route, find_item_market, recent_snapshot, snapshot_coverage, craft_chains, arbitrage_routes. This is the pattern demonstrated by the canonical example commit — see §3. You add an if (action === "your_action") { ... return textResult(...); } branch inside the big per-tool dispatch chain in createGantryServerV2() (server/src/proxy/gantry-v2.ts).

Read the full file on GitHub · 236 lines

Changes

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.

  1. 10d ago First seen · 236 lines · 78 tokens per session scan A 1497806b9468

Subscribe to this mod's changes

add-v2-action is a skill published in the GitHub repository geleynse/gantry (3 stars, last pushed 4d ago), licensed MIT. It adds 78 tokens to every session and 3,623 once invoked, about $0.0004 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.

Related

Other skills, from other repositories