gantry: Skill for Claude Code

.claude/skills/add-routine/SKILL.md

add-routine is a skill for Claude Code from geleynse/gantry. It costs 69 tokens per session (3,311 once invoked), scanned A, original, MIT.

A guide for adding or changing deterministic game routines: scripted, multi-step sequences that run without asking an AI model for every step. It covers how these routines are defined, registered, triggered, and saved.

In plain words
What is it for?
Use it when implementing or debugging sequences such as travelling, mining, selling, refuelling, patrolling, or managing a game fleet.
Why use it?
It gives developers the conventions needed to add routines consistently and avoid common registration or state-management errors.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

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 →

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-routine/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-routine

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/geleynse/gantry/add-routine"><img src="https://agentmods.dev/badge/skills/geleynse/gantry/add-routine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,311 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 $0.00069 $0.03311
Opus 5 $0.00034 $0.01656
Sonnet 5 $0.00014 $0.00662
Haiku 4.5 $0.00007 $0.00331

Measured 8d ago against content hash 5c1664880ee7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

add-routine 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 8d 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-routine/SKILL.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adding a Routine — Gantry Server

1. What a routine is

A routine is a scripted state machine that runs a full multi-step game sequence (travel → dock → sell, or check-fleet → jump → verify-arrival) without LLM inference per step — the whole sequence executes server-side and returns one result. They cut cost by avoiding an LLM round-trip per game action.

18 routines exist today (server/src/routines/routine-runner.ts, BUILTIN_ROUTINES): sell_cycle, mining_loop, refuel_repair, patrol_and_attack, mission_run, mission_check, navigate_and_mine, craft_and_sell, explore_system, salvage_loop, full_trade_run, supply_run, navigate_home, explore_and_mine, manage_storage, upgrade_ship, fleet_refuel, fleet_jump.

Stale doc warning: the execute_routine unknown-routine error message in server/src/proxy/gantry-v2.ts (~line 830) hard-codes a 13-name list that is missing manage_storage, navigate_home, explore_and_mine, fleet_refuel, fleet_jump. Don't treat that error string as the source of truth — always call getAvailableRoutines() (or read BUILTIN_ROUTINES) for the real list. If you touch that error message while adding a routine, fix the list too.

Canonical examples to copy:

  • Simple, single-destination: server/src/routines/sell-cycle.ts + sell-cycle.test.ts (14 tests) — travel/dock, market analysis, retry-on- not_docked, early-abort-on-no-demand.
  • Fleet-coordination style (no travel/dock): server/src/routines/fleet-jump.ts — checks spacemolt_fleet(action="status"), hands off if members are scattered, jumps, re-verifies via a second fleet-status call.

2. Module shape

New file: server/src/routines/<name>.ts. Test: server/src/routines/<name>.test.ts (co-located, bun:test). Every routine implements RoutineDefinition<TParams> from server/src/routines/types.ts:

export interface RoutineDefinition<TParams = Record<string, unknown>> {
  name: string;                    // e.g. "sell_cycle" — must match ROUTINE_REGISTRY key
  description: string;             // shown to agents
  parseParams(raw: unknown): TParams;   // validate + parse, throw Error on bad input
  run(ctx: RoutineContext, params: TParams): Promise<RoutineResult>;
}

Read the full file on GitHub · 229 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. 8d ago First seen · 229 lines · 69 tokens per session scan A 5c1664880ee7

Subscribe to this mod's changes

add-routine is a skill published in the GitHub repository geleynse/gantry (3 stars, last pushed 3d ago), licensed MIT. It adds 69 tokens to every session and 3,311 once invoked, about $0.0003 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.