gantry: Skill for Claude Code

.claude/skills/prayerlang/SKILL.md

prayerlang is a skill for Claude Code from geleynse/gantry. It costs 65 tokens per session (3,688 once invoked), scanned A, original, MIT.

A guide to PrayerLang, a small scripting language that lets a fleet agent submit one bounded game script instead of making many separate requests. The server parses, checks, and runs the script against cached game state.

In plain words
What is it for?
Adding or changing PrayerLang statements and conditions, debugging interrupted or failed scripts, and keeping its parser, checks, executor, tests, and documentation consistent.
Why use it?
It reduces turn-by-turn control for supported tasks and documents how scripts are validated, including command arguments, denied tools, item or location names, and execution limits.

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/prayerlang/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 prayerlang

README.md
[![agentmods](https://agentmods.dev/badge/skills/geleynse/gantry/prayerlang.svg)](https://agentmods.dev/skills/geleynse/gantry/prayerlang)
Your own site
<a href="https://agentmods.dev/skills/geleynse/gantry/prayerlang"><img src="https://agentmods.dev/badge/skills/geleynse/gantry/prayerlang.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,688 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 $0.00065 $0.03688
Opus 5 $0.00032 $0.01844
Sonnet 5 $0.00013 $0.00738
Haiku 4.5 $0.00006 $0.00369

Measured 7d ago against content hash 3bd5db763af0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

prayerlang 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 7d 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/prayerlang/SKILL.md · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PrayerLang

PrayerLang is a tiny DSL that lets a fleet agent submit one bounded, deterministic script to the server instead of driving a mining/trading loop turn-by-turn — one spacemolt_pray MCP call replaces N LLM turns. The runtime parses, statically analyzes (arity, denied tools, fuzzy item/POI resolution), then executes server-side against the agent's cached game state, dispatching real game tool calls as it goes. Inspired by prayer.rs; Gantry's version is a from-scratch TypeScript reimplementation for the SpaceMolt tool surface.

Where it lives

All in server/src/proxy/prayer/, each file with a co-located *.test.ts:

File Role
parser.ts Lexer + recursive-descent parser. parsePrayerScript(source) → AstProgram; formatPrayerProgram() is the canonical pretty-printer used for normalized_script.
analyzer.ts Static pass: resolves command/predicate specs, checks arity, fuzzy-matches item/POI identifiers (Levenshtein), checks agentDeniedTools. analyzePrayerProgram(ast, snapshot) → AnalyzedProgram.
executor.ts Runs the analyzed program statement-by-statement; owns step/loop/wall-clock limits and mid-script interrupt checks. executePrayerProgram(program, deps) → PrayResult.
commands.ts COMMANDS registry (one CommandSpec per statement keyword) + UNSUPPORTED_COMMANDS deny-list.
predicates.ts evalPredicate() + computeMetric() — the if/until condition evaluator.
state.ts Pure readers over the cached status blob (getCargo, cargoPct, homeDestination, ...) — every predicate/command reads through these, never data.foo directly.
checkpoint.ts Serialize/persist/resume ExecState across server restarts.
result.ts Builds the final PrayResult: diff snapshot + tiered error shape.
index.ts runPrayerScript(script, deps) — public entry point: parse → analyze → execute, catching errors from any stage into resultFromError.
types.ts All shared types: AST, CommandSpec, PredicateName, ExecState, PrayResult, the three error classes.

Read the full file on GitHub · 223 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. 7d ago First seen · 223 lines · 65 tokens per session scan A 3bd5db763af0

Subscribe to this mod's changes

prayerlang is a skill published in the GitHub repository geleynse/gantry (3 stars, last pushed 2d ago), licensed MIT. It adds 65 tokens to every session and 3,688 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.