meridian59-bot

meridian59-bot is a skill for Claude Code, Codex from cpappas213/meridian59-llm-bot. It costs 48 tokens per session (1,688 once invoked), scanned A, original, MIT.

A tool for running and supervising an autonomous character in Meridian 59, an online role-playing game. It keeps the character working toward long-term goals and uses game information to guide its actions.

In plain words
What is it for?
Use it to manage research, resource gathering, travel, equipment, training, trading, recovery, and other ongoing game activities.
Why use it?
It lets play continue after the supervising agent disconnects while keeping goals, pauses, fair-play limits, and completion checks under control.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to manage research, resource gathering, travel, equipment, training, trading, recovery, and other ongoing game activities.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cpappas213/meridian59-llm-bot/meridian59-bot
Install

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.

Any agent
npx skills add cpappas213/meridian59-llm-bot --skill meridian59-bot
Clone the repo
git clone --depth 1 https://github.com/cpappas213/meridian59-llm-bot

Made for: Claude Code, Codex.

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 meridian59-bot

README.md
[![agentmods](https://agentmods.dev/badge/skills/cpappas213/meridian59-llm-bot/meridian59-bot/github.svg)](https://agentmods.dev/skills/cpappas213/meridian59-llm-bot/meridian59-bot)
Your own site
<a href="https://agentmods.dev/skills/cpappas213/meridian59-llm-bot/meridian59-bot"><img src="https://agentmods.dev/badge/skills/cpappas213/meridian59-llm-bot/meridian59-bot/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 meridian59-bot

Your own site · 80×15
<a href="https://agentmods.dev/skills/cpappas213/meridian59-llm-bot/meridian59-bot"><img src="https://agentmods.dev/badge/skills/cpappas213/meridian59-llm-bot/meridian59-bot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,688 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 $0.00048 $0.01688
Opus 5 $0.00024 $0.00844
Sonnet 5 $0.00010 $0.00338
Haiku 4.5 $0.00005 $0.00169

Measured 11d ago against content hash 7ce45190a7c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

meridian59-bot 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 11d 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.

config/hermes/meridian59-bot/SKILL.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meridian 59 Bot

Use meridian_bot to configure and supervise durable play. Use meridian_knowledge to ground game facts. The controller and configured LLM executor continue after this supervising agent disconnects.

Authority and execution contract

  • The human or higher-level agent owns the character identity, strategic goals, explicit pauses/cancellations, and deployment policy.
  • The configured LLM owns execution beneath an active goal. It plans research, farming, recovery, inventory, commerce, equipment, training, and travel.
  • The controller enforces tool boundaries, fair-play policy, deterministic completion, non-blocking consequence preflights, and durable recovery.
  • Never turn a tactical prerequisite into a replacement public goal unless the operator explicitly asks for that outcome.
  • Model claims, timestamps, and repeated action labels are not completion evidence. Use verified criterion and game-state changes.
  • A failed internal phase normally changes tactics while preserving the strategic goal. Pause or replace a goal only for explicit direction, deterministic completion, invalid/superseded intent, or a verified external blocker with ordinary-game alternatives exhausted.

The normative execution design is LONG_HORIZON_EXECUTION_ARCHITECTURE.md in the project repository.

First-run onboarding

Always inspect status(detail="supervision", include_recent_events=0) before submitting goals.

  1. If onboarding is awaiting_persona, ask the human for the desired character name and persona. Do not invent either.
  2. Call persona with action="get", then set one complete persona using the returned version and a fresh request ID.
  3. The configured LLM selects the supported build and the controller creates and verifies it. Generated placeholder characters may be replaced automatically.
  4. If an established differently named character is present, preserve it and ask whether it should be replaced. Only set replace_existing_character=true after explicit direction.
  5. Wait until onboarding.ready_for_goals is true. Then accept a strategic goal from the human or higher-level agent.

Read the full file on GitHub · 166 lines

Files

What ships with it

4 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.

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. 11d ago First seen · 166 lines · 48 tokens per session scan A 7ce45190a7c4

Subscribe to this mod's changes

meridian59-bot is a skill published in the GitHub repository cpappas213/meridian59-llm-bot (0 stars, last pushed 16d ago), licensed MIT. It adds 48 tokens to every session and 1,688 once invoked, about $0.0002 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.