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 cpappas213/meridian59-llm-bot --skill meridian59-botgit clone --depth 1 https://github.com/cpappas213/meridian59-llm-botWrote 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/cpappas213/meridian59-llm-bot/meridian59-bot)<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.
<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>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 | $0.00048 | $0.01688 |
| Opus 5 | $0.00024 | $0.00844 |
| Sonnet 5 | $0.00010 | $0.00338 |
| Haiku 4.5 | $0.00005 | $0.00169 |
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.
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.
- If onboarding is
awaiting_persona, ask the human for the desired character name and persona. Do not invent either. - Call
personawithaction="get", then set one complete persona using the returned version and a fresh request ID. - The configured LLM selects the supported build and the controller creates and verifies it. Generated placeholder characters may be replaced automatically.
- If an established differently named character is present, preserve it and ask
whether it should be replaced. Only set
replace_existing_character=trueafter explicit direction. - Wait until
onboarding.ready_for_goalsis true. Then accept a strategic goal from the human or higher-level agent.
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.
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.
- 11d ago First seen · 166 lines · 48 tokens per session scan A 7ce45190a7c4
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.
Other skills, from other repositories
pixel-art
Pixel art w/ era palettes (NES, Game Boy, PICO-8).
pokemon-player
Play Pokemon via headless emulator + RAM reads.
minecraft-modpack-server
Host modded Minecraft servers (CurseForge, Modrinth).
building-mobile-game
Build mobile games and game-like interactive experiences in React Native and Expo. Use when Codex is creating or refactoring arcade, puzzle, casual, action, physics-based, or animation-heavy gameplay, including Expo game setup with the with-reanimated template, sprite-sheet generation and extraction, frame-based…
pixel-art-storyboard
Convert short scene descriptions, book/album cover briefs, or 2-paragraph synopses into seamless-loop animated pixel-art covers rendered as self-contained HTML+canvas. Companion skill to pixel-art-studio. Use when the user asks to "make a cover for", "animated book cover", "looped pixel scene", "convert this story…
avalon-8-10p
Eight-to-ten-player Avalon rules for a permanent Agent host, with the user choosing to join the randomized player pool or spectate.