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 IvanSkainet/arena-agent --skill book-of-eternitygit clone --depth 1 https://github.com/IvanSkainet/arena-agentWrote 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/ivanskainet/arena-agent/book-of-eternity)<a href="https://agentmods.dev/skills/ivanskainet/arena-agent/book-of-eternity"><img src="https://agentmods.dev/badge/skills/ivanskainet/arena-agent/book-of-eternity/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/ivanskainet/arena-agent/book-of-eternity"><img src="https://agentmods.dev/badge/skills/ivanskainet/arena-agent/book-of-eternity.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 | $0.00000 | $0.01435 |
| Opus 5 | $0.00000 | $0.00718 |
| Sonnet 5 | $0.00000 | $0.00287 |
| Haiku 4.5 | $0.00000 | $0.00144 |
Grade A, and why
book-of-eternity 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 12d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Book of Eternity: Reborn — Arena Agent Mode GM
Use an already-running Arena.ai Agent Mode session as the external Game Master for The Book of Eternity: Reborn through Skainet Bridge.
The integration uses the normal Bridge surface: relay.*, fs.*, exec.*, and
any other generally available tool the task needs. A game-only token or a
hard-coded narrow tool subset is not required. The operator's global Bridge
profile remains the only capability policy layer.
Authority boundary
Skainet Bridge is transport and host access, not a second game engine.
- The game owns rules, validation, progression, canonical state, request correlation, and terminal-signal formats.
- The daemon packet and its current
gm_context_packown turn instructions. - The Arena agent owns reasoning and authorship.
- Do not copy C# validators, dice rules, realm matrices, or narrative rules into Bridge code or this skill.
- Do not treat chat history as canonical game memory. Read current host files.
No Codex process is required. Do not start or automate an Arena browser session; the relay is a durable mailbox for a session the player started themselves.
Transport chain
player action
-> game client writes canonical request
-> game_master_daemon.ps1 builds the current packet
-> BookOfEternityGMBridge hosts persistent arena-relay terminal in ConPTY
-> generic authenticated relay mailbox
-> active Arena Agent Mode session
-> ordinary fs.* / exec.* host work
-> game-owned terminal signal
-> correlated relay.reply releases the terminal
-> client validates and renders
Connect Arena Agent Mode
Two supported paths expose the same full Bridge tool catalog.
Browser-extension path
- Install
chat_extension/and configure the Bridge HTTPS URL and token. - On arena.ai, copy extension instructions with catalog scope GM: relay. + fs. + exec.***.
- Start Agent Mode yourself and paste this skill/bootstrap instruction.
- Tool blocks execute through
/v1/extension/execute; the extension does not automate login, model selection, or session creation.
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.
- 12d ago First seen · 140 lines · 0 tokens per session scan A d2b86ce85991
book-of-eternity is a skill published in the GitHub repository IvanSkainet/arena-agent (6 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,435 tokens. 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
site-audit
Use when user asks to audit a website, review all pages, check for broken links, capture full site state, or do a comprehensive product review.
kaboom
Use when user asks to check browser state, debug page errors, inspect network traffic, take screenshots, automate clicks or form fills, run accessibility or security audits, measure performance, generate tests, or record browser sessions. Trigger phrases: "check my browser", "debug this page", "take a screenshot"…
kaboom-connection-guard
Use when a tool call fails with "extension not connected", the daemon is unreachable, or browser telemetry stops arriving.
audit
Use when the user wants a full Kaboom quality audit of a web app or tracked site, with one polished report covering Functionality, UX Polish, Accessibility, Performance, Release Risk, and SEO.
api-validation
Use when user asks to check API responses, validate request/response contracts, compare API behavior against a spec, or detect schema drift.
automate
Use when user asks to automate browser actions, click buttons, fill forms, navigate pages, run a sequence of browser steps, or build a repeatable workflow.