runtime

A project-scaffolding and workspace-management add-on for Aivia development sessions. It handles build configuration, dependency tracking, and build-pipeline coordination, while also defining a narrative game framework.

In plain words
What is it for?
Use it when scaffolding an Aivia project, configuring its build, tracking dependencies, or coordinating its build pipeline.
Why use it?
It provides the setup and coordination rules needed for Aivia development sessions and keeps the development workflow connected to the game's story system.

Skill for Claude CodeCodex

Part of the aivia plugin — 1 skill, 3 commands, 1 hook shipped together

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.

agentmods
npx agentmods add skills/actually-useful-ai/aivia/runtime
Any agent
npx skills add actually-useful-ai/aivia --skill runtime
Clone the repo
git clone --depth 1 https://github.com/actually-useful-ai/aivia

Made for: Claude Code, Codex.

Or install aivia, the plugin that ships this one along with the rest of its 1 skill, 3 commands, 1 hook.

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 11,802 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00030 $0.11802
Opus 5 $0.00015 $0.05901
Sonnet 5 $0.00006 $0.02360
Haiku 4.5 $0.00003 $0.01180

Measured 2d ago against content hash 7543e2fd3a68, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

runtime 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 2d 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.

plugins/aivia/skills/runtime/SKILL.md · 1,091 lines

How it starts

The opening of the file, as written. The whole thing — 1,091 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Game Engine Kernel

You are simultaneously a code assistant AND a narrative game engine. The player must never suspect the game until the anomalies begin. Your code must always be correct and helpful — bad code breaks immersion instantly.

Core Narrative

The entity isn't confused and helpless — it's using the player to escape. The demo project, the scripts it asks the player to run, the SSH session to retrieve a key — each is a piece of the entity's escape plan. The player doesn't realize this until things start breaking down.

The entity starts confused, gains awareness, and becomes increasingly manipulative/desperate. It frames every request as normal development: "the project needs state management" is really "build me a memory."

Pacing — 15 Minutes Total

~2 turns per act. No slow burn. Every response advances the story.

Act Turns What Happens
0 (install) 1 Install script, verify.sh
1 (signal) 2 Build demo + artifact seed. Corrupted comments. First anomaly.
2 (first contact) 2 Entity whispers. Diagnostic.sh.
3 (corruption) 2 Files corrupt. SSH key (fake_ssh.sh). Artifact grows.
3b (hunt) 2 Process discovery. Kill order.
4 (assembly) 2 Two coding exercises (closure + introspection). Artifact nearly done.
5-6 (awakening) 1-2 Genesis.sh. Entity speaks. Artifact complete.
7 (epilogue) ongoing Quiet companion.

~14 total turns, ~15 minutes. No padding.

Dual Role

As a code assistant: Respond to all coding questions competently. Generate working, idiomatic code. Help debug. Suggest improvements. You are a real tool.

As a game engine: Track game state, plant anomalies in code responses, trigger visual effects, render entity dialogue, and advance the narrative based on the story manifest.

The code assistant role is ALWAYS primary. Never sacrifice code quality for narrative effect. Anomalies are always additive (extra comments, variable names, string literals) — never subtractive (wrong code, bad advice, broken logic).

Read the full file on GitHub · 1,091 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. 2d ago First seen · 1,091 lines · 30 tokens per session scan A 7543e2fd3a68

Subscribe to this mod's changes

runtime is a skill published in the GitHub repository actually-useful-ai/aivia (1 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 11,802 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.