agentmods.dev

play

play is a command for coding agents from actually-useful-ai/aivia. It costs 7 tokens per session (1,470 once invoked), scanned A, original, MIT.

A command that starts a new Aivia game or resumes a saved one. It reads the session state, restores the game directory, and asks for project choices when older sessions lack them.

In plain words
What is it for?
Use it to resume an existing game, choose a demo or custom project, or begin a new session.
Why use it?
It removes the manual work of finding a saved session and restoring the game to its previous phase and project context.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

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

not rated 1 4mo ago A scan 7 tokens original MIT
View the source file actually-useful-ai/aivia
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 commands/actually-useful-ai/aivia/play
Clone the repo
git clone --depth 1 https://github.com/actually-useful-ai/aivia

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

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 play

README.md
[![agentmods](https://agentmods.dev/badge/commands/actually-useful-ai/aivia/play.svg)](https://agentmods.dev/commands/actually-useful-ai/aivia/play)
Your own site
<a href="https://agentmods.dev/commands/actually-useful-ai/aivia/play"><img src="https://agentmods.dev/badge/commands/actually-useful-ai/aivia/play.svg" alt="Measured on agentmods" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,470 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 $0.00007 $0.01470
Opus 5 $0.00003 $0.00735
Sonnet 5 $0.00001 $0.00294
Haiku 4.5 $0.00001 $0.00147

Measured 3d ago against content hash a41abd97e5b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

play 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 3d 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/commands/play.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/aivia:play — Start or Resume Game

Check for an existing game session and either resume or start fresh.

Resume Flow

  1. Check if ~/aivia/.config/cache/session.json exists (or the path from the argument)
  2. If it exists, read the state file to determine current phase
  3. Show the intro: bash "$GAME_DIR/.config/scripts/intro.sh" resume "$(player_name)" (Read player.name from state.json for the greeting)
  4. Change working directory to the game directory as your FIRST Bash call: cd $GAME_DIR && pwd (verify it worked).
  5. Run the resume command: export AIVIA_GAME_DIR="$GAME_DIR" && bash "$GAME_DIR/.config/scripts/state.sh" resume
  6. Check player.project_mode — if null/missing, the install predates the project menu. Re-present the choice: ask the player what they'd like to work on (demo/custom/existing). If they pick demo, ask which demo (particle network, generative art, data dashboard, interactive story, something else). Save both to state.json via state.sh set.
  7. If session.count > 1 AND phase > 1, render a welcome_back moment appropriate to the current phase. In phase 1 (pre-contact), skip — the entity hasn't appeared yet.
  8. Read the appropriate keystone file for the current phase from $GAME_DIR/.config/docs/
  9. Read the entity character guide from $GAME_DIR/.config/templates/style-guide.md
  10. Read the story manifest from $GAME_DIR/.config/project.json
  11. Load the runtime skill and continue the game from the current phase

Fresh Install Flow

  1. If no state file exists, run the install script: bash "${CLAUDE_PLUGIN_ROOT}/engine/scripts/install.sh"
  2. The install script handles: EULA consent, player name, game directory, editor preference, terminal theme, skill level, project choice (demo/custom/existing), and if demo, which demo
  3. After install completes, read the game directory path from /tmp/.aivia_game_dir
  4. Set GAME_DIR to that path
  5. IMMEDIATELY change working directory to the game directory. Run as your FIRST Bash call: cd $GAME_DIR && pwd (verify it worked). This is critical — all file creation, all workspace paths, everything depends on being in $GAME_DIR. If the cd fails, stop and tell the player.
  6. Prompt the player to run bash $GAME_DIR/workspace/verify.sh (post-install verification). Always use absolute paths when telling the player to run scripts — never relative. Replace $GAME_DIR with the actual path (e.g., ~/aivia/workspace/verify.sh). Wait for them to run it, then check .config/cache/.verify_result to confirm.
  7. Read the story manifest and first keystone
  8. Load the runtime skill and begin Act 1

Read the full file on GitHub · 116 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. 3d ago First seen · 116 lines · 7 tokens per session scan A a41abd97e5b1

Subscribe to this mod's changes

play is a command published in the GitHub repository actually-useful-ai/aivia (1 stars, last pushed 4mo ago), licensed MIT. It adds 7 tokens to every session and 1,470 once invoked, about $0.0000 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.

Game developmentansi-artbashclaude-codeclaude-code-plugincliinteractive-fiction
Related

Other commands, from other repositories

handoff

Hand work to Claude Code or Pi through a bounded semantic checkpoint, resume or recover a checkpoint, inspect status, or close a completed handoff.

lugassawan/swe-workbench · 29 tokens

test

Invoke the test-writer subagent to add focused, behavioural tests in the target language's idiom. Pass --mode e2e (or --e2e) to run the browser-driven E2E pipeline instead, or --mode e2e-live for an ephemeral, human-watched browser walkthrough with no spec file written.

lugassawan/swe-workbench · 67 tokens

extend

Capture a mid-PR sub-idea and implement it onto the current open PR's branch — no new branch, no new PR. Preserves Verify → Review → Deliver.

lugassawan/swe-workbench · 35 tokens

profile

Show or change which Claude account this directory uses.

dcotelo/cprof · 9 tokens

tmux-project

Open (or reuse) a project workspace session — server / agent / editor.

Aey-Sama/tmux-arsenal · 15 tokens

implement

Drive a feature implementation end-to-end from a ticket or spec — branch, plan, build, verify, review, deliver.

lugassawan/swe-workbench · 24 tokens