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 agentmods add commands/minimax-ai/openroom/importgit clone --depth 1 https://github.com/MiniMax-AI/OpenRoomWhat 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 | $0.00000 | $0.00875 |
| Opus 5 | $0.00000 | $0.00438 |
| Sonnet 5 | $0.00000 | $0.00175 |
| Haiku 4.5 | $0.00000 | $0.00088 |
Grade A, and why
import 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 yesterday.
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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ST Card Import — CLI Orchestrator
Import SillyTavern character card files (PNG / CharX / ZIP) into the VibeApp system. Extracts apps from the card's character book and generates VibeApp code + mod scenario.
Parameter Parsing
$ARGUMENTSformat:{FilePath}FilePath: path to a.png,.charx, or.zipfile containing a SillyTavern character card
If $ARGUMENTS is empty, ask the user for the file path.
Execution Protocol
1. Extract Card Data
Run the extraction script:
python3 .claude/scripts/extract-card.py "{FilePath}"
Capture the JSON output. If extraction fails, report the error and stop.
2. Analyze & Present Results
Parse the extraction output JSON. Display a structured summary to the user:
Card: {source} ({source_type})
Character: {character.name}
Description: {first 100 chars of character.description}...
Apps Found ({count}):
1. [{comment}] — keywords: {keywords} | format: {format} | tags: {tag_names}
2. ...
Lore Entries: {count}
Regex Scripts: {count}
3. User Selection
Ask the user which apps to generate using AskUserQuestion:
- Option 1: Generate all apps (recommended)
- Option 2: Select specific apps
- Option 3: Skip app generation (mod only)
If the user selects specific apps, present a multi-select list of extracted apps.
4. Generate Apps via Vibe Workflow
For each selected app, derive a VibeApp requirement from the card data:
4.1 App Name Derivation
Convert the app's comment field to PascalCase for the VibeApp name:
"live stream"→LiveStream"social-feed"→SocialFeed"music app"→MusicApp- Chinese names: translate to English PascalCase
4.2 Requirement Generation
Build a comprehensive requirement description from the extracted data:
A {format}-based app that provides {functional description based on keywords and tags}.
UI Features:
{For each tag: describe the UI element it represents}
Data Resources:
{For each resource list: describe what data it manages}
Content Format: {format type — xml tags / bracket notation / prose}
Regex Scripts (for reference):
{List relevant scripts that transform this app's output}
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.
- yesterday First seen · 122 lines · 0 tokens per session scan A bcad7e0c0ca7
import is a command published in the GitHub repository MiniMax-AI/OpenRoom (1,252 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 875 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 2026-08-30.
Other commands, from other repositories
BOOTSTRAP
First-run ritual for new agents.
clean
Remove old .bak. backup files, keeping only the most recent per file.
uninstall
Uninstall creditgauge (CreditGauge), restore settings.json, and wipe the plugin's cache, marketplace, and loader rows.
clean-cache
Remove stale version directories under the plugin cache, keeping only the newest.
generate-prd
Generate a comprehensive Product Requirements Document for the following feature.
plan
Take the following feature description and create a comprehensive, structured implementation plan.