← Back to Skills Marketplace
OpenClaw SillyTavern Plugin
by
garfeildma
· GitHub ↗
· v0.1.0
· MIT-0
275
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install openclaw-tavern
Description
SillyTavern-compatible roleplay plugin with character cards, long memory, multimodal output (TTS/image), and Generative-Agents-style companion.
Usage Guidance
This plugin implements the described RP features and includes real source code (not just an instruction-only skill), but exercise caution before installing.
- Reconcile metadata: SKILL.md requests an `npm install` step and lists OPENCLAW_RP_LOCALE, while the registry summary omitted these—treat the SKILL.md as authoritative.
- Sensitive actions: the plugin can read ~/.openclaw configs, persist session/memory data (SQLite), modify plugin config, and write the agent's SOUL.md (system persona). Those are valid features but allow persistent modification of agent prompts and autonomous proactive messages—only grant these capabilities deliberately.
- Credentials: don’t expose unrelated high-privilege credentials. If you supply OPENAI_*/GEMINI_* keys, prefer least-privileged gateway accounts and isolate usage.
- Deployment advice: review the repository yourself (or have a trusted admin do so), run npm install and the smoke tests in a sandboxed environment, back up SOUL.md and OpenClaw config before enabling persona sync, and disable/require approval for the companion_tick scheduler or any automatic proactive features until you’ve verified behavior.
- If unsure: install in a non-production gateway, or request the publisher to clarify the metadata mismatches and provide an explicit security note about SOUL.md writes and scheduled companion behavior.
Capability Analysis
Type: OpenClaw Skill
Name: openclaw-tavern
Version: 0.1.0
The skill bundle provides a highly complex roleplay system with several high-risk capabilities that, while plausibly necessary for its stated purpose, create a significant security surface. Key concerns include the ability to programmatically modify the agent's core instruction file (SOUL.md) via 'src/openclaw/agentPersona.js', and broad filesystem access in 'src/openclaw/register.js' and 'src/core/commandRouter.js' for importing assets from local paths or remote URLs. Additionally, 'src/openclaw/register.js' executes external binaries (ffmpeg) via 'child_process.execFile' for media transcoding. While no explicit evidence of intentional data exfiltration was found, the plugin's ability to read environment variables and local configuration files containing API keys (OpenAI/Gemini) makes it a high-privilege component that should be monitored.
Capability Assessment
Purpose & Capability
Functionality in source (imports, session manager, TTS/image, long memory, companion) matches the stated purpose. However there are metadata mismatches: the top-level registry claimed no required env/install, while SKILL.md frontmatter declares an install step (npm install) and requires OPENCLAW_RP_LOCALE. The package is not instruction-only (many source files exist) despite an earlier note saying 'No install spec'. These inconsistencies should be reconciled.
Instruction Scope
Runtime instructions and code read and write OpenClaw config and user-facing files (e.g., ~/.openclaw/provider.json, SOUL.md) and register hooks (message_received, before_prompt_build, llm_output). The plugin exposes a `/rp sync-agent-persona` that writes the current RP character into the agent SOUL.md (system persona), and `/rp restore-agent-persona` to revert. The companion feature can be scheduled to proactively message users via hooks. These are powerful operations (modifying agent system prompts and initiating messages) and expand scope beyond simple import/response behavior; they are legitimate for this plugin's goals but sensitive and worth explicit operator approval.
Install Mechanism
SKILL.md requests running `npm install` after clone (normal for Node.js plugins). package.json uses peerDependencies (optional better-sqlite3, js-tiktoken) so npm install will not pull unexpected third-party runtime dependencies beyond those declared. No remote arbitrary binary downloads or obscure extract-from-URL steps were found. That said, the registry metadata initially claiming 'no install spec' conflicts with SKILL.md's install entry.
Credentials
The plugin legitimately uses environment variables for provider resolution (OPENCLAW_RP_LOCALE, OPENAI_*, GEMINI_*, TELEGRAM_BOT_TOKEN in examples). The registry initially listed no env requirements but SKILL.md notes OPENCLAW_RP_LOCALE; other provider envs are optional. Access to provider credentials (OPENAI_*/GEMINI_*) is reasonable for image/embedding/tts providers but is sensitive—operators should avoid supplying unrelated high-privilege credentials to the plugin. The plugin can read user config files under ~/.openclaw, which is expected but gives it visibility into gateway config.
Persistence & Privilege
The plugin persists session data and embeddings (SQLite or in-memory), can modify plugin configuration entries and write into agent-managed files (SOUL.md), and registers hooks that enable proactive, scheduled outbound messages (companion_tick). While these behaviors are part of its feature set, they grant the plugin persistent presence and the ability to modify agent/system prompts and initiate messages — a meaningful privilege that should be explicitly authorized and monitored.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install openclaw-tavern - After installation, invoke the skill by name or use
/openclaw-tavern - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
OpenClaw RP Plugin 0.1.0 — Initial Release
- SillyTavern-compatible RP extension for OpenClaw with support for character cards, presets, and lorebooks (PNG/JSON import).
- Session lifecycle management with long memory, auto-summarization, and SQLite persistence (supports in-memory fallback).
- Multimodal output features: text-to-speech (`/rp speak`) and image generation (`/rp image`), including agent tool support.
- Generative Agents-style Companion system for proactive engagement and memory-based reflection.
- Full `/rp` command suite for asset management, session control, and companion interactions.
- Multilingual support (English/Chinese), easy installation via ClawHub or Git, and flexible configuration options.
Metadata
Frequently Asked Questions
What is OpenClaw SillyTavern Plugin?
SillyTavern-compatible roleplay plugin with character cards, long memory, multimodal output (TTS/image), and Generative-Agents-style companion. It is an AI Agent Skill for Claude Code / OpenClaw, with 275 downloads so far.
How do I install OpenClaw SillyTavern Plugin?
Run "/install openclaw-tavern" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is OpenClaw SillyTavern Plugin free?
Yes, OpenClaw SillyTavern Plugin is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does OpenClaw SillyTavern Plugin support?
OpenClaw SillyTavern Plugin is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created OpenClaw SillyTavern Plugin?
It is built and maintained by garfeildma (@garfeildma); the current version is v0.1.0.
More Skills