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 skills/lfyxhappy/lfcode/tavern-managementnpx skills add lfyxhappy/lfcode --skill tavern-managementgit clone --depth 1 https://github.com/lfyxhappy/lfcodeWrote 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/lfyxhappy/lfcode/tavern-management)<a href="https://agentmods.dev/skills/lfyxhappy/lfcode/tavern-management"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/tavern-management.svg" alt="Measured on agentmods" 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 | $0.00043 | $0.00842 |
| Opus 5 | $0.00022 | $0.00421 |
| Sonnet 5 | $0.00009 | $0.00168 |
| Haiku 4.5 | $0.00004 | $0.00084 |
Grade A, and why
tavern-management 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 today.
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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lfcode Tavern Management
Scope
Use this skill for Lfcode Tavern character cards, worldbooks, and the Tavern plugin itself. Tavern accepts Character Card V2 JSON and PNG cards carrying chara metadata in tEXt, zTXt, or iTXt PNG chunks. Treat a PNG card as both an image and structured character data; do not flatten it to a plain image.
The original SillyTavern migration vault is read-only. Importing or translating creates a new Lfcode Tavern copy and must never overwrite the user's source card, source worldbook, or migration archive.
Plugin Lifecycle
Use plugin_manage for plugin library work.
- Inspect first with
plugin_managelistorinspect. - For a new plugin package, call
import_preview; report the reviewed package details before any install. - Only call
import_commit,enable,disable, oruninstallafter the user has explicitly approved that change. Give the tool a concise reason. - Do not use shell deletion or edit the plugin registry directly. Disable or uninstalling Tavern must not be used as a shortcut to delete Tavern conversations or private data.
Import Workflow
- Open Tavern, then use
角色or世界书management and choose the import action. - Character cards may be
.jsonor.png; worldbooks are JSON files. The app copies the selected file into Tavern private storage before creating its index entry. - Preserve card data such as
data.character_book, alternate greetings, tags, and template variables. A card's embedded worldbook should stay associated with that imported character. - Verify the imported character name, opening message, and linked worldbook before creating a conversation.
Character Card Translation
- Work from a user-selected source file or a new exported copy. Do not modify the original in place.
- Extract JSON from either format with the script in this skill directory:
node scripts/tavern-card.mjs read "input-card.png" > card.json
- Translate
data.name, description, personality, scenario, first message, example dialogue, creator notes, system prompt, post-history instructions, alternate greetings, tags, and embeddedcharacter_booktext. Keep{{char}},{{user}},<START>, Markdown, regular expressions, JSON keys, and formatting intact. If V1 mirror fields exist at the top level, keep them synchronized withdata. - For embedded worldbook keys, preserve the original trigger and append a Chinese trigger rather than replacing it. Translate entry content, comments, names, and descriptions.
- For a PNG source, write a separate PNG that preserves all image chunks and replaces only the
charametadata:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today First seen · 59 lines · 43 tokens per session scan A ac317d290f1e
tavern-management is a skill published in the GitHub repository lfyxhappy/lfcode (2 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 842 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 2026-09-05.
Other skills, from other repositories
Review a GitHub PR (via gh)
Review a specific GitHub pull request with gh — fetch the diff, fan out reviewers, consolidate, and optionally post the review. Requires the gh CLI or the GitHub MCP server.
Best of N (parallel attempts)
Delegate N parallel subagents on the same task, then pick the best result.
Design doc (write -> review loop)
Draft a design document and iterate writer/reviewer subagents until consensus.
Implement (multi-agent loop)
Orchestrate an implement -> review -> fix loop with subagents until reviewers sign off.
PR babysit (watch & drive to green)
Watch a pull request and delegate fixes until CI is green and reviews are addressed. Requires the GitHub MCP server or gh.
Review changes (multi-agent)
Delegate read-only reviewers over the local changes/branch and consolidate findings.