tbm-plugin

tbm-plugin is a skill for Claude Code, Codex from Far-Se/tabame. It costs 74 tokens per session (23,460 once invoked), scanned A, original, MIT.

A guide for building Tabame launcher plugins as external Python, Node.js, or Bun scripts. The scripts communicate with the launcher by sending newline-separated JSON messages.

In plain words
What is it for?
It helps create launcher keywords, handle queries and selections, perform actions, and render purpose-built plugin views.
Why use it?
It explains how a long-running script receives user actions and describes the launcher screen without inventing undocumented message types.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps create launcher keywords, handle queries and selections, perform actions, and render purpose-built plugin views.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/far-se/tabame/tabame_plugin
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.

Any agent
npx skills add Far-Se/tabame --skill tabame_plugin
Clone the repo
git clone --depth 1 https://github.com/Far-Se/tabame

Made for: Claude Code, Codex.

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 tbm-plugin

README.md
[![agentmods](https://agentmods.dev/badge/skills/far-se/tabame/tabame_plugin.svg)](https://agentmods.dev/skills/far-se/tabame/tabame_plugin)
Your own site
<a href="https://agentmods.dev/skills/far-se/tabame/tabame_plugin"><img src="https://agentmods.dev/badge/skills/far-se/tabame/tabame_plugin.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 23,460 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00074 $0.23460
Opus 5 $0.00037 $0.11730
Sonnet 5 $0.00015 $0.04692
Haiku 4.5 $0.00007 $0.02346

Measured 3d ago against content hash 8be142b83cda, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

tbm-plugin scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**HTTP / APIs** — use the runtime's HTTP client (`requests`/`urllib` in Python,
skills/TABAME_PLUGIN_SKILL.md · 1,755 lines

How it starts

The opening of the file, as written. The whole thing — 1,755 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tabame Launcher Plugin — Authoring Skill

If you're the AI reading this: treat everything below as authoritative. Do not invent fields or message types that aren't documented here. Choose the view from the user's task and the shape of the data. Do not default to a list + preview merely because the smoke-test templates use it. A substantial plugin should feel like a small, navigable application made of purpose-built pages, not a command list with every capability hidden in Ctrl+K.


1. What a plugin is

Tabame's launcher can be extended with plugins — external scripts written in Python, Node.js, or Bun. A plugin is a normal script that Tabame launches as a long-running child process when the user types the plugin's keyword in the launcher.

The conversation is newline-delimited JSON over stdin/stdout:

  • Tabame → your script (stdin): UI events — the user's query text, selection changes, actions, and a shutdown signal.
  • Your script → Tabame (stdout): render frames — JSON objects that fully describe what the launcher should display right now.

Your script is the source of truth for the UI. Every time you want the launcher to show something different, you print a new render frame. The process stays alive the whole time the plugin's keyword owns the query, and is shut down when the user leaves it.

There is no SDK — just read lines from stdin and print lines to stdout. No third-party packages are needed for the protocol itself; if your plugin's own logic wants extra libraries, see §4.1.


2. Quick start (minimal protocol example)

A plugin is a folder with a plugin.json and a script. Minimal Python plugin that echoes the query as a single-item list. This only demonstrates the wire protocol; it is not a UX template for a real plugin:

plugin.json

{
  "name": "Hello",
  "category": "Utilities",
  "keyword": "hi",
  "runtime": "python",
  "version": "1.0.0",
  "entry": "main.py"
}

main.py

Read the full file on GitHub · 1,755 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 · 1,755 lines · 74 tokens per session scan A 8be142b83cda

Subscribe to this mod's changes

tbm-plugin is a skill published in the GitHub repository Far-Se/tabame (364 stars, last pushed 3d ago), licensed MIT. It adds 74 tokens to every session and 23,460 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.