Borrowing it
Nothing to install: this file belongs to Far-Se/tabame. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Far-Se/tabame/main/.agents/skills/tbm-plugin/SKILL.mdgit clone --depth 1 https://github.com/Far-Se/tabameWrote 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/far-se/tabame/tbm-plugin)<a href="https://agentmods.dev/skills/far-se/tabame/tbm-plugin"><img src="https://agentmods.dev/badge/skills/far-se/tabame/tbm-plugin/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/far-se/tabame/tbm-plugin"><img src="https://agentmods.dev/badge/skills/far-se/tabame/tbm-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00074 | $0.01912 |
| Opus 5.5 | $0.00030 | $0.00765 |
| Sonnet 5.5 | $0.00015 | $0.00382 |
| Haiku 4.5 | $0.00007 | $0.00191 |
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 18d 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.
The plugin is an ordinary process: HTTP (`requests`/`urllib`, or global `fetch` in Node 18+/Bun), filesystem, spawning tools. Read secrets from a `config.json` in the plugin folder (the CWD) or env vars – see `plugins/li How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tabame Launcher Plugin Authoring
Tabame's launcher is extensible with plugins: standalone scripts (Python, Node.js, or Bun) that Tabame runs as a long-lived child process when the user types the plugin's keyword. Communication is newline-delimited JSON over stdin/stdout – no SDK, no dependencies.
- Tabame → script (stdin): UI events (
init,query,select,action,close). - Script → Tabame (stdout): render frames – JSON objects that fully describe what the launcher shows right now.
The script is the source of truth for the UI: every time you want the launcher to display something different, you print a new render frame.
Authoritative references (read these)
The complete, authoritative protocol spec lives in the repo. Read it before writing non-trivial plugins – do not invent fields or message types not documented there:
- Full spec: skills/TABAME_PLUGIN_SKILL.md – every message type, render-frame field, item field, view type, icon name, and pattern.
- Working examples to copy from:
plugins/echo/– Python demo exercising list/grid/detail/preview + actions.plugins/linear/– Node.js plugin with an HTTP API andconfig.jsonsecrets.plugins/caniuse/– Node.js plugin with fetched data and detail views.
When a detail isn't covered below, consult the full spec rather than guessing.
Workflow for building a plugin
- Clarify the shape (only if unspecified): keyword, runtime, data source, what each item shows, what Enter does, what Ctrl+K actions to offer, and which view (list / grid / detail / preview pane).
- Pick a runtime the user has on
PATH:python,node(18+), orbun. Tabame bundles none. - Scaffold the folder with
plugin.json+ entry script. Start from the matching template in §15 of the full spec, or copy the closestplugins/plugin. - Implement the event loop (see contract below).
- Install & test: drop the folder in
%localappdata%\Tabame\plugins\<id>\, reopen the launcher (it rescans on every open – no restart), and type the keyword.
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.
- 18d ago Changed · +6 lines 15bb20e046bd
- 26d ago Changed f4864351a5ec
- 1mo ago First seen · 113 lines · 74 tokens per session scan A 0ed08a24a70d
tbm-plugin is a skill published in the GitHub repository Far-Se/tabame (373 stars, last pushed 3d ago), licensed MIT. It adds 74 tokens to every session and 1,912 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
shadcn-ui-flutter
A comprehensive Flutter UI library inspired by shadcn/ui. Provides high-quality, customizable, and accessible components including Buttons, Cards, Forms, and more. Use this skill when building Flutter UIs, implementing design systems, or needing specific component usage examples.
reverse-engineering-tools
Analyze supplied game binaries, protection components, drivers, dumps, or traces through reproducible disassembly, decompilation, debugging, diffing, and interface reconstruction.
skill-deployment
Use when deploying the shared agent skills via chezmoi, or fixing "not managed" errors.
hermes-cron-automations
Use when building a recurring automation on the Hermes box.
cleanup-code-inspections
Reduce technical debt and improve code quality by systematically resolving static analysis warnings.
codebase-review
Review an entire codebase for architecture, engineering health, and exploitable risk; generate a prioritized remediation plan, an evidence-anchored system knowledge document, or both.