yapitalism: Skill for Claude Code

.agents/skills/superset-operator/SKILL.md

superset-operator is a skill for Claude Code, Codex from AytuncYildizli/yapitalism. It costs 103 tokens per session (3,470 once invoked), scanned A, original, MIT.

A voice-oriented control guide for operating terminal-based coding agents through Superset workspaces and projects on a Mac Studio.

In plain words
What is it for?
Use it to operate coding agents remotely by voice, manage their workspaces and projects, create or close agents, and send verified terminal input.
Why use it?
It provides strict routing rules for finding the right workspace, reading terminal panes, sending commands, and confirming that messages were delivered.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions Codex.

This is AytuncYildizli/yapitalism's own configuration. It tells Claude Code and Codex how to work on yapitalism itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything yapitalism configures →

Reuse

Borrowing it

Nothing to install: this file belongs to AytuncYildizli/yapitalism. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/AytuncYildizli/yapitalism/main/.agents/skills/superset-operator/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/AytuncYildizli/yapitalism

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 superset-operator

README.md
[![agentmods](https://agentmods.dev/badge/skills/aytuncyildizli/yapitalism/superset-operator/github.svg)](https://agentmods.dev/skills/aytuncyildizli/yapitalism/superset-operator)
Your own site
<a href="https://agentmods.dev/skills/aytuncyildizli/yapitalism/superset-operator"><img src="https://agentmods.dev/badge/skills/aytuncyildizli/yapitalism/superset-operator/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.

agentmods 80×15 button for superset-operator

Your own site · 80×15
<a href="https://agentmods.dev/skills/aytuncyildizli/yapitalism/superset-operator"><img src="https://agentmods.dev/badge/skills/aytuncyildizli/yapitalism/superset-operator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,470 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00103 $0.03470
Opus 5 $0.00051 $0.01735
Sonnet 5 $0.00021 $0.00694
Haiku 4.5 $0.00010 $0.00347

Measured 12d ago against content hash e98fee2fb77b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

superset-operator 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 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (sync.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/superset-operator/SKILL.md · 119 lines

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.

Superset Operator

Two MCP servers cover this together. yapitalism runs locally and owns reading panes and every send, because it is the only one that returns a receipt. superset owns workspaces, projects, and agent lifecycle.

Hard routing

  • Do not use Browser, Chrome, Computer Use, shell scraping, or filesystem guessing to operate Superset.
  • Do not reach for a third MCP server, or for a shell, to do what these two cover.
  • Start by resolving the Mac Studio host through hosts_list, then resolve the target workspace/session from live Superset state.
  • If the user's target is ambiguous, list the closest matching live workspaces/sessions and ask which one.
  • Two MCP servers are enabled and they are not interchangeable. Use superset for workspaces, projects, and creating/closing agents. Use yapitalism for reading panes and for every send. See the section below.

Yapitalism terminal contract (all sends go here)

  • Send only through yapitalism.pane_send. Superset's terminals_send returns {terminalId, submitted} and nothing else — no phase, no delivery id, no await tool — so a send routed through it can never be proven. submitted:true means a key was pressed. It is not evidence an agent read anything, and it must never be spoken as success.
  • Read with panes_list and pane_read. panes_list covers every backend at once, including Superset terminals, so prefer it over terminals_list when the user asks what is running.
  • Target ids are namespaced — tmux:%0, superset:<uuid>. Pass them back verbatim. Never invent one, never strip the prefix.
  • panes_list returns errors alongside panes. A backend that failed is not the same as a backend with nothing in it. Never say "no terminals" while errors is non-empty; say which backend could not be reached.
  • Report the whole list, compactly — never a subset presented as the answer. With many panes, "compact" means totals and a breakdown, not one example. Say the count, then group by runtime, then offer to narrow: "23 pane var — 9 claude, 6 codex, 3 kimi, 5 shell. Hangisini istersin?" Listing only one backend, or only the first few, misleads the user into thinking that is everything. If the user then asks "what about Superset?", that means the first answer was wrong; do not defend it, just give the full picture.
  • Check runtime before sending. Only codex, claude, and kimi are agents. Sending to a pane whose runtime is shell types the text into a shell prompt, which executes it — confirm explicitly with the user before doing that, and say plainly that it is a shell, not an agent.

Read the full file on GitHub · 119 lines

Files

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.

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. 12d ago First seen · 119 lines · 103 tokens per session scan A e98fee2fb77b

Subscribe to this mod's changes

superset-operator is a skill published in the GitHub repository AytuncYildizli/yapitalism (7 stars, last pushed 4d ago), licensed MIT. It adds 103 tokens to every session and 3,470 once invoked, about $0.0005 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 2026-08-31.