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.
curl -O https://raw.githubusercontent.com/AytuncYildizli/yapitalism/main/.agents/skills/superset-operator/SKILL.mdgit clone --depth 1 https://github.com/AytuncYildizli/yapitalismWrote 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/aytuncyildizli/yapitalism/superset-operator)<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.
<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>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 | $0.00103 | $0.03470 |
| Opus 5 | $0.00051 | $0.01735 |
| Sonnet 5 | $0.00021 | $0.00694 |
| Haiku 4.5 | $0.00010 | $0.00347 |
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.
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 — 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
supersetfor workspaces, projects, and creating/closing agents. Useyapitalismfor reading panes and for every send. See the section below.
Yapitalism terminal contract (all sends go here)
- Send only through
yapitalism.pane_send. Superset'sterminals_sendreturns{terminalId, submitted}and nothing else — no phase, no delivery id, no await tool — so a send routed through it can never be proven.submitted:truemeans a key was pressed. It is not evidence an agent read anything, and it must never be spoken as success. - Read with
panes_listandpane_read.panes_listcovers every backend at once, including Superset terminals, so prefer it overterminals_listwhen 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_listreturnserrorsalongsidepanes. A backend that failed is not the same as a backend with nothing in it. Never say "no terminals" whileerrorsis 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
runtimebefore sending. Onlycodex,claude, andkimiare agents. Sending to a pane whose runtime isshelltypes 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.
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.
- 12d ago First seen · 119 lines · 103 tokens per session scan A e98fee2fb77b
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.
Other skills, from other repositories
delivering-morning-briefings
Weather + news morning briefing: fetch live weather and headlines, compose a plain-text briefing, deliver it. Multi-step; load before acting.
daily-digest
Build and deliver the daily activity digest, covering GitHub activity, AI Gateway spend, visitor counts, CLI usage, and a short news section. Load this when the morning digest schedule fires, or when someone asks for a digest, a daily recap, or "what happened" over a recent period, on any channel.
k8s-incident-triage
Read-only Kubernetes incident triage using kubectl. Accepts natural language or structured input. Produces root-cause hypotheses, evidence, and next-step commands.
Contacts
A contact-management skill for finding, adding, changing, and removing people in an address book.
Reminders
A skill for creating timed reminders in a task or reminder list.
Clipboard
A skill for reading and writing the computer’s system clipboard, the temporary place used for copied text.