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 skills add Kijun0708/llm-router-mcp --skill ensemble-debategit clone --depth 1 https://github.com/Kijun0708/llm-router-mcpWrote 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/kijun0708/llm-router-mcp/ensemble-debate)<a href="https://agentmods.dev/skills/kijun0708/llm-router-mcp/ensemble-debate"><img src="https://agentmods.dev/badge/skills/kijun0708/llm-router-mcp/ensemble-debate/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/kijun0708/llm-router-mcp/ensemble-debate"><img src="https://agentmods.dev/badge/skills/kijun0708/llm-router-mcp/ensemble-debate.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 | $0.00020 | $0.00286 |
| Opus 5 | $0.00010 | $0.00143 |
| Sonnet 5 | $0.00004 | $0.00057 |
| Haiku 4.5 | $0.00002 | $0.00029 |
Grade A, and why
ensemble-debate 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 8d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 8d ago First seen · 37 lines · 20 tokens per session scan A d888a550f69b
ensemble-debate is a skill published in the GitHub repository Kijun0708/llm-router-mcp (0 stars, last pushed 15d ago), with no licence file. It adds 20 tokens to every session and 286 once invoked, about $0.0001 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
special-grill
A questioning workflow for testing plans and decisions by mapping their choices, asking focused follow-up questions, checking facts, and waiting for agreement before acting.
roundtable
A guided discussion format in which a moderator brings several real people’s documented viewpoints into a structured debate about one topic.
debate-core
A set of rules for deciding when and how an analysis should be challenged by several independent reviewers. It uses different levels of debate depending on uncertainty, failures, conflicts, and the importance of the result.
stacker
Stack overlapping skills instead of picking one. When two or more installed skills or tools can do the same job (web scraping, search, code review, test generation, data extraction), run the best candidates in parallel on the same task, score their outputs, and merge them into one result that beats any single tool.…
codex-debate
Use when the user wants a debate, second opinion, adversarial review, or iterative discussion between Claude and Codex (the OpenAI CLI) about a spec, design, plan, document, position, refactoring, or codebase — the subject can be anything, technical or non-technical, e.g. "ask Codex", "debate this with Codex", "have…
multi-perspective-meeting
Turn a single Agent into a full multi-perspective meeting. The Agent auto-generates one role-played participant per perspective, runs a structured debate with cross-examination, converges to a conclusion, and outputs an HTML meeting-minutes file. Trigger on any research / analysis / discussion / decision request.