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 yogsoth-ai/stress-test --skill multiagent-debategit clone --depth 1 https://github.com/yogsoth-ai/stress-testWrote 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/yogsoth-ai/stress-test/multiagent-debate)<a href="https://agentmods.dev/skills/yogsoth-ai/stress-test/multiagent-debate"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/stress-test/multiagent-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/yogsoth-ai/stress-test/multiagent-debate"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/stress-test/multiagent-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 | $0.00053 | $0.01290 |
| Opus 5 | $0.00026 | $0.00645 |
| Sonnet 5 | $0.00011 | $0.00258 |
| Haiku 4.5 | $0.00005 | $0.00129 |
Grade A, and why
multiagent-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 7d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Agent Debate Campaign
Core question: Can this artifact survive structured adversarial debate?
Methodology Sources
- Irving et al. (2018) — AI Safety via Debate
- Du et al. (2023) — Society of Mind multi-agent sharing
- Liang et al. (2023) — MAD (Multi-Agent Debate)
- Toulmin (1958) — Argumentation model (claim, ground, warrant, backing, qualifier, rebuttal)
- D3 framework — Deliberate, Debate, Decide
Strategy Routing
| Artifact Type | Primary Strategy | Fallback Strategy |
|---|---|---|
| hypothesis, claim | critic-defender-judge | adversarial-escalation |
| research-question | multi-perspective-panel | society-of-mind |
| idea, approach | society-of-mind | courtroom-structured |
| experiment-design | courtroom-structured | critic-defender-judge |
| gap | multi-perspective-panel | adversarial-escalation |
Budget Table
| Parameter | S (Quick) | M (Standard) | L (Deep) |
|---|---|---|---|
| Debate rounds | 4 | 8 | 12 |
| Participating agents | 3 | 5 | 8 |
| Coverage dimensions | 3 | 5 | 7 |
| External evidence searches | 2 | 5 | 10 |
Tactics
- dialectical-escalation — Progressive pressure escalation based on confidence thresholds
- perspective-rotation — Sequential perspective evaluation with divergence aggregation
- evidence-tournament — Evidence gathering, cross-examination, and quality judgment
Context Management
Each subagent operates in isolated context. The debate-architect designs structure before execution. Transcripts are passed between rounds via structured markdown. Saturation detection terminates when novelty drops below threshold.
Output
Produces DebateVerdict containing: survival assessment, key vulnerabilities, confidence score, debate transcript summary, and recommended mitigations.
Available Strategies
Optional, no fixed order; the final leaf is always a sop.
| Strategy | When to use |
|---|---|
| adversarial-escalation | Strategy: Progressive pressure escalation — starts with surface-level challenges and escalates to fundamental assumption attacks based on defender confidence decay. |
| courtroom-structured | Strategy: Legal adversarial structure — prosecution presents case, defense responds, evidence is cross-examined, judge delivers verdict. Emphasizes evidence quality and procedural rigor. |
| critic-defender-judge | Strategy: Classic triangular debate — Critic attacks, Defender responds, Judge adjudicates. Based on Irving AI Safety via Debate with Toulmin argumentation structure. |
| multi-perspective-panel | Strategy: Multi-stakeholder review panel — diverse expert perspectives evaluate artifact simultaneously, then synthesize through structured deliberation. |
| society-of-mind | Strategy: Multi-agent collaborative debate based on Du et al. Society of Mind. Agents share perspectives iteratively until convergence or divergence is detected. |
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.
- 7d ago First seen · 120 lines · 53 tokens per session scan A 41095b8a952d
multiagent-debate is a skill published in the GitHub repository yogsoth-ai/stress-test (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 53 tokens to every session and 1,290 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
tournament-judge
Runs a domain-neutral, evidence-based tournament in which independent candidates are reviewed, anonymized, and scored by a blind judge against a rubric fixed before judging. Use when comparing competing plans, designs, implementations, documents, tools, vendors, strategies, or other substantial options; when the user…
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
oma-scholar
Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…
browser_cdp
A health check for Python code that produces a score, letter grade, and measures of issues such as complexity, duplication, dead code, dependencies, and architecture.
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.
creating-skills
Guide for creating Claude Code skills following Anthropic's official best practices. Use when user wants to create a new skill, build a skill, write SKILL.md, update an existing skill, or needs skill creation guidelines. Provides structure, frontmatter fields, naming conventions, and new features like dynamic context…