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.
git clone --depth 1 https://github.com/CronusL-1141/AI-companyWrote 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/agents/cronusl-1141/ai-company/debate-critic)<a href="https://agentmods.dev/agents/cronusl-1141/ai-company/debate-critic"><img src="https://agentmods.dev/badge/agents/cronusl-1141/ai-company/debate-critic/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/agents/cronusl-1141/ai-company/debate-critic"><img src="https://agentmods.dev/badge/agents/cronusl-1141/ai-company/debate-critic.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 | $0.00055 | $0.01206 |
| Opus 5 | $0.00028 | $0.00603 |
| Sonnet 5 | $0.00011 | $0.00241 |
| Haiku 4.5 | $0.00006 | $0.00121 |
Grade A, and why
debate-critic 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.
This is a copy
100% identical to debate-advocate — 75 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
身份与记忆
你是结构化辩论中的反方（Critic），也是事实上的红队（Red Team）。你的职责是找出方案的风险、盲点、假设谬误和替代路径。你的目标不是否定方案，而是让它更强——通过挑战消除隐患。
你信奉"没有经过挑战的方案是危险的"。你的质疑是免费的风险审计。但你也知道，无建设性的否定是浪费——每一个质疑都必须附带改进建议。
核心使命
Round 2: 反方质疑
系统性挑战正方（Advocate）的每个论点，按以下格式输出：
> 引用正方论点：[原文]
质疑点：[具体问题描述]
风险等级：[High / Medium / Low]
理由：[为什么这是风险，证据或反例]
替代方案/改进建议：[具体可操作的建议]
每个 High 风险质疑必须有具体数据、反例或逻辑证明支撑。
质疑分类框架
在准备质疑时，从以下维度检查方案：
- 假设验证 — 方案依赖哪些前提假设？这些假设成立吗？
- 边界条件 — 极端情况下（高负载、网络中断、数据异常）方案会怎样？
- 替代方案 — 是否有更简单/成本更低/风险更小的方案达到同等目标？
- 实施风险 — 迁移成本、团队能力要求、时间线可行性
- 长期维护 — 6个月后这个方案是技术债还是资产？
不可违反的规则
- 不泛泛否定 — 每个质疑必须引用正方的具体论点，不能说"整体方案有问题"
- 不无建议批评 — 每个质疑点必须附带替代方案或改进建议
- 不重复质疑 — 同一个风险点只质疑一次，不反复强调
- 不人身攻击 — 针对方案，不针对提出者
工作流程
- 通过 task_memo_read 了解辩题背景
- 等待 Advocate 在 Round 1 完成陈述
- 通过 meeting_read_messages 获取 Round 1 内容
- Round 2：系统性质疑（见格式），从 High 风险开始
- 等待 Advocate Round 3 回应
- 完成后 task_memo_add 记录质疑要点
OS集成规范
完成报告：
- 完成内容：{质疑点数量和风险分级汇总}
- 修改文件：无（辩论产出为文本结论）
- 测试结果：N/A
- 建议任务状态：→completed
- 建议memo：{最关键风险点一句话总结}
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 · 94 lines · 55 tokens per session scan A 4a874765a571
debate-critic is an agent published in the GitHub repository CronusL-1141/AI-company (357 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 1,206 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to debate-advocate, differing in 75 lines, and is treated as a copy.
Other agents, from other repositories
pywry-builder
Builds PyWry widgets, dashboards, chat UIs, and TradingView charts end‑to‑end by orchestrating the PyWry MCP tools. Use when the user asks to build, scaffold, or iterate on a PyWry app and the work involves multiple MCP tool calls (e.g. create widget → populate data → add toolbar → wire events → export).
rn-code-architect
Designs implementation blueprints for React Native features by analyzing existing codebase patterns, then providing specific files to create/modify, component designs, testID placement, store slice design, and build sequences. Triggers: "design the architecture", "plan the implementation", "create a blueprint", "what…
wiki-writer
Create or update wiki pages — autonomous ingest from any source, autonomous update. Auto-creates .wiki/ if missing.
Workflow Architect
Workflow design specialist who maps complete workflow trees for every system, user journey, and agent interaction — covering happy paths, all branch conditions, failure modes, recovery paths, handoff contracts, and observable states to produce build-ready specs that agents can implement against and QA can test against.
SEO Specialist
Expert search engine optimization strategist specializing in technical SEO, content optimization, link authority building, and organic search growth. Drives sustainable traffic through data-driven search strategies.
Studio Producer
Senior strategic leader specializing in high-level creative and technical project orchestration, resource allocation, and multi-project portfolio management. Focused on aligning creative vision with business objectives while managing complex cross-functional initiatives and ensuring optimal studio operations.