Borrowing it
Nothing to install: this file belongs to xi-kari/crossframe-skill. 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/xi-kari/crossframe-skill/main/.claude/skills/crossframe-debate/SKILL.mdgit clone --depth 1 https://github.com/xi-kari/crossframe-skillWrote 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/xi-kari/crossframe-skill/crossframe-debate)<a href="https://agentmods.dev/skills/xi-kari/crossframe-skill/crossframe-debate"><img src="https://agentmods.dev/badge/skills/xi-kari/crossframe-skill/crossframe-debate.svg" alt="Measured on agentmods" 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 | $0.00031 | $0.01671 |
| Opus 5 | $0.00015 | $0.00835 |
| Sonnet 5 | $0.00006 | $0.00334 |
| Haiku 4.5 | $0.00003 | $0.00167 |
Grade A, and why
crossframe-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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CrossFrame Debate
本 skill 不独立触发。 所有 CrossFrame 任务统一从
crossframe-suite入口调度。用户无需直接调用本 skill；suite 根据路由规则在需要时自动加载。
如果命题论证之后要写文章、公共评论、读书笔记或案例沉淀，先读取 ../crossframe-suite/SKILL.md 做总调度；本 skill 只负责命题拆解、正反结构、证据要求和撤回条件。
crossframe-debate 是 crossframe 的平行轻入口，用于把一个命题拆成可检验论证，而不是帮助某一方赢辩论。
中文为权威语义；英文只用于 skill id、文件名和接口说明。遇到中英文理解冲突时，以中文术语和中文判断为准。
轻入口规则
每次触发后，先读取 canonical skill 和路由图，不复制 CrossFrame 全文：
- 读取
../crossframe/SKILL.md。 - 读取
../crossframe/references/read-routing-map.md。 - 如果命题触发高责任、公共制度、亲密关系、长期演化、框架治理、AI 现实验证、弱信号/不透明、无法退出、工具化、隐喻/来源透明或文章输出，必须追加读取
../crossframe/references/continuity-bundles.md，并按需使用../crossframe/worksheets/source-continuity-check.md；未完成联读时只能降档。 - 复用
../crossframe/templates/read-state-capsule.md规定的v5-read-state-capsule，并在高责任、公共、AI/过程性产物、生命周期、无法退出主体或文章输出场景执行../crossframe/worksheets/source-anchor-integrity-check.md。如果胶囊缺失，回到../crossframe/SKILL.md补齐；本 skill 不重新发明源路由。
- 若本 skill 产生新的中心命题、机制句、高风险概念判断、公共定性、行动建议、案例复用判断、组织处置建议或可成文材料，必须把这些内容作为
claim ledger delta交回../crossframe/templates/claim-ledger.md与../crossframe/worksheets/claim-ledger-check.md。本 skill 不得新增未登记判断；若无法登记claim_id、判断档位、行动上限、撤回条件和发布边界，只能删除、降档，或标为“本文推断 / 表达转译 / 外部思想映射”。
- 读取本目录的
protocols/debate-protocol.md。 - 读取
templates/debate-analysis-output.md。 - 按需读取
references/debate-quality-gates.md和references/debate-failure-patterns.md。
按命题类型追加 canonical 路由：
- 公共议题、平台治理、政策、机构、真实人物或组织：按路由图进入公共制度、强判断、高责任、证据成本或命题验证材料；涉及最新事实时必须查源或降档。
- 关系、家庭、照护、边界、解释劳动：按路由图进入亲密关系、疗愈转移、责任链或爱/开放行动相关材料。
- 哲学、意义、第一因、虚无主义、价值命题：按路由图进入概念解释、开放断言和框架边界材料。
- 处分、名誉、权利、资格、资源、公开指控：必须进入命题验证和高责任路由；未完成验证只能作为开放断言或待核验命题。
默认任务
收到命题后，默认输出：
- 命题重写：把口号、情绪或价值表态改写为可检验命题。
- 正方结构：正方最好版本，不稻草人化。
- 反方结构：反方最好版本，不把反方写成愚蠢或恶意。
- 隐藏前提：事实前提、因果前提、价值前提、尺度前提、责任前提。
- 证据要求：当前证据、缺失证据、高成本证据、不可用证据。
- 最强反驳：每方必须面对的 strongest objection。
- 反向条件：哪些事实出现时，原命题要降档、改写或转向。
- 撤回条件：哪些证据足以撤回本判断。
- 更稳表达：把强硬结论改写为开放断言、条件判断或待核验命题。
工作流程
- 界定命题对象：对象、尺度、时间窗口、影响对象、判断档位。
- 判断命题类型：公共议题、关系命题、组织命题、哲学命题、强判断、表达修辞或混合命题。
- 拆出待证内容：这个命题到底需要证明什么，哪些只是情绪、价值偏好或修辞。
- 生成正反双方最好版本：先 steelman，再批评；不允许稻草人。
- 列出隐藏前提：事实、因果、价值、尺度、责任链和可操作性前提。
- 设定证据门槛：什么材料能支持、削弱、推翻、无法证明本命题。
- 写反向条件和撤回条件：没有撤回条件的命题不能作为合格结论。
- 输出更稳表达：让结论可检验、可降档、可被新事实修改。
What ships with it
10 files 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.
- agents/openai.yaml 431 B
- evals/crossframe-debate-smoke-tests.md 3.9 KB
- examples/failure-samples.md 1.1 KB
- examples/philosophical-proposition-case.md 1.3 KB
- examples/public-proposition-case.md 1.3 KB
- examples/relationship-proposition-case.md 1.3 KB
- protocols/debate-protocol.md 4.2 KB
- references/debate-failure-patterns.md 1.7 KB
- references/debate-quality-gates.md 1.9 KB
- templates/debate-analysis-output.md 1.7 KB
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 · 95 lines · 31 tokens per session scan A b81e1e5c351e
crossframe-debate is a skill published in the GitHub repository xi-kari/crossframe-skill (18 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 1,671 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
personalize-ai-assistant
Build or update privacy-first AI-assistant configuration and reusable preference skills for Codex, Claude Code, Cursor, Gemini CLI, and similar tools. Use when the user provides explicit preferences, existing config files, example rules, or asks to optimize AGENTS.md, CLAUDE.md, assistant rules, memory files, or…
polar-billing
This skill should be used when working on Polar billing system, Stripe integration, subscription lifecycle, checkout flows, or benefit provisioning.
simplify
This skill should be used when the user asks to "simplify", "clean up the diff", "run simplify", "simplify the changes", "review changed code for cleanup", explicitly invokes "/simplify", or asks to "commit without simplify", "skip simplify for this commit", or "commit this but skip simplify". Reviews changed code…
dokploy-deploy
This skill should be used when user asks to "deploy with Dokploy", "use Dokploy Cloud", "manage self-hosted Dokploy", "deploy Docker Compose on Dokploy", "manage Dokploy databases", "configure Dokploy domains", or "look up Dokploy CLI commands".
ultralytics-platform
This skill should be used when user asks to "upload my model to Ultralytics Platform", "push this run to the platform", "upload a dataset to platform", "download a dataset from platform", "search platform datasets", "start cloud training", "train on platform GPUs", "export a model on platform", "deploy a model…
mongodb-connection
Optimize MongoDB client connection configuration (pools, timeouts, patterns) for any supported driver language. Use this skill when working/updating/reviewing on functions that instantiate or configure a MongoDB client (eg, when calling connect()), configuring connection pools, troubleshooting connection errors…