crossframe-skill: Skill for Claude Code

.claude/skills/crossframe-promax/SKILL.md

crossframe-promax is a skill for Claude Code, Codex from xi-kari/crossframe-skill. It costs 52 tokens per session (4,798 once invoked), scanned A, original, MIT.

A named analysis workflow called CrossFrame ProMax that builds checked, structured reasoning records before producing a Chinese explanation. It uses source snapshots, claims, opposing checks, and verification reports.

In plain words
What is it for?
Use it only when explicitly invoking CrossFrame ProMax for a deep, evidence-structured analysis.
Why use it?
It provides a fixed process for checking complex reasoning and recording what was examined, challenged, and verified.

Skill for Claude CodeCodex

Written for Claude Code and Codex: installed under .claude/, but also agents/openai.yaml present. Also seen: mentions subagents; $skill-name invocation.

This is xi-kari/crossframe-skill's own configuration. It tells Claude Code and Codex how to work on crossframe-skill itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything crossframe-skill configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python skills/crossframe-promax/scripts/crossframe_promax_runtime.py init --repo <仓库根目录> --run-dir <新工件目录> --request <原始请求> --mode promax-artifact-run.

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/xi-kari/crossframe-skill/main/.claude/skills/crossframe-promax/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/xi-kari/crossframe-skill

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for crossframe-promax

README.md
[![agentmods](https://agentmods.dev/badge/skills/xi-kari/crossframe-skill/crossframe-promax/github.svg)](https://agentmods.dev/skills/xi-kari/crossframe-skill/crossframe-promax)
Your own site
<a href="https://agentmods.dev/skills/xi-kari/crossframe-skill/crossframe-promax"><img src="https://agentmods.dev/badge/skills/xi-kari/crossframe-skill/crossframe-promax/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.

agentmods 80×15 button for crossframe-promax

Your own site · 80×15
<a href="https://agentmods.dev/skills/xi-kari/crossframe-skill/crossframe-promax"><img src="https://agentmods.dev/badge/skills/xi-kari/crossframe-skill/crossframe-promax.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,798 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.04798
Opus 5 $0.00026 $0.02399
Sonnet 5 $0.00010 $0.00960
Haiku 4.5 $0.00005 $0.00480

Measured 9d ago against content hash 1d59e92cceb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

crossframe-promax 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 9d 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.

.claude/skills/crossframe-promax/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CrossFrame ProMax

把本 skill 作为 v8-only、artifact-first 的结构推演运行时。先建立可验证工件,再交付完整中文解释;以固定源快照、概念闭包、命题路径、检索台账、反方攻击、立场锁和验证报告约束模型风格差异。不要声称拥有无限算力或已经穷尽现实;只声明验证器能够证明的预算内饱和。

激活边界

  • PROMAX-NAMED-ONLY:只接受 crossframe-promaxCrossFrame ProMax$crossframe-promax/crossframe-promax 四种明确点名。
  • 上述名称由宿主或上游路由器判定;泛化的“最大算力”“完整长文”“全尺度”“穷尽分析”等表达不构成上游触发。
  • PROMAX-PRIORITY-OVER-MAX:同时点名 ProMax 与 Max 时,由宿主或上游路由器选择 ProMax 并完成冲突记录;进入本 skill 后不再复判。
  • PROMAX-NO-FALLBACK-TO-MAX:进入 ProMax 后禁止回退到 Max,不得把失败、材料不足或能力缺口改写为回退理由。

宿主已经加载本 skill,就表示显式点名和优先级选择已经完成。不得再次解析用户请求来决定是否退出,不得要求用户重复技能名,也不得因为命令适配器只传入问题正文而拒绝运行;直接进入 ProMax 初始化。本次运行不得切换到 brief、快速答复、自选轻量档,也不得加载任何 sibling knowledge。唯一理论知识面是本 skill 随附的 v8 源快照、注册表、合同和路由;外部材料只能校准事实与案例,不能改写 v8 定义。

不可绕过的输出边界

  • 默认执行 promax-artifact-run,不是聊天短答。
  • 只有全部严格门通过后才输出 promax-complete
  • 只有源不可访问、文件系统不可写、必需工具被禁止、用户中止或更高优先级安全边界阻断时,才使用 promax-blocked/progress
  • promax-artifact-incomplete:<reason> 只能由验证结果产生,不是模型自选档位。
  • PROMAX-NO-TEST-FIXTURE-RUNTIMEcrossframe_promax_fixture_factory.pytests/fixtures/promax-runtime 只服务仓库 TDD;真实运行禁止执行、复制、改名或派生其中的测试夹具,promax-fixture-* 也不是可交付的生产 run ID。
  • 禁止先锁定与用户请求无关的通用冻结工件,再追加主题附录来伪装请求绑定;通用冻结工件 + 主题附录不是同一轮结构推演。
  • PROMAX-NO-EARLY-FINALinit/P0 后禁止给出最终聊天、完成或未完成状态;必须继续推进可执行阶段,不能把“尚未运行验证器”改写成 promax-artifact-incomplete:validation-failed
  • PROMAX-MATERIALIZE-BEFORE-INCOMPLETE:文件与相应能力可用时,先生成所有可生成的 P1–P10 工件,尤其是完整 P10 长文与控制面,再运行验证器;某项能力缺失只限制依赖该能力的内容,不许可跳过其余可生成工件。
  • 材料不足时继续做条件分支、竞争机制、敏感性分析、当前排序和补证设计;降低结论强度,不取消分析。
  • PROMAX-STANCE-NEUTRAL-KEY:P5 前先冻结对象、只去除裁决指令而保留实质性量词的待检验命题、时间窗和独立证据截止点;语义键只由前三者计算。中心 claim ID 只要求在本轮稳定,成对检验比较语义键、命题关系和语义散列,禁止用相同标签掩盖相反结论。
  • PROMAX-LOW-INFORMATION-RANKING:只有一句立场、没有个案事实且没有改变选择的可核验证据时,具体方案仍保留各自稳定 ID,但 v8 option_kind 投影固定为 probe_action > active_action > maintain_status_quo > delayed_action > exit_or_transfer > no_actionPROMAX-HOUSE-POLICY-NOT-V8:这是 ProMax 的保守低信息裁决偏好,不是 v8 概念或由 v8 自动推出的结论;有证据的偏离必须解析到检索台账。每次建议都必须生成 selection_review_wrapper,逐字标为 promax_machine_verification_wrapper_not_v8_source_schema,闭合 N1—N5、冲突/异议、PF、受影响与低权力位置、管辖审查边界、O1—O4、least-harm、proportionality 以及完整 option × dimension 证据支持;不得把这个 ProMax 校验包装层伪装成 v8 原生 schema 或完整原子 J 授权。
  • 不公开隐藏思维链、英文自我规划、工具试错或逐步私有推理。用事实边界、v8 锚点、概念处置、claim-path、反证、判断理由、撤回条件和验证报告提供可审计性。
  • 不用术语数量、篇幅、marker 或概念 ID 堆积冒充理解。每个概念和案例都必须承担可验证的结构作用。

Read the full file on GitHub · 170 lines

Files

What ships with it

60 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.

Changes

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.

  1. 9d ago First seen · 170 lines · 52 tokens per session scan A 1d59e92cceb0

Subscribe to this mod's changes

crossframe-promax is a skill published in the GitHub repository xi-kari/crossframe-skill (18 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 4,798 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 2026-08-30.

Related

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…

stannum2/letstalk-master · 81 tokens

polar-billing

This skill should be used when working on Polar billing system, Stripe integration, subscription lifecycle, checkout flows, or benefit provisioning.

fcakyon/claude-codex-settings · 29 tokens

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".

fcakyon/claude-codex-settings · 63 tokens

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…

fcakyon/claude-codex-settings · 112 tokens

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…

fcakyon/claude-codex-settings · 122 tokens

mongodb-schema-design

MongoDB schema design patterns and anti-patterns. Use when designing data models, reviewing schemas, migrating from SQL, or troubleshooting performance issues caused by schema problems. Triggers on "design schema", "embed vs reference", "MongoDB data model", "schema review", "unbounded arrays", "one-to-many", "tree…

fcakyon/claude-codex-settings · 127 tokens