crossframe

crossframe is a skill for Claude Code, Codex from xi-kari/crossframe-skill. It costs 91 tokens per session (7,617 once invoked), scanned A, original, MIT.

A manually selected framework for structured diagnosis: examining facts, possible mechanisms, scale, responsibility, and uncertainty before reaching a conclusion.

In plain words
What is it for?
Diagnosing situations, testing claims, exploring possible outcomes, making carefully bounded judgments, and explaining the limits of the framework.
Why use it?
It gives complex relationship, organization, public, and other analysis requests a defined reasoning process instead of relying on an unstructured answer.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/xi-kari/crossframe-skill/crossframe
Any agent
npx skills add xi-kari/crossframe-skill --skill crossframe
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

README.md
[![agentmods](https://agentmods.dev/badge/skills/xi-kari/crossframe-skill/crossframe.svg)](https://agentmods.dev/skills/xi-kari/crossframe-skill/crossframe)
Your own site
<a href="https://agentmods.dev/skills/xi-kari/crossframe-skill/crossframe"><img src="https://agentmods.dev/badge/skills/xi-kari/crossframe-skill/crossframe.svg" alt="Measured on agentmods" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,617 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00091 $0.07617
Opus 5 $0.00046 $0.03809
Sonnet 5 $0.00018 $0.01523
Haiku 4.5 $0.00009 $0.00762

Measured 4d ago against content hash 0f69ee4d75b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

crossframe 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 4d 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/SKILL.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CrossFrame

如果用户任务需要多个 CrossFrame 平行 skill 连续协作,先读取 ../crossframe-suite/SKILL.md 做总调度;本 skill 负责其中的结构诊断、事实边界、尺度窗口、机制候选、七闸复核和判断档位。

语言原则

本 skill 的权威语义是中文。CrossFrame 只是英文传播名与 skill id,不承担概念解释权。

遇到中英文可能冲突时,以中文术语为准:承接、回流、开放断言、尺度转移、责任链、观测反身性、低条件试探行动、退出转移、不浪费爱、强判断八件套、局部状态坐标、过程性产物边界。

英文可以用于文件名、别名、对外简介或必要的双语标注;不要把中文概念硬译成英文后再反向理解。

核心定位

CrossFrame 不是“把 v5.0 文本塞进上下文”的提示词包,而是一个可执行的结构推理协议。

每次使用都必须先形成内部推理产物,再输出结论。结论可以很短,但不能跳过事实抽取、七闸复核、机制候选、概念契约、判断档位、源结构连续性、claim ledger 和表达闸。

必须执行的顺序

  1. 判断用户请求类型:快速诊断、完整诊断、推演、开放断言、命题验证、强判断、高反身性对象、亲密关系轻量入口、疗愈与转移、公共制度专项、低条件行动、高责任反俘获审查、框架边界、生命周期/状态坐标、递进闭环、势场/自主解离、治理连续性、框架治理与证伪、AI 过程性产物边界、弱信号/不透明检查、无制度基础设施中间路径、无法退出主体保护、隐喻/来源透明、工具化可及性、观测收束、超大规模压力测试、表达翻译、理论后台,或概念解释。
  2. 读取 references/runtime-read-policy.mdreferences/read-routing-map.md 和必要时 references/v5-material-selection-map.md,确定本次需要加载的 v5 source modules、连读包、协议、工作表、概念卡和模板。
  3. 先定位 v5 source modules,不全量打开大文件。默认只记录需要的 source module、关键词、V5-H 或源范围;只有源锚点不足、用户要求源审计、或高责任判断需要核验时,才定向读取 references/v5-source-spine.mdreferences/v5-section-digest-index.mdreferences/v5-coverage-map.mdreferences/v5-term-fidelity.md 的相关局部。
  4. 读取 references/continuity-closure-map.md 展开入口包的“必须同读闭包”;需要包说明、源锚点或降档细节时,再读取 references/continuity-bundles.md 和对应 references/continuity-bundles/v5/<bundle-id>.md。默认最多读取 3 个入口核心包 + 2 个相邻辅助包;这个上限不限制必须同读闭包。高责任、公共制度、组织处置、公开判断必须优先读七闸、强判断八件套、低权力保护、证据降级与行动上限包及其闭包。
  5. templates/read-state-capsule.md 生成 v5-read-state-capsule:先列 source modules,再列入口包、必须同读闭包、相邻候选、源锚点、降档边界和下游读取策略。suite 不生成胶囊,胶囊由本核心层生成并传给专项 skill、essay 和 review。
  6. 填写内部 intake:对象、尺度、事实、证据缺口、用户用途、受影响对象、观测影响、权力结构、行动上限。
  7. 通过七闸:对象闸、证据闸、尺度闸、责任闸、观测闸、权力闸、行动闸。七闸必须登记为 pass / weak / fail / blocked;任一为 failblocked,不能维持强判断。
  8. 判断是否触发 v5.0 半量化 DLC 运行时闸:默认不触发;只有用户明确要求量化、评分、半量化、比较、校准、一致性、审计、DLC 工具,或高责任/公开发布前需要内部边界审计时,才读取 DLC 文件。普通关系、组织和公共议题不得自动输出分数。
  9. 形成至少两个机制候选;除非证据足以说明只有一个机制。每个机制候选必须登记 mechanism_id,并回指事实、源锚点、反向证据、概念契约和判断档位上限。
  10. 对承担判断作用的概念做完整吸收:读取对应概念卡,并读取 references/concept-contracts/core-contracts.md 中对应概念契约;用 worksheets/concept-fidelity-check.md 做保真检查。概念卡回答含义,概念契约回答是否允许承担判断。
  11. worksheets/source-continuity-check.md 检查是否只读了孤立概念卡、漏掉 v5 相邻约束或需要降档。
  12. worksheets/source-anchor-integrity-check.md 检查中心命题、机制候选、高风险概念和行动边界能否回指胶囊源锚点;不能回指的内容只能标为“本文推断 / 表达转译 / 外部思想映射”,不得写成 CrossFrame v5 原义。
  13. templates/claim-ledger.md 生成 claim ledger:中心命题、机制候选、判断档位、行动建议、公共定性、文章转译和高风险概念使用都必须登记 claim_id。没有 claim_id 的命题不得进入正文或结论。
  14. worksheets/claim-ledger-check.md 检查正文前命题台账:若中心命题、行动建议、高风险概念或公共定性缺少事实锚点、源锚点、概念契约、判断档位、撤回条件或发布边界,必须删除、补证、降档,或标为“本文推断 / 表达转译 / 外部思想映射”。
  15. 决定判断档位:轻量观察、开放断言、完整诊断、强判断、低条件试探行动、退出转移。若必须联读但未联读、源锚点不足、概念契约未通过、claim ledger 缺失,不能维持强判断。
  16. 先输出现实诊断第一段,再给可见结构映射提纲并选择模板输出。第一段必须不用术语说清现实中发生了什么、为什么卡住、谁在承担成本、下一步看什么;结构映射提纲不展示完整工作表,但必须显示判断来自事实、机制候选、七闸和命题台账,而不是来自术语套用。

Read the full file on GitHub · 237 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. 4d ago First seen · 237 lines · 91 tokens per session scan A 0f69ee4d75b5

Subscribe to this mod's changes

crossframe is a skill published in the GitHub repository xi-kari/crossframe-skill (18 stars, last pushed 28d ago), licensed MIT. It adds 91 tokens to every session and 7,617 once invoked, about $0.0005 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

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

openai-frontend-design

Use for new frontend applications, dashboards, games, creative websites, hero sections, and visually driven UI from scratch, or when the user explicitly asks for a redesign/restyle/modernization. Builds from clean, airy, high-taste, readable image-generated concept design with section-specific references, faithful…

fcakyon/claude-codex-settings · 71 tokens

resolve-pr-comments

This skill should be used when user asks to "address PR comments", "resolve PR feedback", "handle review comments", "fix PR issues", "respond to PR review", or explicitly invokes "resolve-pr-comments".

fcakyon/claude-codex-settings · 47 tokens

update-pr-summary

This skill should be used when user asks to "update PR summary", "update PR description", "rewrite PR body", "refresh PR title and body", or explicitly invokes "update-pr-summary".

fcakyon/claude-codex-settings · 43 tokens

user-research-cookiy

End-to-end user research assistant — qualitative and quantitative. Use this skill whenever the user mentions user research, user interviews, discussion guides, interview guides, research plans, qualitative research, quantitative research, user surveys, survey design, usability studies, participant recruitment…

cookiy-ai/user-research-skill · 154 tokens