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-casebook/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-casebook)<a href="https://agentmods.dev/skills/xi-kari/crossframe-skill/crossframe-casebook"><img src="https://agentmods.dev/badge/skills/xi-kari/crossframe-skill/crossframe-casebook.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 | $0.00035 | $0.01632 |
| Opus 5 | $0.00017 | $0.00816 |
| Sonnet 5 | $0.00007 | $0.00326 |
| Haiku 4.5 | $0.00003 | $0.00163 |
Grade A, and why
crossframe-casebook 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CrossFrame Casebook
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。
如果案例沉淀之后还要成文、教学、辩论或公共/组织专项判断，先读取 ../crossframe-suite/SKILL.md 做总调度；本 skill 只负责案例库条目和可复用材料结构。
CrossFrame Casebook 是 crossframe 的平行案例库 skill，不替代 crossframe。它只负责把材料整理成可复用案例条目：先守住事实、来源和隐私边界，再抽取尺度窗口、机制链、责任链、反向条件、可复用概念和后续观察。
中文为权威语义。英文只用于 skill id、文件名、字段名或对外简介；遇到中英文冲突，以中文术语为准。
必须执行的顺序
- 读取
../crossframe/SKILL.md，确认本次材料应遵守的 CrossFrame 基本闸门与表达边界。 - 读取
../crossframe/references/read-routing-map.md，按材料主题选择需要对齐的 CrossFrame protocol、概念卡和判断档位。 - 如果材料触发高责任、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
protocols/material-boundary-protocol.md，先做来源、事实、推测、隐私和可公开性分层。 - 读取
protocols/casebook-build-protocol.md，决定本次是新建案例、清洗旧案例、批量索引、比较案例，还是把复盘转成案例库。 - 读取
references/casebook-field-guide.md，保证每个案例至少沉淀九项：案例摘要、事实边界、材料来源、尺度窗口、机制链、责任链、反向条件、可复用概念、后续观察。 - 读取
references/privacy-and-redaction-rules.md，对个人、组织、地名、时间、聊天原文、截图、链接和可识别细节做脱敏。 - 读取
protocols/mechanism-extraction-protocol.md，从故事叙述中抽出机制链与责任链，避免只写剧情或堆概念。 - 按任务读取模板：单案例读
templates/casebook-entry-template.md；批量案例读templates/casebook-index-template.md；需要来源审计读templates/redacted-source-ledger-template.md。 - 输出前做 smoke check：不得把猜测当事实、不得泄露隐私、不得只写故事不抽机制、不得概念堆砌。
输入处理
- 聊天记录：保留互动结构、角色关系、可观察行为和时间顺序；删除或泛化姓名、账号、联系方式、精确位置和无关私密细节。
- 组织材料：区分正式制度、口头惯例、会议纪要、项目记录、个人感受和二手转述。
- 项目复盘：区分结果事实、过程事实、解释、责任归因、补救动作和未验证假设。
- 公共争议：区分公开来源、当事人说法、媒体报道、平台规则、法律事实、舆论解释和模型推测；涉及最新事实或真实人物组织时必须查源。
What ships with it
28 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 622 B
- evals/crossframe-casebook-smoke-tests.md 3.2 KB
- examples/failure-samples.md 2.1 KB
- examples/organization-case.md 3.1 KB
- examples/public-dispute-case.md 3.4 KB
- examples/relationship-case.md 3.2 KB
- examples/v5-dlc-quant-trials/ai-compliance-report-proof-regression.md 1.5 KB
- examples/v5-dlc-quant-trials/misuse-counterexample-trial.md 5.1 KB
- examples/v5-dlc-quant-trials/organization-case-trial.md 6.3 KB
- examples/v5-dlc-quant-trials/organization-retrospective-proof-regression.md 1.6 KB
- examples/v5-dlc-quant-trials/public-announcement-low-power-regression.md 1.4 KB
- examples/v5-dlc-quant-trials/public-dispute-case-trial.md 6.3 KB
- examples/v5-dlc-quant-trials/rater-disagreement-sample.md 2.1 KB
- examples/v5-dlc-quant-trials/relationship-case-trial.md 4.7 KB
- examples/v5-dlc-quant-trials/relationship-scale-erasure-regression.md 1.5 KB
- examples/v5-dlc-quant-trials/validation-summary.md 2.5 KB
- protocols/casebook-build-protocol.md 2.8 KB
- protocols/material-boundary-protocol.md 2.2 KB
- protocols/mechanism-extraction-protocol.md 1.8 KB
- references/casebook-field-guide.md 1.9 KB
- references/privacy-and-redaction-rules.md 1.7 KB
- references/reuse-taxonomy.md 1.6 KB
- references/v5-dlc-casebook-validation-protocol.md 3.8 KB
- templates/casebook-entry-template.md 1.5 KB
- templates/casebook-index-template.md 680 B
- templates/redacted-source-ledger-template.md 729 B
- templates/v5-dlc-quant-case-trial-template.md 2.1 KB
- templates/v5-dlc-rater-disagreement-record-template.md 1014 B
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 · 80 lines · 35 tokens per session scan A 86064eaebdda
crossframe-casebook is a skill published in the GitHub repository xi-kari/crossframe-skill (18 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 1,632 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…
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…