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.
npx agentmods add instructions/xi-kari/crossframe-skill/copilot-instructionsgit 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/instructions/xi-kari/crossframe-skill/copilot-instructions)<a href="https://agentmods.dev/instructions/xi-kari/crossframe-skill/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/xi-kari/crossframe-skill/copilot-instructions.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 | $0.01801 | $0.01801 |
| Opus 5 | $0.00901 | $0.00901 |
| Sonnet 5 | $0.00360 | $0.00360 |
| Haiku 4.5 | $0.00180 | $0.00180 |
Grade A, and why
crossframe-skill copilot-instructions.md 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 3d 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.
What it actually says
GitHub Copilot 仓库指令
- 本仓库主体内容以中文为主；
CrossFrame只是英文传播名与 skill id。 - 实际可安装的 Codex skill 位于
skills/crossframe/。 - 总调度 skill 位于
skills/crossframe-suite/；复杂任务先用它决定连续触发顺序。 crossframe-suite是推荐默认入口。只要从总入口进入任何 CrossFrame 内容任务，默认先完成必要专项 skill，再追加crossframe-essay -> crossframe-review，输出full-visible-v5-longform：完整可见底稿 + 完整长文正文；只有用户明确说“只要/不要文章/短答/表格/清单/纯诊断/仅行动方案”时才关闭文章层。- 平行文章写作 skill 位于
skills/crossframe-essay/。 - 其它平行专项 skill 位于
skills/crossframe-review/、skills/crossframe-dialogue/、skills/crossframe-casebook/、skills/crossframe-history/、skills/crossframe-inquiry/、skills/crossframe-max/、skills/crossframe-promax/、skills/crossframe-public/、skills/crossframe-org/、skills/crossframe-teach/、skills/crossframe-debate/、skills/crossframe-notebook/。 README.md与skills/crossframe/SKILL.md是原始说明来源；新增适配优先薄封装，不要复制出多套漂移正文。- 结构诊断、推演、开放断言、反俘获审查或低条件行动任务请遵循
AGENTS.md。 - 中文文章、长文、评论、思想文章、批判性洞察文章和结构洞察文章任务请遵循
skills/crossframe-essay/SKILL.md。 - 评审、短答复、案例库、历史研究、公共议题、组织修复、概念教学、命题辩论、研究笔记任务请遵循对应
skills/crossframe-*/SKILL.md。 - 多 skill 连续任务请先遵循
skills/crossframe-suite/SKILL.md，例如公共评论文章走crossframe -> crossframe-public -> crossframe-essay -> crossframe-review，组织复盘文章走crossframe -> crossframe-org -> crossframe-essay -> crossframe-review，历史研究走crossframe -> crossframe-history -> crossframe-essay -> crossframe-review，完成后追问走crossframe -> crossframe-review(lite) -> crossframe-inquiry；不要一次读取全部 skill。 - 完整链路已经完成分析、成文和 review 后，下一轮用户未明确说“新任务 / 换主题 / 退出追问 / 不接着上文”，且不是“谢谢 / 好的 / 明白了 / 先这样”等纯致谢、确认收到或结束语时，默认进入
crossframe-inquiry；它可以定向检索 1-3 个相关 sibling skill 的必要材料，但不得把检索写成正式专项判断。 crossframe-max是 named-only 独立模式；只有明确点名或要求最大算力、全尺度穷尽推演、不设字数限制完整解释时才读取skills/crossframe-max/SKILL.md，不走 suite 的2+1选择器或普通文章类型选择器。- CrossFrame ProMax 是 v8-only 的 exact-name only 独立 skill：仅在用户精确点名
crossframe-promax、CrossFrame ProMax、$crossframe-promax或/crossframe-promax时读取skills/crossframe-promax/SKILL.md。Max 与 ProMax 同时出现时 ProMax 优先；泛化最大化请求仍由 Max；suite 不得自动升级；ProMax 使用独立审计，不串联 review，也不得降级回 Max。 - 文章任务需要深度、概念上升、引经据典、理论参照或文学互文时，按需读取
skills/crossframe-essay/protocols/concept-elevation-protocol.md与skills/crossframe-essay/references/reference-and-allusion-rules.md。 - 文章任务自动成文默认读取
skills/crossframe-essay/protocols/editorial-comrade-voice-protocol.md与skills/crossframe-essay/references/editorial-voice-principles.md；只有显式中性报告/备忘录/表格/纯诊断时关闭。 - 概念解释或思想解释任务也应进入 CrossFrame，但先读
skills/crossframe/protocols/concept-explanation-protocol.md。 - 强判断、高反身性、亲密关系、疗愈转移、公共制度、框架边界、生命周期、递进、势场解离、治理连续性、超大规模压力测试和长期演化任务必须按
skills/crossframe/references/read-routing-map.md读取深水区模块。 - 默认先展示简短推理提纲，再输出普通用户能读懂的判断。
- 文章任务默认先输出完整可见
结构洞察底稿，再输出完整长文文章正文。 - 默认文章不得缩水成短答；正文需要标题、铺陈、概念上升、现实回落、边界段和余味结尾。
- 直接引用必须可核验；不确定原句时只做意译或思想映射；经典/理论参照不能接管文章命题。
- 现代编辑底色只负责前台表达：亲切但不和稀泥，果敢但不人格审判，不复古口号化。
- 输出必须区分事实、解释、机制候选、判断档位和本次读取的概念。
- 默认不展示内部 reasoning、工具调用参数、路径试错、错误栈或英文自我规划；需要审计时只展示台账摘要和风险点。
- 高风险概念如承接/回流、开放断言、尺度转移、观测反身性、权力封闭、低条件行动、爱/开放行动、责任链、证据成本、机制候选、判断档位、退出转移、修复副产品，必须先读
skills/crossframe/references/concept-cards/对应卡片。 - 输出前优先用
skills/crossframe/references/runtime-read-policy.md、skills/crossframe/references/read-routing-map.md和skills/crossframe/references/continuity-closure-map.md做轻量闭包检查，避免概念压缩、联读遗漏和源结构断裂。 - 高责任、公共制度、亲密关系、长期演化、深度分析和文章输出，需要展开审计时，再读取
skills/crossframe/references/continuity-bundles.md，按需读取skills/crossframe/references/v5-source-spine.md、skills/crossframe/references/v5-section-digest-index.md和skills/crossframe/worksheets/source-continuity-check.md，避免只读单概念卡导致 5.0 连续性失真。 - 强判断不得绕开命题验证；高反身性不得无限递归；亲密关系不得把爱变成忍耐义务。
- 框架边界不得把 CrossFrame 当专业替代品；生命周期不得写成命运；超大规模判断必须承认可判断边界。
- 不要把结构诊断变成人格审判、命运预言、责任稀释或概念堆砌。
- 修改仓库时，不要删除
skills/crossframe/的可安装入口。 - 修改仓库时，不要删除
skills/crossframe-essay/的可安装入口，也不要把它的文章协议复制进薄适配层。 - 修改仓库时，不要删除任何
skills/crossframe-*/可安装入口；适配层只做分发说明，不复制专项协议。
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.
- 3d ago First seen · 37 lines · 1,801 tokens per session scan A e88067a5d963
crossframe-skill copilot-instructions.md is an instructions file published in the GitHub repository xi-kari/crossframe-skill (18 stars, last pushed 27d ago), licensed MIT. It adds 1,801 tokens to every session, about $0.0090 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 instructions, from other repositories
skills CLAUDE.md
Claude Code instructions for lovstudio/skills, covering claude.md, what this is, repo layout, how users install and skills.yaml schema.
FDEOps AGENTS.md
Instructions for suboss87/FDEOps, covering agents.md - working in the fdeops repository, if you are helping use fdeops in an engagement, if you are contributing to this repository and boundaries.
Dragon-Brain CLAUDE.md
Instructions for iikarus/Dragon-Brain, covering dragon brain — claude.md, the harness, audit remediation (april–may 2026, complete 2026-05-09), the lie this audit closed and the contract that matters now.
cli-continues parsers.instructions.md
Instructions for yigitkonur/cli-continues, covering parser review guidelines, crash safety (critical), required exports, jsonl streaming and tool summarizer.
cli-continues ci.instructions.md
Instructions for yigitkonur/cli-continues, covering ci workflow review guidelines, security, prefer explicit permissions scoping, node.js version requirements and package manager.
cli-continues typescript.instructions.md
Instructions for yigitkonur/cli-continues, covering typescript review guidelines, type safety, discriminated unions, async patterns and import rules.