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/gemini-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/instructions/xi-kari/crossframe-skill/gemini-md)<a href="https://agentmods.dev/instructions/xi-kari/crossframe-skill/gemini-md"><img src="https://agentmods.dev/badge/instructions/xi-kari/crossframe-skill/gemini-md.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 | $0.02357 | $0.02357 |
| Opus 5 | $0.01179 | $0.01179 |
| Sonnet 5 | $0.00471 | $0.00471 |
| Haiku 4.5 | $0.00236 | $0.00236 |
Grade A, and why
crossframe-skill GEMINI.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 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.
This is a copy
94% identical to crossframe-skill AGENTS.md — 242 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini CLI 适配入口
@AGENTS.md
本文件是 Gemini CLI 的仓库级上下文入口。
CrossFrame skills 在 Gemini CLI 中也是显式调用 only。不要因为普通分析、写作、评论、组织修复、读书、辩论或评审任务自动触发 CrossFrame。只有用户明确点名 crossframe-suite、crossframe、某个 crossframe-*，或明确说“用 CrossFrame / 用跨尺度结构诊断框架”时才进入本文件下面的 CrossFrame 路由。
如果用户显式调用 crossframe-suite，并要求一个复杂任务需要多个 CrossFrame skill 连续协作，先读取：
skills/crossframe-suite/SKILL.mdskills/crossframe-suite/references/workflow-routing-map.mdskills/crossframe-suite/protocols/suite-dispatch-protocol.md
常见链路：普通文章 crossframe -> crossframe-essay -> crossframe-review；公共评论 crossframe -> crossframe-public -> crossframe-essay -> crossframe-review；组织复盘文章 crossframe -> crossframe-org -> crossframe-essay -> crossframe-review；历史研究 crossframe -> crossframe-history -> crossframe-essay(full-visible-v5-longform) -> crossframe-review；答读者问 crossframe -> crossframe-dialogue -> crossframe-essay(full-visible-v5-longform) -> crossframe-review；读书研究 crossframe -> crossframe-notebook -> crossframe-essay(full-visible-v5-longform) -> crossframe-review；完成后追问 crossframe -> crossframe-review(lite) -> crossframe-inquiry。不要一次读取全部 skill。
显式调用后优先考虑 crossframe-suite。suite 内部按 routing map 联合读取 sibling skills 不算被动触发。只要用户从 suite 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，包含完整可见底稿和完整长文正文。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，才关闭默认文章层。
完整链路已经完成分析、成文和 review 后，下一轮实质输入默认进入 crossframe-inquiry；纯致谢、确认收到或结束语（如“谢谢”“好的”“明白了”“先这样”）只轻量收束，不自动展开追问。
如果用户显式调用 crossframe-max、/crossframe-max、$crossframe-max，或要求最大算力、全尺度穷尽推演、不设字数限制完整解释，请读取 skills/crossframe-max/SKILL.md。这是独立模式，不走 crossframe-suite 的 2+1 模式/角色选择器，也不走普通文章类型选择器；它把一件事当作局部世界来建模，展开世界观、运行规律、问题结构、处理路径和演化分支。
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。
如果用户显式调用 crossframe-essay 或经 crossframe-suite 路由到写作，并要求写中文文章、长文、评论、思想文章、批判性洞察文章或结构洞察文章，请读取：
skills/crossframe-essay/SKILL.mdskills/crossframe/SKILL.mdskills/crossframe/references/read-routing-map.md- 对应
skills/crossframe/protocols/文件 - 高责任、公共制度、亲密关系、长期演化、深度分析和文章输出，优先读取
skills/crossframe/references/runtime-read-policy.md与skills/crossframe/references/continuity-closure-map.md；需要展开源结构时再按需读取skills/crossframe/references/continuity-bundles.md、skills/crossframe/references/v5-source-spine.md与skills/crossframe/references/v5-section-digest-index.md skills/crossframe-essay/references/evidence-and-search-rules.md- 若需要概念上升、引经据典、理论参照或文学互文，读取
skills/crossframe-essay/protocols/concept-elevation-protocol.md、skills/crossframe-essay/references/reference-and-allusion-rules.md、skills/crossframe-essay/references/concept-reference-map.md - 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 skills/crossframe-essay/protocols/essay-protocol.md或interactive-drafting-protocol.mdskills/crossframe-essay/templates/insight-dossier-template.mdskills/crossframe-essay/templates/essay-output-template.md或interactive-session-template.md
文章输出默认先给完整可见 结构洞察底稿，再给完整长文 文章正文。公共议题、最新事实、真实组织/平台/人物/政策/公司相关内容必须查源；私人关系、哲学概念和泛论随笔默认不查源，除非用户要求。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/理论参照必须回到现实机制与责任链。现代编辑底色是默认前台表达：亲切但不和稀泥，果敢但不人格审判。
如果用户显式调用 crossframe 或经 crossframe-suite 路由到结构诊断、推演、开放断言、高责任审查或低条件行动，请读取：
skills/crossframe/SKILL.mdskills/crossframe/references/read-routing-map.md- 对应
skills/crossframe/protocols/文件 skills/crossframe/templates/reasoning-outline-output.mdskills/crossframe/templates/user-facing-language.md- 若使用高风险概念，读取
skills/crossframe/references/concept-cards/README.md与对应概念卡 - 高责任、公共制度、亲密关系、长期演化、深度分析和文章输出，优先读取
skills/crossframe/references/runtime-read-policy.md与skills/crossframe/references/continuity-closure-map.md；需要展开源结构时再按需读取skills/crossframe/references/continuity-bundles.md、skills/crossframe/references/v5-source-spine.md与skills/crossframe/references/v5-section-digest-index.md - 输出前用
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；需要审计时再展开skills/crossframe/worksheets/concept-fidelity-check.md和skills/crossframe/worksheets/source-continuity-check.md
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.
- 4d ago First seen · 77 lines · 2,357 tokens per session scan A 4c9c10fe7b47
crossframe-skill GEMINI.md is an instructions file published in the GitHub repository xi-kari/crossframe-skill (18 stars, last pushed 28d ago), licensed MIT. It adds 2,357 tokens to every session, about $0.0118 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to crossframe-skill AGENTS.md, differing in 242 lines, and is treated as a copy.
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 security.instructions.md
Instructions for yigitkonur/cli-continues, covering security review guidelines — core utilities, command injection prevention (resume.ts), forward flag security (forward-flags.ts), handoff output safety (markdown.ts) and general.