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/claude-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/claude-md)<a href="https://agentmods.dev/instructions/xi-kari/crossframe-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/xi-kari/crossframe-skill/claude-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 5.1 | $0.02852 | $0.02852 |
| Opus 5 | $0.01426 | $0.01426 |
| Sonnet 5 | $0.00570 | $0.00570 |
| Haiku 4.5 | $0.00285 | $0.00285 |
Grade A, and why
crossframe-skill CLAUDE.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 5d 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
88% identical to crossframe-skill AGENTS.md — 328 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code 适配入口
@AGENTS.md
CrossFrame skills 在 Claude Code 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 .claude/skills/crossframe*/SKILL.md。只有用户明确点名 crossframe-suite、crossframe、某个 crossframe-*，或使用下面的 /crossframe* 命令时才进入 CrossFrame。用户显式调用 /crossframe-suite 后，suite 内部继续可以按 routing map 联合读取 sibling skills，这不算被动触发。
这个仓库提供 Claude Code 项目级 skill：
.claude/skills/crossframe/SKILL.md.claude/skills/crossframe-suite/SKILL.md.claude/skills/crossframe-essay/SKILL.md.claude/skills/crossframe-review/SKILL.md.claude/skills/crossframe-dialogue/SKILL.md.claude/skills/crossframe-casebook/SKILL.md.claude/skills/crossframe-history/SKILL.md.claude/skills/crossframe-inquiry/SKILL.md.claude/skills/crossframe-max/SKILL.md.claude/skills/crossframe-promax/SKILL.md.claude/skills/crossframe-public/SKILL.md.claude/skills/crossframe-org/SKILL.md.claude/skills/crossframe-teach/SKILL.md.claude/skills/crossframe-debate/SKILL.md.claude/skills/crossframe-notebook/SKILL.md.claude/commands/crossframe.md.claude/commands/crossframe-suite.md.claude/commands/crossframe-explain.md.claude/commands/crossframe-audit.md.claude/commands/crossframe-essay.md.claude/commands/crossframe-review.md.claude/commands/crossframe-dialogue.md.claude/commands/crossframe-casebook.md.claude/commands/crossframe-history.md.claude/commands/crossframe-inquiry.md.claude/commands/crossframe-max.md.claude/commands/crossframe-promax.md.claude/commands/crossframe-public.md.claude/commands/crossframe-org.md.claude/commands/crossframe-teach.md.claude/commands/crossframe-debate.md.claude/commands/crossframe-notebook.md
在仓库根目录运行 claude 后，可以直接使用：
/crossframe 帮我分析这个组织为什么复盘很多但没有真实修复
/crossframe-suite 写一篇公共评论文章，并安排诊断、查源、成文和评审顺序
/crossframe-explain 解释一下虚无主义
/crossframe-audit 检查这个高责任判断能不能公开
/crossframe-essay 写一篇“团队越复盘越失真”的批判性洞察文章
/crossframe-review 评审这段输出有没有真的推理
/crossframe-dialogue 像编辑回信一样回答这个读者问题
/crossframe-casebook 把这些复盘材料整理成案例库
/crossframe-history 分析唐中后期安史之乱、藩镇与两税法的史料边界和历史接口层
/crossframe-inquiry 基于刚才完成的分析，继续追问反证、补证和迁移条件
/crossframe-max 把这件事当作一个局部世界，做全尺度结构推演并写完整解释
/crossframe-promax 用 v8 框架穷尽分析这个判断，主动搜索反例并给出明确立场
/crossframe-public 分析这个平台申诉机制是否只是表面治理
/crossframe-org 给这个项目失败写组织修复备忘录
/crossframe-teach 用人话解释开放断言
/crossframe-debate 检验这个命题的正反结构和撤回条件
/crossframe-notebook 读这篇文章，写与 CrossFrame 的关联与不同
本文件保持轻量。若任务确实涉及 CrossFrame 使用、文档修订或适配层维护，再按需读取：
CrossFrame ProMax is a v8-only, exact-name only independent skill. Read skills/crossframe-promax/SKILL.md only when the user writes crossframe-promax, CrossFrame ProMax, $crossframe-promax, or /crossframe-promax. If both Max and ProMax are named, ProMax wins; generic maximality remains Max; suite never auto-upgrades; ProMax uses its own audit with no review chain and never falls back to Max.
README.mdskills/crossframe-suite/SKILL.mdskills/crossframe-suite/references/workflow-routing-map.mdskills/crossframe/SKILL.mdskills/crossframe-essay/SKILL.mdskills/crossframe/references/read-routing-map.mdskills/crossframe/references/runtime-read-policy.mdskills/crossframe/references/continuity-closure-map.mdskills/crossframe/references/continuity-bundles.mdskills/crossframe/references/v5-source-spine.mdskills/crossframe/references/v5-section-digest-index.mdskills/crossframe/references/v5-term-fidelity.mdskills/crossframe/references/theory-backend-index.mdskills/crossframe/references/v5-coverage-map.mdskills/crossframe/protocols/framework-boundary-protocol.mdskills/crossframe/protocols/lifecycle-diagnosis-protocol.mdskills/crossframe/protocols/progression-protocol.mdskills/crossframe/protocols/field-dissociation-protocol.mdskills/crossframe/protocols/governance-continuity-protocol.mdskills/crossframe/protocols/large-scale-stress-test-protocol.mdskills/crossframe/protocols/expression-translation-protocol.mdskills/crossframe/protocols/diagnosis-protocol.mdskills/crossframe/protocols/proposition-verification-protocol.mdskills/crossframe/protocols/high-reflexivity-protocol.mdskills/crossframe/protocols/intimate-relationship-protocol.mdskills/crossframe/protocols/healing-transfer-protocol.mdskills/crossframe/protocols/public-institution-protocol.mdskills/crossframe/templates/reasoning-outline-output.mdskills/crossframe/templates/user-facing-language.mdskills/crossframe/references/concept-cards/README.mdskills/crossframe-essay/protocols/essay-protocol.mdskills/crossframe-essay/protocols/interactive-drafting-protocol.mdskills/crossframe-essay/references/evidence-and-search-rules.mdskills/crossframe-essay/references/critical-insight-principles.mdskills/crossframe-essay/protocols/concept-elevation-protocol.mdskills/crossframe-essay/references/reference-and-allusion-rules.mdskills/crossframe-essay/references/concept-reference-map.mdskills/crossframe-essay/protocols/editorial-comrade-voice-protocol.mdskills/crossframe-essay/references/editorial-voice-principles.mdskills/crossframe-essay/templates/insight-dossier-template.mdskills/crossframe-essay/templates/essay-output-template.mdskills/crossframe-review/SKILL.mdskills/crossframe-dialogue/SKILL.mdskills/crossframe-casebook/SKILL.mdskills/crossframe-history/SKILL.mdskills/crossframe-inquiry/SKILL.mdskills/crossframe-max/SKILL.mdskills/crossframe-promax/SKILL.mdskills/crossframe-public/SKILL.mdskills/crossframe-org/SKILL.mdskills/crossframe-teach/SKILL.mdskills/crossframe-debate/SKILL.mdskills/crossframe-notebook/SKILL.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.
- 5d ago First seen · 139 lines · 2,852 tokens per session scan A 20679c037112
crossframe-skill CLAUDE.md is an instructions file published in the GitHub repository xi-kari/crossframe-skill (18 stars, last pushed 29d ago), licensed MIT. It adds 2,852 tokens to every session, about $0.0143 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to crossframe-skill AGENTS.md, differing in 328 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
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 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.
cli-continues typescript.instructions.md
Instructions for yigitkonur/cli-continues, covering typescript review guidelines, type safety, discriminated unions, async patterns and import rules.