agentmods.dev

crossframe-max

crossframe-max is a skill for Claude Code, Codex from xi-kari/crossframe-skill. It costs 72 tokens per session (2,929 once invoked), scanned A, original, MIT.

A CrossFrame v6 meta-runtime skill for exhaustively analyzing and reviewing skills, prompts, agents, tools, templates, scripts, and operating rules.

In plain words
What is it for?
Use it for maximum-scale explanations, structural reviews, and design reviews that require dossiers, essays, continuation records, manifests, and validation status.
Why use it?
It gives complex reviews a defined process for modeling the subject, checking evidence, recording gaps, and producing traceable work files.

Skill for Claude CodeCodex

not rated 18 29d ago A scan 72 tokens original MIT
View the source file xi-kari/crossframe-skill xi-kari.github.io
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-max
Any agent
npx skills add xi-kari/crossframe-skill --skill crossframe-max
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-max

README.md
[![agentmods](https://agentmods.dev/badge/skills/xi-kari/crossframe-skill/crossframe-max.svg)](https://agentmods.dev/skills/xi-kari/crossframe-skill/crossframe-max)
Your own site
<a href="https://agentmods.dev/skills/xi-kari/crossframe-skill/crossframe-max"><img src="https://agentmods.dev/badge/skills/xi-kari/crossframe-skill/crossframe-max.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,929 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 5.1 $0.00072 $0.02929
Opus 5 $0.00036 $0.01465
Sonnet 5 $0.00014 $0.00586
Haiku 4.5 $0.00007 $0.00293

Measured 5d ago against content hash 7169441b9b70, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

crossframe-max 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.

.claude/skills/crossframe-max/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CrossFrame Max

crossframe-max 是 CrossFrame v6 世界观前置的 meta-runtime。它不是超长回答模板，也不是省略式诊断模板；它先让 AI 拥有用户预先设计的世界观，再把对象当作局部世界建模，在材料、工具、上下文和行动边界内完成最大推演、校准回合、举证推理、反向证据、产物交付和续写索引。

max-clean-runtime-entry

运行入口保持正向、精简：SKILL.md 只放触发边界、运行档位、必读顺序、交付闸门和校验命令。失败样本和反例压力测试放在 evals/；长细则放在 protocols/、templates/ 和脚本。

默认目标不是聊天短答，也不是先判定自己做不到。默认目标是 max-artifact-run：先创建产物目录，先生成阶段文件、dossier、essay、continuation 和 manifest，再登记未满足项。

触发边界

这是 explicit-only skill。只有用户明确要求 crossframe-max、最大尺度、穷尽推演、完整解释、无限制长文、全尺度世界观解释，或明确要求用 v6 meta-runtime 审查 skill、prompt、agent、工具、模板、脚本、运行协议时使用。

运行档位

  • max-artifact-run：普通 /crossframe-max 默认档位。必须尽力创建独立产物目录和最小产物集，写出 max-dossier.md、max-essay.md、max-continuation-ledger.md、max-continuation-index.md 和 max-artifact-manifest.md。如果 full-source、结构化台账或 validator 未满足，产物状态写为 max-artifact-incomplete:*，但不得因此省略长文或只输出读态。
  • max-complete：完整 full-source exhaustive pass、阶段锁、artifact-first、template-fidelity、longform-dominance、route-ledger gate 和 validator 全部满足后才可宣称完成。
  • max-design-review：用于 skill、prompt、agent、工具、模板、脚本和运行时设计。必须使用 skill_design route，登记 route_key、route concepts、design decision、v6 rule、反向证据、撤回条件和行动上限；不得伪称完整 max 长文完成。
  • max-blocked/progress：只有文件系统不可写、必需材料不可访问、用户明确中止、工具权限缺失，或安全/政策边界阻断时使用。任务庞大、3273/3273 未完成、validator 未通过、外部检索不完整，不是停止产物生成的理由；这些只阻断 max-complete 声明。

max-artifact-incomplete:<registered-reason> 是 validator 根据未满足项生成的交付标签，不是第五种运行档位。新建或修复后的 run contract 从 validation_state=not_run 开始；validator 只在检查结束后持久化 passed 或 failed。失败 contract 必须先重置为 not_run，才可重新校验，不能直接跳到 passed。

世界观层先行

第一动作是建立 max-worldview-capsule。先加载 v6 全量分层源库作为本轮预先设计的世界观，再进入局部世界建模、概念命中、证据审计、路径推演和正文生成。

执行时必须把对象当作一个局部世界来对待：

  • 先做局部世界建模，再做判断。
  • 先识别运行规律，再定位问题。
  • 先查 registry 再读 full-source。
  • 先完成举证链、推理链、反向证据和证据-推理-反例-降档循环，再进入最终表达。
  • 先保留撤回条件、行动上限和不可穷尽声明，再写完整长文或设计审查结论。

必读顺序

  1. protocols/max-worldview-protocol.md
  2. protocols/max-repair-loop-protocol.md
  3. references/source_manifest.json
  4. references/v6-route-map.yaml
  5. references/concept-registry/index.md
  6. references/concept-contracts/v6-core-contracts.md
  7. references/concept-contracts/v6-contract-map.json
  8. references/retrieval-trigger-policy.md
  9. references/v6-full-source/00-index.md
  10. references/v6-full-source/00-heading-index.md
  11. references/v6-full-source/00-term-index.md
  12. references/v6-full-source/00-table-index.md
  13. route 指定的 v6 full-source 分层文件与 tables/
  14. templates/ 中本轮产物对应 contract
  15. scripts/ 中对应 validator

Read the full file on GitHub · 182 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. 5d ago First seen · 182 lines · 72 tokens per session scan A 7169441b9b70

Subscribe to this mod's changes

crossframe-max is a skill published in the GitHub repository xi-kari/crossframe-skill (18 stars, last pushed 29d ago), licensed MIT. It adds 72 tokens to every session and 2,929 once invoked, about $0.0004 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.

Building agentsai-skillclaude-codecodex-skillcrossframecursorgemini-cli
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

polar-billing

This skill should be used when working on Polar billing system, Stripe integration, subscription lifecycle, checkout flows, or benefit provisioning.

fcakyon/claude-codex-settings · 29 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

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…

fcakyon/claude-codex-settings · 97 tokens

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…

fcakyon/claude-codex-settings · 112 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