crossframe-suite

A routing rule for choosing and ordering several CrossFrame skills when a task combines multiple kinds of analysis or writing. It defines when to use the standard suite and when a specifically named advanced mode takes priority.

In plain words
What is it for?
Use it to coordinate workflows such as diagnosis followed by writing, research followed by an essay, debate-to-essay work, and casebook extraction with review.
Why use it?
It prevents complex CrossFrame tasks from using the wrong sequence of skills or skipping required stages.

Cursor rule for Cursor

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 rules/xi-kari/crossframe-skill/crossframe-suite
Clone the repo
git clone --depth 1 https://github.com/xi-kari/crossframe-skill

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 681 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 $0.00000 $0.00681
Opus 5 $0.00000 $0.00341
Sonnet 5 $0.00000 $0.00136
Haiku 4.5 $0.00000 $0.00068

Measured 3d ago against content hash 834b186eff7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

crossframe-suite 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.

.cursor/rules/crossframe-suite.mdc · 26 lines

What it actually says

When a task asks for a complex CrossFrame workflow, such as writing after diagnosis, public commentary, organization repair writing, history research-to-essay, debate-to-essay, reading-note-to-essay, casebook extraction plus review, post-completion inquiry, or "which CrossFrame skills should trigger in what order", read skills/crossframe-suite/SKILL.md first.

If the user explicitly asks for crossframe-max, maximum CrossFrame mode, exhaustive structural projection, full-scale world-model interpretation, or no word-limit complete explanation, do not use the suite selector. Read skills/crossframe-max/SKILL.md instead.

CrossFrame ProMax is a v8-only, exact-name only independent skill. Read skills/crossframe-promax/SKILL.md only for 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.

Use this suite rule as the default CrossFrame entry. For any CrossFrame content task through Suite, finish the needed sibling skills first, then append crossframe-essay -> crossframe-review and use full-visible-v5-longform: complete visible structural dossier plus complete long-form article with the modern editor-comrade base voice. Only skip the article layer when the user explicitly says only/no article/short answer/table/checklist/pure diagnosis/action plan only.

Required flow:

  1. Read skills/crossframe-suite/SKILL.md.
  2. Read skills/crossframe-suite/references/workflow-routing-map.md.
  3. Read skills/crossframe-suite/protocols/suite-dispatch-protocol.md.
  4. Output a concise 调度提纲.
  5. Read only the sibling skills selected by the workflow.

For high-responsibility, public, intimate, long-evolution, deep-analysis, or article workflows, ensure the underlying crossframe step reads skills/crossframe/references/runtime-read-policy.md, skills/crossframe/references/read-routing-map.md, and skills/crossframe/references/continuity-closure-map.md. Use continuity-bundles.md and source-continuity-check.md only when an expanded audit is needed.

Do not trigger every crossframe-* skill at once. Use crossframe-history for historical materials, source tiers, periodization, long-duration evolution, and archive/FOIA backlog work. Use crossframe-review as a quality gate for formal, public, long-form, strong-judgment, or high-responsibility outputs. After a completed workflow, any substantive follow-up without an explicit new-task/exit or pure acknowledgment/thanks signal should route to crossframe-inquiry; pure acknowledgments or endings such as "谢谢", "好的", "明白了", or "先这样" should only close lightly. Inquiry may retrieve 1-3 relevant sibling skills for question design, counterexamples, transfer conditions, and risk boundaries.

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. 3d ago First seen · 26 lines · 0 tokens per session scan A 834b186eff7c

Subscribe to this mod's changes

crossframe-suite is a cursor rule published in the GitHub repository xi-kari/crossframe-skill (18 stars, last pushed 27d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 681 tokens. 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.