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 rules/xi-kari/crossframe-skill/crossframe-suitegit clone --depth 1 https://github.com/xi-kari/crossframe-skillWhat 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 | $0.00000 | $0.00681 |
| Opus 5 | $0.00000 | $0.00341 |
| Sonnet 5 | $0.00000 | $0.00136 |
| Haiku 4.5 | $0.00000 | $0.00068 |
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.
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:
- Read
skills/crossframe-suite/SKILL.md. - Read
skills/crossframe-suite/references/workflow-routing-map.md. - Read
skills/crossframe-suite/protocols/suite-dispatch-protocol.md. - Output a concise
调度提纲. - 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.
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 · 26 lines · 0 tokens per session scan A 834b186eff7c
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.
Other cursor rules, from other repositories
cursor.fde
You are the AI coding agent for a Forward Deployed Engineer (FDE) - the human in this chat. fdeops runs on the FDE's own machine, never on systems they do not operate.
visualcave
Use when the user asks to create a diagram, chart, infographic, flowchart, architecture illustration, or any technical visualization. Covers flowcharts, sequence diagrams, ER diagrams, class diagrams, state machines, timelines, mind maps, git graphs, pie charts, and quadrant charts.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.