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-essaygit 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/rules/xi-kari/crossframe-skill/crossframe-essay)<a href="https://agentmods.dev/rules/xi-kari/crossframe-skill/crossframe-essay"><img src="https://agentmods.dev/badge/rules/xi-kari/crossframe-skill/crossframe-essay.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 | $0.00000 | $0.00673 |
| Opus 5 | $0.00000 | $0.00336 |
| Sonnet 5 | $0.00000 | $0.00135 |
| Haiku 4.5 | $0.00000 | $0.00067 |
Grade A, and why
crossframe-essay 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 the user asks to write a 中文文章、长文、评论、思想文章、批判性洞察文章、结构洞察文章, or wants CrossFrame reasoning turned into readable prose, read skills/crossframe-essay/SKILL.md first.
If the article also requires public evidence, organization repair, history research, debate, reading notes, casebook extraction, post-completion inquiry, or final review, read skills/crossframe-suite/SKILL.md first and follow skills/crossframe-suite/references/workflow-routing-map.md. Then return to this essay rule only when the workflow reaches crossframe-essay.
Required flow:
- Read
skills/crossframe-essay/SKILL.md. - Read
skills/crossframe/SKILL.md. - Read
skills/crossframe/references/read-routing-map.md. - Read
skills/crossframe/references/runtime-read-policy.mdandskills/crossframe/references/continuity-closure-map.mdto confirm the required concept cards, continuous-reading bundles, and downgrade conditions. - Route the topic through the appropriate CrossFrame protocol.
- Decide whether to search using
skills/crossframe-essay/references/evidence-and-search-rules.md. - If the topic needs depth, concept elevation, 引经据典, theory, or literary allusion, read
skills/crossframe-essay/protocols/concept-elevation-protocol.md,skills/crossframe-essay/references/reference-and-allusion-rules.md, andskills/crossframe-essay/references/concept-reference-map.md. - Automatic article mode reads
skills/crossframe-essay/protocols/editorial-comrade-voice-protocol.mdandskills/crossframe-essay/references/editorial-voice-principles.mdby default; only close this voice for explicit neutral report, memo, table, pure diagnosis, or academic summary requests. - Output a complete visible
结构洞察底稿before a complete long-form文章正文; default output mode isfull-visible-v5-longform.
Do not write only the article body, and do not let the dossier replace the body. Do not shrink automatic articles into short answers. Public/current/real-world topics require sources and evidence boundaries; private relationship, philosophical, and general essay topics do not browse by default unless requested.
Use plain Chinese for ordinary readers. Keep terms like 承接, 回流, 开放断言, 责任链, 证据成本, 修复副产品 as backend mapping unless they genuinely help the article.
Direct quotes must be verifiable. If unsure, use paraphrase, allusion, or thought mapping. References must return to concrete mechanism, evidence, and responsibility chain.
Modern editor-comrade base voice is the default for automatic articles: patient, humble, serious, and decisive. It may use answer-form for reader questions, but must not become retro slogan, empty comfort, or personality judgment.
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 · 30 lines · 0 tokens per session scan A 1149827918e5
crossframe-essay 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 673 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
project
Project conventions - canonical source is AGENTS.md.
evaluation-protocol
Evaluation protocol for blind skill testing across model tiers.
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.