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/jeevan-vj/iamjeevan/avoid-nested-code-blocksgit clone --depth 1 https://github.com/jeevan-vj/iamjeevanWhat 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 | $0.00114 | $0.00114 |
| Opus 5 | $0.00057 | $0.00057 |
| Sonnet 5 | $0.00023 | $0.00023 |
| Haiku 4.5 | $0.00011 | $0.00011 |
Grade A, and why
avoid-nested-code-blocks 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 yesterday.
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
Avoid Nested Code Blocks in Blog Posts
- Do NOT use triple backticks (```) inside another triple backtick code block in any markdown/MDX blog post.
- MDX does not support nested code fences and this will cause build errors.
- If you need to show code-within-code, use 4-space indentation for the inner code, or use a single code block and clearly comment or separate the sections.
See README.md for more details. description: globs: alwaysApply: false
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.
- yesterday First seen · 12 lines · 114 tokens per session scan A a9fcbe725bb7
avoid-nested-code-blocks is a cursor rule published in the GitHub repository jeevan-vj/iamjeevan (3 stars, last pushed 3mo ago), licensed MIT. It adds 114 tokens to every session, about $0.0006 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 2026-08-31.
Other cursor rules, from other repositories
ruler_cursor_instructions
1) Use the "ikas" MCP list tool to find the correct query/mutation name. 2) Use the "ikas" MCP introspect tool to get the operation's full shape (variables, return fields, enums). 3) Only after confirming via list + introspect, add the document to graphql-requests.ts and run codegen.
project-structure
Overall project structure & standards.
utilities
Project utilities & helper functions for use across the project.
ui-components
Cursor rule "ui-components" from FluroAsh/nextjs-mdx-portfolio, covering ui components and styling, component libraries, shadcn/ui, custom components and styling approach.
open-source-guidelines
This is a database-free blog system that prioritizes.
performance-accessibility
Cursor rule "performance-accessibility" from muzaffar640/commitpress, covering performance and accessibility guidelines, performance optimization, image optimization, static generation and code splitting.