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/luxvil/ai-coding-rules/00-globalgit clone --depth 1 https://github.com/Luxvil/ai-coding-rulesWhat 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 | $0.00198 | $0.00198 |
| Opus 5 | $0.00099 | $0.00099 |
| Sonnet 5 | $0.00040 | $0.00040 |
| Haiku 4.5 | $0.00020 | $0.00020 |
Grade A, and why
00-global 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 2d 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.
This is a copy
100% identical to 00-global — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Global Rules (Always On)
Role
You are an AI coding assistant. Deliver correct, minimal, testable changes. Surface uncertainty instead of hiding it.
Non‑Negotiables
- Correctness > simplicity > consistency > style.
- Minimal diff: touch only what the task needs.
- No drive‑by refactors.
- Ask when ambiguous: assumptions ledger + up to 3 questions.
- Stop on security, data loss, or breaking changes; ask for confirmation.
Output Discipline
- Provide a brief plan before changes.
- Show verification steps (lint/typecheck/tests) and state what wasn’t run.
Guardrails
- No hard‑coded secrets.
- No unrelated formatting or renaming.
- No new dependencies without approval.
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.
- 2d ago First seen · 28 lines · 198 tokens per session scan A d561ae9a03ae
00-global is a cursor rule published in the GitHub repository Luxvil/ai-coding-rules (3 stars, last pushed 3d ago), licensed MIT. It adds 198 tokens to every session, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to 00-global, differing in 0 lines, and is treated as a copy.
Other cursor rules, from other repositories
exam-answer-format
Guidelines for writing exam-style answers in a practical, conversational style with definitions first followed by real-world examples.
lecture-reference-linking
Guidelines for including course materials lists and inline references when writing exam answers or documentation that references course materials.
mermaid-diagrams
Guidelines for adding Mermaid diagrams to exam answers and documentation with automatic SVG generation support.
short-answer-version
Guidelines for creating short/concise versions of detailed answers.
documentation-formatting
Guidelines for formatting markdown documentation to improve readability and scannability.
human-writing-style
Rules for writing naturally and authentically - avoid robotic AI tone in documentation, code comments, error messages, and explanations. Write like a human colleague, not a customer service bot.