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.
git clone --depth 1 https://github.com/wufunc/novaWrote 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/wufunc/nova/cursor-rule-snippet)<a href="https://agentmods.dev/rules/wufunc/nova/cursor-rule-snippet"><img src="https://agentmods.dev/badge/rules/wufunc/nova/cursor-rule-snippet/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/wufunc/nova/cursor-rule-snippet"><img src="https://agentmods.dev/badge/rules/wufunc/nova/cursor-rule-snippet.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00534 | $0.00534 |
| Opus 5.5 | $0.00214 | $0.00214 |
| Sonnet 5.5 | $0.00107 | $0.00107 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
cursor-rule-snippet 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Management
Session Initialization
At the start of each session:
- Read
~/.nova/constitution.md- personal principles and constraints - Read
.nova/constitution.md- project principles and constraints - Judge whether the task needs memory context. Load memory for non-trivial, multi-step, multi-file, history-sensitive, preference-sensitive, or uncertain work. Skip session memory for simple self-contained tasks that can be completed safely from the user's message and immediate local context.
- When memory is needed, perform ALL of these in parallel:
- Read
~/.nova/memory/user.md- user identity and collaboration preferences - Read
.nova/memory/arch.md- project architecture overview - Read
~/.nova/memory/memory.md- curated long-term personal memory /memory recall- search relevant experience from project history (DevLog, ADR) and personal notes based on the user's request
- Read
- If you initially skip memory loading and later realize more context is needed, load it before proceeding.
If a file doesn't exist, skip it.
Snapshot memory is not part of this on-demand durable path. Only use /memory snapshot-recall when the user explicitly asks to search historical sessions or past Q&A.
Explicit Remember
When the user explicitly asks you to remember something ("remember this", "请记住", "以后默认", "别忘了"), execute /memory remember.
This path must first inspect user.md, memory.md, and relevant notes/. If the requested memory is clearly project-related, also inspect project arch.md, ADR, and DevLog before writing.
Reflect
Use /memory reflect to capture insights from non-coding sessions (research, troubleshooting, system administration).
Constitution Protocol
CRITICAL: You MUST read constitution files to understand governing principles before proposing or implementing any solution:
~/.nova/constitution.md- personal principles (if exists).nova/constitution.md- project principles (if exists)
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.
- 1mo ago First seen · 51 lines · 534 tokens per session scan A 39e9e3481426
cursor-rule-snippet is a cursor rule published in the GitHub repository wufunc/nova (2 stars, last pushed 6mo ago), licensed MIT. It adds 534 tokens to every session, about $0.0021 per session on Opus 5.5. 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
search-routing
Smart Search Routing — always use QMD semantic search when available, never bypass with grep for vault content.
context-discipline
Manage AI context window efficiently - read before write, no re-reads, tool-call budgets, one-pass discipline.
context-management
Context window management — prevents AI from losing track during long sessions.
archcore-context
Archcore knowledge base context — document types, MCP tools, and conventions for working with .archcore/ documents.
demo-consume-context
Worked example that discovers, loads, and tags a context package per CONSUMING-CONTEXT-PACKAGE.md, then writes a reverse-index addendum — proves the produce/consume/tag loop end-to-end. Do NOT use for real feature work.
tell-plumbing-reference
Peer plumbing reference memory for platform/MCP/auth/design-flow plans — never name the peer in commits.