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/sunmh207/entire-dashboard/entitygit clone --depth 1 https://github.com/sunmh207/entire-dashboardWhat 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 | $0.00458 |
| Opus 5 | $0.00000 | $0.00229 |
| Sonnet 5 | $0.00000 | $0.00092 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
entity 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.
What it actually says
Entity Development Guidelines
For an example of an Entity class, refer to the Reop entity (src/main/java/com/mzfuture/entire/gitrepo/entity/Reop.java).
1. Basic Requirements
All Entity classes must inherit from BaseEntity. The BaseEntity already defines several common fields: id, createdAt, and updatedAt.
2. Naming Conventions
2.1. Class Name and Table Name
- Entity class names must be singular business nouns, such as
Reop. - In most cases,
@Tableis not required. The default JPA naming strategy will automatically map the class name to a lowercase table name separated by underscores. For example, the class namePushReviewLogwill be automatically mapped topush_review_log.
2.2. Field Names
- Field names must follow Java naming conventions (
lowerCamelCase). - Normally, the
@Columnannotation should not be used. Let JPA automatically map the field names according to the naming strategy.
3. Annotation Guidelines
- The
@Builderannotation is not allowed in Entity classes. - For enum types, the annotation
@Enumerated(EnumType.STRING)must be used. UsingORDINALis strictly prohibited. - JPA relationship annotations such as
@ManyToOne,@OneToMany,@OneToOne, and@ManyToManyare not allowed. - Avoid using
@Tableand@Columnannotations unless absolutely necessary.
4. Commenting Guidelines
- Both class names and field names must include comments.
5. Behavioral Guidelines
- Simple domain behaviors are allowed, such as
isActive()andgetFullName(). - The following behaviors are prohibited:
- Business process logic
- Calling
Repository,Service, or other external components
6. Migration Guidelines
- When creating or modifying an Entity class, a corresponding Migration script must also be created.
- Migration scripts must follow the Migration Script Guidelines.
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 · 47 lines · 458 tokens per session scan A e350e15b9f15
entity is a cursor rule published in the GitHub repository sunmh207/entire-dashboard (24 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 458 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
engine-internals
Coding Agent engine implementation details (Cursor + Claude Code) — reference when modifying engine.ts or debugging Agent behavior.
testing-conventions
Testing conventions — must reference when modifying src/ code or tests.
architecture-constraints
GolemBot architecture hard constraints — must check before modifying any src/ code.
dual-memory
Use both semantic (qdrant-find) and structural (graphify) memory before non-trivial code changes.
skill-conventions
Project conventions for creating and editing Obsidian vault skills.
skill-registry
When a skill is created, renamed, or deleted, update the skill registry.