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/bahulneel/agent-brain-trust/naminggit clone --depth 1 https://github.com/bahulneel/agent-brain-trustWrote 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/bahulneel/agent-brain-trust/naming)<a href="https://agentmods.dev/rules/bahulneel/agent-brain-trust/naming"><img src="https://agentmods.dev/badge/rules/bahulneel/agent-brain-trust/naming.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 | $0.01254 | $0.01254 |
| Opus 5 | $0.00627 | $0.00627 |
| Sonnet 5 | $0.00251 | $0.00251 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
naming 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 5d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Naming & Construction Style Guide
1. General Rules
- camelCase: Use for variables, functions, constants, and modules.
- PascalCase: Use for classes, components, and exported namespaces that contain domain values or helpers.
- kebab-case: Use for file names.
- Organisational Namespaces: These must stay camelCase as they exist to mirror the filesystem taxonomy and provide structure rather than collecting type-specific values.
- Structure: Prefer a domain/sub-domain taxonomical structure over use-case organisation.
- Mononyms: Use singular mononyms for the filenames of components and pages. The component name itself must be the PascalCase join of its path parts to ensure uniqueness and context.
2. Visual Distinction & Privacy
- Domain Language: Use PascalCase for constants and namespaces that define the vocabulary of the domain.
- Infrastructure, Global, & Symbolic: Use UPPER_SNAKE_CASE for environment-specific values, application-wide "universal truths", or abstract tokens used for logic branching.
- All Other Identifiers: Use camelCase for everything else, including organisational namespaces and general variables.
- Privacy: Use the
#prefix for private members. The_prefix is reserved exclusively for unused function arguments. Any other non-argument identifier starting with_should be removed.
3. Eliminating Nominative Redundancy
Do not repeat context provided by the file path, object, or scope.
- Entry Points: Prefer single, generic entry points within a specific scope.
- Members: Member functions should not repeat the name of the object or class they belong to.
- Scope: In a non-conflicting scope, use the simplest name available.
- Auto-Import Caveat: Do not introduce redundant specificity prematurely to avoid potential auto-import collisions. Naming should remain minimal by default; address collisions only when they occur in practice.
4. Relational & Functional Naming
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.
- 5d ago First seen · 87 lines · 1,254 tokens per session scan A fee4b759469e
naming is a cursor rule published in the GitHub repository bahulneel/agent-brain-trust (5 stars, last pushed 4mo ago), licensed MIT. It adds 1,254 tokens to every session, about $0.0063 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
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-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.