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/sagar25-code-it/ps3d-cad-studio/coding-standardsgit clone --depth 1 https://github.com/sagar25-Code-it/ps3d-cad-studioWhat 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 | $0.00821 | $0.00821 |
| Opus 5 | $0.00411 | $0.00411 |
| Sonnet 5 | $0.00164 | $0.00164 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
coding-standards 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
PS3D coding standards
codingStandards:
languages:
TypeScript:
version: "7.0.2"
rules:
- strict mode with exact optional properties and unchecked-index protection
- ES modules with explicit .js import suffixes
- immutable readonly domain records unless mutation is private and contained
- no any, dynamic evaluation, or silent schema coercion in model boundaries
JavaScript:
version: ES2023
rules:
- build and verification scripts use Node built-ins where practical
CSS:
rules:
- original project-owned tokens and responsive accessible layouts
frameworks:
React:
version: 19.2.8
rules:
- functional components and accessible native controls
- keep domain logic outside presentation components
Three.js:
version: 0.185.1
rules:
- disposable viewport adapter only; never authoritative model state
Vite:
version: 7.3.6
rules:
- enforce production geometry and Node-server boundaries and include license artifacts
MCP:
version: "2.0.0"
rules:
- keep transport code in apps/mcp-server and pure tool semantics in packages/workbench-mcp
- expose no filesystem, network, environment-secret, credential, or hidden-state behavior
- require preview, matching receipt, and explicit confirmation before returning a mutated project
testing:
framework: project-owned typed test harness
runner: TypeScript compiler followed by Node execution
location: tests
requirements:
- New model, constraint, geometry, persistence, protocol, export, and automation behavior requires independently derived tests
- Tests use neutral requirements, mathematics, approved standards, or original synthetic cases
- Boundary, failure, retry, determinism, and rollback cases accompany happy paths
- Browser-visible workflows receive an executing Chromium smoke test before release review
coverage:
tool: requirement-traceability plus executed assertions
threshold: null
naming:
commits: conventional with accurate Signed-off-by only from the actual contributor
packages: workspace packages under packages/*; UI modules under apps/studio-web/src
stableIds: lower-case namespace colon identifier
review:
blockingSeverities: [BLOCKER]
strictReview: true
dimensions:
- neutral requirement traceability
- independent authorship and provenance
- semantic and numerical correctness
- worker and transaction safety
- security and privacy
- accessibility and original UI identity
- performance and resource limits
- determinism and reproducibility
- maintainability and entropy
securityChecks:
- exact schemas and size or count limits on untrusted inputs
- no secrets, private keys, credentials, personal data, or .env contents
- no dynamic code evaluation, remote code, or unapproved production WASM
- dependency, license, integrity, notice, vulnerability, and production-graph reconciliation
- exact lockfile-to-provenance inventory reconciliation
entropy:
enabled: true
policy: remove-on-touch
onChange:
- remove unused symbols and commented-out code
- delete superseded paths when replacing behavior
- remove orphaned tests and configuration keys
- keep source modules focused and below 500 lines where practical
blockReview:
- new commented-out code without a tracked reason
- parallel superseded implementation left in the diff
- unsupported feature represented as if it were implemented
- untraceable generated or copied material
reference: INDEPENDENT_DEVELOPMENT.md
documentation:
sdlcArtifacts: docs/sdlc/{workflowId}/
projectGuide: CONTRIBUTING.md
stackRules: []
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 · 106 lines · 821 tokens per session scan A 215926984548
coding-standards is a cursor rule published in the GitHub repository sagar25-Code-it/ps3d-cad-studio (0 stars, last pushed 2d ago), licensed MIT. It adds 821 tokens to every session, about $0.0041 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-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.
family-instance-domain-actions
Family instance domain action implementation patterns.