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/versoxbt/claude-initial-setup/cursorrulesgit clone --depth 1 https://github.com/VersoXBT/claude-initial-setupWhat 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 | $0.01329 | $0.01329 |
| Opus 5 | $0.00665 | $0.00665 |
| Sonnet 5 | $0.00266 | $0.00266 |
| Haiku 4.5 | $0.00133 | $0.00133 |
Grade A, and why
cursorrules 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.
This is a copy
95% identical to claude-initial-setup — 6 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.
How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coding Standards
Immutability
Always create new objects instead of mutating. Use spread operators, structuredClone, or library solutions like immer.
// WRONG
user.name = name;
items.push(newItem);
// CORRECT
const updated = { ...user, name };
const added = [...items, newItem];
const removed = items.filter(x => x.id !== id);
const mapped = items.map(x => x.id === id ? { ...x, ...changes } : x);
Python: Use @dataclass(frozen=True) and replace(). Use tuples and frozensets for immutable collections.
Go: Use value receivers and return new structs.
File Organization
- 200-400 lines per file, 800 max
- Organize by feature/domain, not by type
- Co-locate tests next to source files
- Move to
shared/only when used by 3+ features - No god files (
utils.tswith 40 exports)
Functions
- Under 50 lines each
- No nesting deeper than 4 levels
- Use early returns and guard clauses
Naming
- Variables: describe WHAT (
activeUsers), not HOW (data) - Booleans:
is/has/can/shouldprefix (isActive,hasPermission) - Functions: verb + noun (
getUserById,formatDate,validateEmail) - Collections: plural nouns (
users,orderItems) - Constants:
SCREAMING_SNAKE(MAX_RETRIES,API_BASE_URL) - Language casing: camelCase (JS/TS), snake_case (Python), PascalCase (Go exports)
Git Conventions
Commits
Format: <type>(<scope>): <description>
Types: feat, fix, refactor, docs, test, chore, perf, ci
Rules: imperative mood, lowercase, under 72 chars, no period
Branches
Format: <type>/<ticket>-<description> in kebab-case
Types: feature/, fix/, hotfix/, release/
Pull Requests
- Under 400 lines of changes
- Include summary, changes, test plan
- Squash merge for features, merge commit for releases
- Never force-push during review
Testing
TDD Workflow
- RED: Write failing test
- GREEN: Write minimal code to pass
- REFACTOR: Clean up, keep tests green
- Target 80%+ coverage
Test Structure
- Unit tests co-located:
auth.ts/auth.test.ts - Integration tests:
test/integration/ - E2E tests:
test/e2e/ - Factories for dynamic data, fixtures for static data
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 · 190 lines · 1,329 tokens per session scan A a4b73332b67d
cursorrules is a cursor rule published in the GitHub repository VersoXBT/claude-initial-setup (4 stars, last pushed 3mo ago), licensed MIT. It adds 1,329 tokens to every session, about $0.0066 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to claude-initial-setup, differing in 6 lines, and is treated as a copy.
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.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.