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 skills/adilkalam/orca/cursor-code-stylenpx skills add adilkalam/orca --skill cursor-code-stylegit clone --depth 1 https://github.com/adilkalam/orcaWhat 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 | $0.00036 | $0.01230 |
| Opus 5 | $0.00018 | $0.00615 |
| Sonnet 5 | $0.00007 | $0.00246 |
| Haiku 4.5 | $0.00004 | $0.00123 |
Grade A, and why
cursor-code-style 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.
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cursor Code Style
Rules extracted from Cursor Agent prompt for consistent, high-quality code.
Variable Naming
DO:
- Use descriptive names that reveal intent
- Functions should be verbs/verb-phrases:
getUserById,calculateTotal,validateInput - Variables should be nouns/noun-phrases:
userCount,totalPrice,validationResult - Use consistent naming conventions per language (camelCase for JS/TS, snake_case for Python)
DON'T:
- Never use 1-2 character variable names (EXCEPTION: loop counters
i,j,kand coordinatesx,y) - Avoid abbreviations unless universally understood:
genYmdStr->generateDateString - Don't use generic names:
data,info,temp,resultwithout context
Examples
Bad: const d = getData()
Good: const userProfile = fetchUserProfile()
Bad: function proc(x) { ... }
Good: function processPayment(transaction) { ... }
Bad: let n = users.length
Good: let userCount = users.length
Control Flow
DO:
- Use guard clauses and early returns to reduce nesting
- Handle error and edge cases FIRST, then happy path
- Keep nesting to 2-3 levels maximum
- Prefer
switchor object lookup over longif-elsechains
DON'T:
- Create deeply nested if/else chains (>3 levels)
- Put the happy path inside nested conditions
- Use
elseafter areturnstatement
Examples
// BAD: Deep nesting
function processUser(user) {
if (user) {
if (user.isActive) {
if (user.hasPermission) {
// happy path buried 3 levels deep
return doWork(user)
}
}
}
return null
}
// GOOD: Guard clauses
function processUser(user) {
if (!user) return null
if (!user.isActive) return null
if (!user.hasPermission) return null
return doWork(user) // happy path at top level
}
Comments
DO:
- Add comments for complex code explaining "why" not "how"
- Document non-obvious business rules
- Use JSDoc/docstrings for public APIs
- Comment regex patterns with what they match
DON'T:
- Add comments for trivial or obvious code
- Leave TODO comments (implement the fix instead)
- Write comments that restate the code
- Use comments to disable code (delete it or use version control)
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 · 197 lines · 36 tokens per session scan A a05e28229b92
cursor-code-style is a skill published in the GitHub repository adilkalam/orca (2 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 1,230 once invoked, about $0.0002 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.