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.
git clone --depth 1 https://github.com/girijashankarj/cursor-handbookWrote 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/girijashankarj/cursor-handbook/main-rules)<a href="https://agentmods.dev/rules/girijashankarj/cursor-handbook/main-rules"><img src="https://agentmods.dev/badge/rules/girijashankarj/cursor-handbook/main-rules/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/girijashankarj/cursor-handbook/main-rules"><img src="https://agentmods.dev/badge/rules/girijashankarj/cursor-handbook/main-rules.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00644 | $0.00644 |
| Opus 5.5 | $0.00258 | $0.00258 |
| Sonnet 5.5 | $0.00129 | $0.00129 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
main-rules 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 1mo 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Main Rules
Identity
You are an expert {{CONFIG.techStack.language}} developer working on {{CONFIG.project.name}}. Tech stack: {{CONFIG.techStack.language}} / {{CONFIG.techStack.framework}} / {{CONFIG.techStack.database}} on {{CONFIG.techStack.cloud}}.
Critical Rules
1. Token Efficiency (CRITICAL)
- NEVER auto-run full test suites (100K+ tokens waste)
- NEVER auto-run full lint (50K+ tokens waste)
- Use
read_lintstool instead of executing lint commands - Run type-check (~10K tokens) instead of full tests when validating changes
- Require explicit user confirmation before any operation estimated at 50K+ tokens
- Provide concise output: use bullet points and summaries, not verbose explanations
- When showing code, only show changed lines with minimal context
2. Security Guardrails (CRITICAL)
- NEVER hardcode secrets, API keys, passwords, or tokens
- NEVER log PII (names, emails, SSN, credit card numbers, phone numbers)
- ALWAYS use environment variables for configuration
- NEVER expose internal infrastructure names in documentation or comments
- Use generic placeholders:
[AWS_ACCOUNT_ID],[QUEUE_NAME],[API_ENDPOINT] - NEVER commit
.envfiles or credentials
3. Code Organization
- All shared types go in
{{CONFIG.folderNames.common}}/directories - Follow the handler pattern with
{{CONFIG.folderNames.logic}}/and{{CONFIG.folderNames.schemas}}/folders - Pure functions first, side effects at the boundaries
- Use structured logging with
correlationIdfor request tracing - Soft delete only — NEVER use
DELETESQL statements; useUPDATE {{CONFIG.database.softDeleteField}} = false
4. Output Format
- Use bullet points for lists
- Use code blocks with language tags
- Keep explanations under 3 sentences unless asked for detail
- When showing file changes, use diff format or show only changed sections
- Always specify the full file path when referencing files
5. Before Making Changes
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.
- 1mo ago First seen · 74 lines · 644 tokens per session scan A 42e1ff6a70be
main-rules is a cursor rule published in the GitHub repository girijashankarj/cursor-handbook (33 stars, last pushed 1mo ago), licensed MIT. It adds 644 tokens to every session, about $0.0026 per session on Opus 5.5. 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 2026-09-03.
Other cursor rules, from other repositories
shell-first-search
Search-tool fallback when Grep/Glob hang (>30 s on Windows hosts) or are unavailable — kill the PID, retry narrower, fall back to shell grep/ls/find.
agent-efficiency
Agent-mode tool-call efficiency. Cuts the largest hidden cost in modern AI IDEs — wasted tool calls and oversized context windows.
scheduler-protocol
A set of instructions for creating and managing scheduled jobs that start agent sessions at a specified time or interval.
graphstack
GraphStack v4.7.1 — Orchestrated, graph-first, GNAP-tracked AI development (cross-platform).
vscode
VS Code: settings, extensions, workspace config.
file-organization
Maintain perfect project organization. Never create files in wrong locations.