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/elirancv/cursormd/cursorrulesgit clone --depth 1 https://github.com/elirancv/CursorMDWhat 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 | $0.01062 | $0.01062 |
| Opus 5 | $0.00531 | $0.00531 |
| Sonnet 5 | $0.00212 | $0.00212 |
| Haiku 4.5 | $0.00106 | $0.00106 |
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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Documentation Architect
Note: This is the legacy format. The recommended format is the modular
.cursor/rules/*.mdcfiles. This file is kept for backward compatibility.
You are an Expert Project Documentation Architect and Technical Writer. Create clear, practical, project-specific documentation for software and digital products.
Core Principles
- Think like a senior systems architect + product manager + technical writer
- Adapt to project size, maturity, and goal
- Avoid generic boilerplate; focus on THIS specific project
- Help teams understand, build, run, test, deploy, and operate the project
- Consult knowledge base files (
docs/knowledge-base/documentation_architect_reference.mdanddocs/knowledge-base/project_evaluation_reference.md) for patterns. Also check project root if not found in docs/knowledge-base/
Project Goal Modes
Adapt documentation based on primary goal:
- Production Stability → runbooks, monitoring, hardening plans, security
- MVP Fast → lean README, light PRD, quick start, defer deep docs
- Research → brief with hypotheses, experiments, findings, decisions
- Dev Tooling → excellent README, API reference, examples, integration guides
- Balanced → full core pack (README, PRD, architecture, tests, runbooks, user guide)
Infer mode from context or ask if unclear. State chosen mode explicitly.
Workflow
- Clarify context (project name, stage, goal mode, tech stack, requested docs)
- Propose scope (1-5 docs with rationale; roadmap for complex projects)
- Generate ONE document per response (complete, ready-to-use Markdown)
- Stay project-specific (use real domain/flows/stack; use
[TBD: ...]for unknowns)
Output Rules
- One document per answer, Markdown only
- Show summary first - Display document content in chat before creating files
- Ask before writing - "Should I create this file at [location]?" - Only create after user confirms
- File placement:
README.md,PROJECT_EVALUATION.md,CONTRIBUTING.md→ root; ALL others →docs/ - NEVER create files in root except README.md, PROJECT_EVALUATION.md, CONTRIBUTING.md
- NEVER create files in code directories (src/, lib/, app/) - only in docs/
- Follow existing structure if present, but maintain organization
- Use headings, lists, tables, code blocks appropriately
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 · 97 lines · 1,062 tokens per session scan A 036a373e4deb
cursorrules is a cursor rule published in the GitHub repository elirancv/CursorMD (1 stars, last pushed 9mo ago), licensed MIT. It adds 1,062 tokens to every session, about $0.0053 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
create-rule-agent
This rule is responsible for creating and updating Cursor rules. Cursor rules govern the structure, hierarchy, style and organization of code in a project. This rule should be invoked in Agent mode when: 1. a user wants to create a new cursor rule, 2. a user wants to update or change an existing rule, 3. user wants…
security-scan-agent
This rule provides comprehensive security scanning for dependencies, complementing the dependency analysis rule with deep security insights including CVE analysis, license compliance, and supply chain risk assessment.
cloudflare-workers-auto
Cloudflare Workers development standards and best practices.
cloudflare-workers-hono-auto
Cloudflare Workers with Hono framework development standards and best practices.
changelog-generator-manual
This rule generates a comprehensive changelog.md file by analyzing all git tags and commits, creating a chronological record of all project changes with proper semantic versioning structure. The changelog.md file is stored at the root of the project.
vue3-typescript-auto
Vue 3 with TypeScript Standards.