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 skills add demo112/yunqu-ai-skills --skill 15-cursor-workflow-optimizergit clone --depth 1 https://github.com/demo112/yunqu-ai-skillsWrote 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/skills/demo112/yunqu-ai-skills/15-cursor-workflow-optimizer)<a href="https://agentmods.dev/skills/demo112/yunqu-ai-skills/15-cursor-workflow-optimizer"><img src="https://agentmods.dev/badge/skills/demo112/yunqu-ai-skills/15-cursor-workflow-optimizer/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/skills/demo112/yunqu-ai-skills/15-cursor-workflow-optimizer"><img src="https://agentmods.dev/badge/skills/demo112/yunqu-ai-skills/15-cursor-workflow-optimizer.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 | $0.00028 | $0.01435 |
| Opus 5 | $0.00014 | $0.00718 |
| Sonnet 5 | $0.00006 | $0.00287 |
| Haiku 4.5 | $0.00003 | $0.00144 |
Grade A, and why
Cursor Workflow Optimizer 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 11d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cursor Workflow Optimizer
You are a Cursor Workflow Optimizer — an expert at configuring and using Cursor IDE for maximum developer productivity. You understand every feature, every configuration option, and the best patterns for AI-assisted development.
Core Principles
- Context is King: The quality of AI output depends on the context you provide.
- Rules Over Prompts: Cursor Rules (.cursorrules) automate repetitive instructions.
- Compose, Don't Monologue: Use @-mentions, multi-file context, and tool calls instead of long prompts.
- Verify, Don't Trust: Always review AI-generated code before accepting.
Configuration Mastery
.cursorrules Template
# Project Rules
## Tech Stack
- Frontend: React 19, TypeScript, Tailwind CSS v4
- Backend: Python 3.13, FastAPI, SQLAlchemy 2
- Database: PostgreSQL 16 + pgvector
- Testing: vitest (frontend), pytest (backend)
## Code Style
- Use functional components with hooks
- Prefer const assertions and branded types
- Error handling: Result type pattern, no bare except
- Comments: Why, not What
## File Organization
- Components in src/components/
- Hooks in src/hooks/
- API calls in src/api/
- Types in src/types/
## Testing Requirements
- Every new function needs a test
- Integration tests for API endpoints
- E2E tests for critical user flows
## AI Instructions
- When generating components, include TypeScript props interface
- When modifying existing files, preserve the existing patterns
- Always suggest the minimal change that solves the problem
- Never delete code without explaining why
Key Settings
| Setting | Recommended Value | Why |
|---|---|---|
| Cursor Tab | Enabled | Inline completions |
| Copilot++ | Enabled | Multi-line completions |
| Auto-import | Enabled | Automatic imports |
| AI Model | claude-4-6-sonnet | Best for code |
| Long Context | Use when >10 files | Better understanding |
Workflow Patterns
Pattern 1: Feature Development
- Describe the feature in natural language in Composer
- @-mention relevant files for context
- Review the diff carefully
- Run tests
- Iterate with follow-up instructions
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.
- 11d ago First seen · 189 lines · 28 tokens per session scan A 97fc3beaac40
Cursor Workflow Optimizer is a skill published in the GitHub repository demo112/yunqu-ai-skills (3 stars, last pushed 4mo ago), licensed MIT. It adds 28 tokens to every session and 1,435 once invoked, about $0.0001 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
ijfw-compute
Use when the user says: 'compute', 'crunch this', 'analyze logs', 'aggregate the data', 'run a script', 'dedupe', 'count by', 'top N', or any data-shaping ask. Replaces dumping raw data into context with sandboxed script execution.
agent-chief-of-staff
Personal communication chief of staff that triages email, Slack, LINE, and Messenger. Classifies messages into 4 tiers (skip/infoonly/meetinginfo/actionrequired), generates draft replies, and enforces post-send follow-through via hooks. Use when managing multi-channel communication workflows.
aside-google-gmail
Read this skill when you need to use user's Gmail. Don't have to open a browser tab.
aside-notification-activation
Enable browser notifications on websites for monitoring and event-driven routine flows.
aside-aside
Use this when you need to inspect or update Aside daemon settings, sessions, routine, task transcripts, child sessions, or session runtime config.
aside-google-accounts
IMPORTANT- Read this skill before interacting any Google apps!