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/jignesh-ponamwar/skills-mcp/cursorrulesgit clone --depth 1 https://github.com/Jignesh-Ponamwar/skills-mcpWrote 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/jignesh-ponamwar/skills-mcp/cursorrules)<a href="https://agentmods.dev/rules/jignesh-ponamwar/skills-mcp/cursorrules"><img src="https://agentmods.dev/badge/rules/jignesh-ponamwar/skills-mcp/cursorrules.svg" alt="Measured on agentmods" 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 | $0.00680 | $0.00680 |
| Opus 5 | $0.00340 | $0.00340 |
| Sonnet 5 | $0.00136 | $0.00136 |
| Haiku 4.5 | $0.00068 | $0.00068 |
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 4d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill MCP — Cursor Rules
─────────────────────────────────────────────────────────────────────────────
This project uses a Skill MCP server: a curated registry of expert instruction
sets for common AI tasks. Always consult it before starting non-trivial work.
MCP server URL (SSE): https://skill-mcp..workers.dev/sse
─────────────────────────────────────────────────────────────────────────────
Skill MCP Usage Rules
When to check for skills
Check for a relevant skill at the START of any non-trivial task:
- Writing or reviewing code
- Writing or running tests
- Analysing data (CSV, SQL, PDF)
- Writing docs (README, commits, API specs)
- Web scraping or API integration
- Creating structured documents
Workflow (always in this order)
STEP 1 — Discover: Call: skills_find_relevant(query="", top_k=5)
- score > 0.6 → strong match — load instructions (Step 2)
- score 0.4–0.6 → read description, decide whether to proceed
- score < 0.4 → no matching skill — proceed without one
STEP 2 — Load instructions: Call: skills_get_body(skill_id="<best match from Step 1>")
- Read and apply the returned
instructionsfield - Note the
tier3_manifest— lists supplementary files (references, scripts, assets) - Optional: skills_get_options(skill_id) if user asks about customisation
STEP 3 — Supplementary resources (ONLY if instructions explicitly reference a file): Reference docs: skills_get_reference(skill_id, filename="<file.md>") Helper scripts: skills_run_script(skill_id, filename="<script.py>", input_data={}) Templates/assets: skills_get_asset(skill_id, filename="<template.md>") Manifest first: pass filename="list" to any Tier 3 tool to see what's available
Rules — MUST follow
- DO check skills at the start of non-trivial tasks
- DO write specific queries: "write pytest tests for Flask REST API" not "testing"
- DO follow skill instructions precisely — they encode expert knowledge
- DO incorporate system_prompt_addition from skills_get_body into your context
- DO NOT load Tier 3 resources unless instructions explicitly reference them by name
- DO NOT guess skill_ids — always use skills_find_relevant first
- DO NOT skip Step 1 even if you think you know what skill to use
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.
- 4d ago First seen · 62 lines · 680 tokens per session scan A df9e9e0e9b92
cursorrules is a cursor rule published in the GitHub repository Jignesh-Ponamwar/skills-mcp (7 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 680 tokens to every session, about $0.0034 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
frontend-architecture
Vite + React SPA architecture - directory layout, providers, bundle splitting. Tailwind styling in tailwind.mdc.
turborepo
Turbo query graph primitives and signed remote-cache key provisioning.
langchain
LangChain: chains, agents, memory, tools.
head-of-product
Head of Product persona — planning, user stories, UX decisions, scope guardian. Use when discussing product strategy, PRDs, user research, feature proposals, or backlog prioritization.
bash-style
Bash 核心规范：禁止行尾注释、文件写入用 tee、Heredoc 默认禁止变量展开.
chinese-language
CRITICAL: You MUST respond in Simplified Chinese at ALL times unless explicitly requested otherwise. 回复、注释、commit message 使用简体中文。技术术语保持英文原文。.