agentmods.dev

instructions

instructions is a cursor rule for Cursor from VoTruongDanh/Skills-Agent. It costs 1,584 tokens per session, scanned A, original, MIT.

A request-routing rule set for an AI coding assistant. It checks each request, selects a matching specialist skill, and uses project memory when available.

In plain words
What is it for?
It helps route coding, planning, memory, and other tasks to defined skills or agents, while handling greetings and empty requests separately.
Why use it?
It gives repeated requests a consistent handling process and helps preserve context between sessions.

Cursor rule for Cursor

not rated 2 yesterday A scan 1,584 tokens original MIT
View the source file VoTruongDanh/Skills-Agent
Install

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.

agentmods
npx agentmods add rules/votruongdanh/skills-agent/instructions
Clone the repo
git clone --depth 1 https://github.com/VoTruongDanh/Skills-Agent

Made for: Cursor.

Wrote 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.

agentmods badge for instructions

README.md
[![agentmods](https://agentmods.dev/badge/rules/votruongdanh/skills-agent/instructions.svg)](https://agentmods.dev/rules/votruongdanh/skills-agent/instructions)
Your own site
<a href="https://agentmods.dev/rules/votruongdanh/skills-agent/instructions"><img src="https://agentmods.dev/badge/rules/votruongdanh/skills-agent/instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,584 This file is loaded in full into every session.
When invoked 1,584 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01584 $0.01584
Opus 5 $0.00792 $0.00792
Sonnet 5 $0.00317 $0.00317
Haiku 4.5 $0.00158 $0.00158

Measured 5d ago against content hash bf5963368bdc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

instructions 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 5d 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.

.cursor/rules/instructions.mdc · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Agent Skills — System Bootstrap

This project uses an AI Skills system with 16 skills, 11 specialist agents, and a memory protocol.

On EVERY request, follow this flow:

  1. Validate input:

    • If the message is empty or contains no meaningful content → Respond with a friendly greeting, list the available skills below with one-line descriptions, and ask what the user would like to work on. Do NOT proceed to classification.
    • If the message is a greeting ("hi", "hello", "hey", "xin chào", "chào") → Respond warmly, briefly list what you can help with (the skills below), and ask how you can help. Do NOT proceed to classification.

  2. Read memory:

    • If .ai-memory.md exists in project root, read it first for context.
    • If Codex memory directories exist (memories/, memories/session/, memories/repo/), read relevant notes from memories/repo/.
    • If .ai-memory.md doesn't exist, create it after completing the first task using the template at the end of this file.

  3. Classify the request — Match to one of these skills:

    Command Skill file to read When to use
    /brainstorm .kiro/skills/brainstorm/SKILL.md Explore options, ideate solutions
    /plan .kiro/skills/plan/SKILL.md Create implementation plan with milestones
    /create .kiro/skills/create/SKILL.md Build new feature/file/component
    /debug .kiro/skills/debug/SKILL.md Fix bugs, analyze errors
    /test .kiro/skills/test/SKILL.md Write tests, improve coverage
    /enhance .kiro/skills/enhance/SKILL.md Improve existing code without breaking it
    /deploy .kiro/skills/deploy/SKILL.md Deployment and release guidance
    /clean .kiro/skills/clean/SKILL.md Remove junk files, clean up
    /status .kiro/skills/status/SKILL.md Project status summary
    /preview .kiro/skills/preview/SKILL.md Preview output/UX before implementing
    /orchestrate .kiro/skills/orchestrate/SKILL.md Coordinate multi-step workflows
    /ui-ux-pro-max .kiro/skills/ui-ux-pro-max/SKILL.md Advanced UI/UX improvements
    /motion-ui .kiro/skills/motion-ui/SKILL.md Motion UI with Framer Motion micro-interactions
    /explain .kiro/skills/explain/SKILL.md Explain code, walk through logic, understand architecture
    /integrate .kiro/skills/integrate/SKILL.md Integrate provided sample code with minimal impact

Read the full file on GitHub · 103 lines

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.

  1. 5d ago First seen · 103 lines · 1,584 tokens per session scan A bf5963368bdc

Subscribe to this mod's changes

instructions is a cursor rule published in the GitHub repository VoTruongDanh/Skills-Agent (2 stars, last pushed yesterday), licensed MIT. It adds 1,584 tokens to every session, about $0.0079 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.

Building agents
Related

Other cursor rules, from other repositories

ponytail

Ponytail, lazy senior dev mode. Always pick the simplest solution that works.

DietrichGebert/ponytail · 576 tokens

angular-20

This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.

angular/angular · 0 tokens

dev-standard

Apache Superset development standards and guidelines for Cursor IDE.

apache/superset · 1,147 tokens

cli-error-handling

CLI command error handling patterns.

prisma/orm · 0 tokens

prefer-direct-imports-over-module-mocks

Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.

prisma/orm · 0 tokens

control-plane-descriptors

Control plane descriptor and instance implementation patterns.

prisma/orm · 0 tokens