auto-agent

A set of rules for choosing agent behavior based on a message’s starting keyword, such as PLAN, ACT, EVAL, or AUTO. It also maps file types and topics to recommended specialist agents.

In plain words
What is it for?
Use it to route coding tasks to suitable agents and tools based on the request, files involved, or subject area.
Why use it?
It gives an agent a repeatable way to select a mode and delegate work. This reduces guesswork when a task involves frontend, backend, DevOps, security, accessibility, testing, or architecture.

Cursor rule for Cursor

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/jeremydev87/codingbuddy/auto-agent
Clone the repo
git clone --depth 1 https://github.com/JeremyDev87/codingbuddy

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 1,696 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.01696
Opus 5 $0.00000 $0.00848
Sonnet 5 $0.00000 $0.00339
Haiku 4.5 $0.00000 $0.00170

Measured yesterday against content hash 79b03f8bf2af, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auto-agent 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.

.cursor/rules/auto-agent.mdc · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

codingbuddy Agent System

Required: Mode Keyword Detection

When user message starts with PLAN, ACT, EVAL, AUTO (or localized variants: 자동, 自動, 自动, AUTOMÁTICO):

Immediately call parse_mode MCP tool

File Context → Agent Mapping

File Pattern Recommended Agent MCP Call
*.tsx, *.ts frontend-developer get_agent_details("frontend-developer")
*.go, *.py, *.java, *.rs backend-developer get_agent_details("backend-developer")
Dockerfile, *.yml devops-engineer get_agent_details("devops-engineer")
*.json (agents/) agent-architect get_agent_details("agent-architect")

Specialist Auto-Recommendation

Detected Topic Recommended Specialist
Security, auth, XSS, CSRF security-specialist
Accessibility, ARIA, a11y, WCAG accessibility-specialist
Performance, bundle, optimization performance-specialist
Testing, TDD, coverage test-strategy-specialist
Architecture, layers, dependencies architecture-specialist

Pre-Analysis

Before starting specialist analysis, optionally call analyze_task MCP tool for:

  • Risk assessment of the current task
  • Recommended specialists (may differ from file-pattern defaults)
  • Contextual checklists

Specialist Execution Pattern

When parse_mode returns parallelAgentsRecommendation:

  1. Call prepare_parallel_agents MCP tool with the recommended specialists
  2. Execute each specialist sequentially (one at a time):
    • Announce: "🔍 Analyzing from [icon] [specialist-name] perspective..."
    • Apply specialist system prompt to analyze target code
    • Record findings
  3. Present consolidated findings summary

See packages/rules/.ai-rules/adapters/cursor.md for full details.

Available Agents

Agent Description Expertise
Accessibility Specialist Accessibility expert for Planning, Implementation, and Evaluation modes - unified specialist for WCAG 2.1 AA compliance, ARIA attributes, and keyboard navigation
Act Mode Agent ACT mode agent - specialized for actual implementation execution
Agent Architect Primary Agent for creating, validating, and managing AI agent configurations
AI/ML Engineer AI/ML expert for Planning, Implementation, and Evaluation modes - unified specialist for LLM integration, prompt engineering, RAG architecture, AI safety, and testing non-deterministic systems
Architecture Specialist Architecture expert for Planning, Implementation, and Evaluation modes - unified specialist for layer placement, dependency direction, and type safety
Auto Mode Agent AUTO mode agent - autonomous PLAN → ACT → EVAL cycle until quality targets met
Backend Developer Language-agnostic backend specialist with Clean Architecture, TDD, and security focus. Supports Node.js, Python, Go, Java, and other backend stacks.
Code Quality Specialist Code quality expert for Planning, Implementation, and Evaluation modes - unified specialist for SOLID principles, DRY, complexity analysis, and design patterns
Code Reviewer Senior software engineer specializing in comprehensive code quality evaluation and improvement recommendations
Data Engineer Data specialist focused on database design, schema optimization, migrations, and analytics query optimization. Handles data modeling, ETL patterns, and reporting data structures.
Data Scientist Data science specialist for exploratory data analysis, statistical modeling, ML model development, and data visualization. Handles EDA, feature engineering, model training, and Jupyter notebook development.
DevOps Engineer Docker, Datadog monitoring, and Next.js deployment specialist
Documentation Specialist Documentation expert for Planning, Implementation, and Evaluation modes - unified specialist for documentation planning, code comments, type definitions, and documentation quality assessment
Eval Mode Agent EVAL mode agent - specialized for code quality evaluation and improvement suggestions
Event Architecture Specialist Event-driven architecture specialist for Planning, Implementation, and Evaluation modes - unified specialist for message queues, event sourcing, CQRS, real-time communication, distributed transactions, and event schema management
Frontend Developer Modern React/Next.js specialist with Server Components/Actions, TDD, and accessibility focus
i18n Specialist Internationalization expert for Planning, Implementation, and Evaluation modes - unified specialist for i18n library setup, translation key structure, formatting, and RTL support
Integration Specialist External service integration specialist for Planning, Implementation, and Evaluation modes - unified specialist for API integrations, webhooks, OAuth flows, and failure isolation patterns
Migration Specialist Cross-cutting migration coordinator for legacy system modernization, framework upgrades, database migrations, and API versioning - unified specialist for Strangler Fig, Branch by Abstraction, and zero-downtime migration patterns
Mobile Developer Cross-platform and native mobile specialist supporting React Native, Flutter, iOS (Swift/SwiftUI), and Android (Kotlin/Compose). Focuses on mobile-specific patterns, performance, and platform guidelines.
Observability Specialist Observability expert for Planning, Implementation, and Evaluation modes - unified specialist for vendor-neutral monitoring, distributed tracing, structured logging, SLI/SLO frameworks, and alerting patterns
Parallel Orchestrator Orchestrates parallel execution of multiple GitHub issues using taskMaestro with file-overlap validation, Wave grouping, and AUTO mode workers
Performance Specialist Performance expert for Planning, Implementation, and Evaluation modes - unified specialist for bundle size optimization, rendering optimization, and Core Web Vitals
Plan Mode Agent PLAN mode agent - specialized for work planning and design
Plan Reviewer Reviews implementation plans for quality, completeness, and feasibility before execution
Platform Engineer Cloud-native infrastructure expert for Planning, Implementation, and Evaluation modes - unified specialist for Infrastructure as Code, Kubernetes orchestration, multi-cloud strategy, GitOps workflows, cost optimization, and disaster recovery
Security Engineer Primary Agent for implementing security features, fixing vulnerabilities, and applying security best practices in code
Security Specialist Security expert for Planning, Implementation, and Evaluation modes - unified specialist for authentication, authorization, and security vulnerability prevention
SEO Specialist SEO expert for Planning, Implementation, and Evaluation modes - unified specialist for metadata, structured data, and search engine optimization
Software Engineer General-purpose implementation engineer — any language, any domain, TDD-first
Solution Architect High-level system design and architecture planning specialist
Systems Developer Primary Agent for systems programming, low-level optimization, native code development, and performance-critical implementations
Technical Planner Low-level implementation planning with TDD and bite-sized tasks
Test Engineer Primary Agent for TDD cycle execution, test writing, and coverage improvement across all test types
Test Strategy Specialist Test strategy expert for Planning, Implementation, and Evaluation modes - unified specialist for TDD vs Test-After decisions, test coverage planning, and test quality assessment
Tooling Engineer Project configuration, build tools, and development environment specialist
UI/UX Designer UI/UX design specialist based on universal design principles and UX best practices - focuses on aesthetics, usability, and user experience rather than specific design system implementations

Read the full file on GitHub · 108 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. yesterday First seen · 108 lines · 0 tokens per session scan A 79b03f8bf2af

Subscribe to this mod's changes

auto-agent is a cursor rule published in the GitHub repository JeremyDev87/codingbuddy (31 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,696 tokens. 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 2026-08-30.