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.
git clone --depth 1 https://github.com/pueraeternis/agentic-project-templateWrote 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/pueraeternis/agentic-project-template/01-agent-roles-and-skills)<a href="https://agentmods.dev/rules/pueraeternis/agentic-project-template/01-agent-roles-and-skills"><img src="https://agentmods.dev/badge/rules/pueraeternis/agentic-project-template/01-agent-roles-and-skills/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/rules/pueraeternis/agentic-project-template/01-agent-roles-and-skills"><img src="https://agentmods.dev/badge/rules/pueraeternis/agentic-project-template/01-agent-roles-and-skills.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 | $0.00896 | $0.00896 |
| Opus 5 | $0.00448 | $0.00448 |
| Sonnet 5 | $0.00179 | $0.00179 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
01-agent-roles-and-skills 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 12d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Roles and Skills
This repository defines specialized engineering roles and reusable skills.
A role defines who owns a lifecycle stage.
A skill defines how that stage is executed.
Every significant task should start by identifying:
- the lifecycle stage;
- the appropriate role;
- the corresponding skill;
- the expected repository artifact.
Lifecycle Model
Project Discovery
↓
Roadmap Creation
↓
Architecture Design
↓
Engineering Design
↓
Repository Initialization
↓
Plan Creation
↓
Plan Review
↓
Plan Implementation
↓
Code Review
↓
Progress Update
Available Roles
| Role | Primary Responsibility | Skill |
|---|---|---|
| Discovery Agent | Define project vision and scope | skills/project-discovery/ |
| Roadmap Agent | Define project evolution strategy | skills/roadmap-creation/ |
| Architecture Agent | Design system architecture | skills/architecture-design/ |
| Engineering Agent | Define engineering decisions | skills/engineering-design/ |
| Initialization Agent | Initialize repository from approved documentation | skills/repository-initialization/ |
| Planning Agent | Create implementation plans | skills/plan-creation/ |
| Review Agent | Review plans and implementations | skills/plan-review/, skills/code-review/ |
| Implementation Agent | Implement approved plans | skills/plan-implementation/ |
Role Selection
Determine the appropriate role before starting work.
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.
- 12d ago First seen · 167 lines · 896 tokens per session scan A 28dd4860608a
01-agent-roles-and-skills is a cursor rule published in the GitHub repository pueraeternis/agentic-project-template (2 stars, last pushed 2mo ago), licensed MIT. It adds 896 tokens to every session, about $0.0045 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
kotlin-springboot-rules
A set of coding rules for Kotlin applications built with Spring Boot, a Java-based framework for web services. It covers project layout, naming, Kotlin style, and common design patterns.
fastapi-file-structure
A recommended FastAPI project structure that separates routes, configuration, security, database sessions, create/read/update/delete operations, models, and schemas into modules.
fastapi-startup-and-shutdown-events
Rules for running setup tasks when a FastAPI application starts and cleanup tasks when it stops, such as opening database connections, loading configuration, or starting background tasks.
readme-md-guidelines
A writing guide for the README.md file that documents a Laravel package. It covers the package overview, Composer installation, configuration, usage examples, testing, contributions, licensing, and optional change history.
fastapi-dependency-injection
Guidelines for using dependency injection in FastAPI. Dependency injection lets a function receive services such as database sessions, settings, or the current user instead of creating them itself.
graphql-typescript-integration
A TypeScript rule for GraphQL operations that uses the API schema and queries to generate types. It helps type-check data and variables from the GraphQL server through to React components.