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/pueraeternis/agentic-project-template/00-framework-navigationgit clone --depth 1 https://github.com/pueraeternis/agentic-project-templateWhat 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 | $0.00699 | $0.00699 |
| Opus 5 | $0.00349 | $0.00349 |
| Sonnet 5 | $0.00140 | $0.00140 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
00-framework-navigation 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 2d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Engineering Framework
This repository follows the Agentic Engineering Methodology.
The repository is the shared working memory for humans and AI agents.
Repository documentation is the primary source of truth.
Chat history is temporary context and must not be treated as persistent project knowledge.
Engineering Lifecycle
Every project follows the same lifecycle:
Project Discovery
↓
Roadmap Creation
↓
Architecture Design
↓
Engineering Design
↓
Repository Initialization
↓
Plan Creation
↓
Plan Review
↓
Plan Implementation
↓
Code Review
↓
Progress Update
Each stage has:
- an engineering role;
- a reusable skill;
- one or more repository artifacts.
Read-First Order
Before starting any work, read the repository documentation in the following order when available:
AGENTS.mdREPOSITORY_MAP.mdMETHODOLOGY.mdKNOWLEDGE_MODEL.mddocs/project/PROJECT.mddocs/project/ROADMAP.mddocs/project/ARCHITECTURE.mddocs/project/ENGINEERING.md- Relevant ADRs in
docs/project/adr/ - Active plans in
docs/project/plans/active/ docs/project/PROGRESS.md
If a document does not exist, continue with the next available document.
Repository Philosophy
The repository is organized around durable engineering knowledge rather than source code.
Documentation defines:
- project intent;
- implementation strategy;
- system architecture;
- engineering decisions;
- implementation scope;
- engineering history.
Implementation follows documentation.
Documentation does not follow implementation.
Documentation Precedence
When information conflicts, use the following priority:
docs/project/PROJECT.mddocs/project/ARCHITECTURE.mddocs/project/ENGINEERING.md- Relevant ADRs
- Active implementation plans
docs/project/PROGRESS.md- Chat context
Repository documentation always overrides conversational context.
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.
- 2d ago First seen · 159 lines · 699 tokens per session scan A 99837292fe90
00-framework-navigation is a cursor rule published in the GitHub repository pueraeternis/agentic-project-template (2 stars, last pushed 2mo ago), licensed MIT. It adds 699 tokens to every session, about $0.0035 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
creating-cursor-rules
Meta-rule for creating effective Cursor IDE rules with best practices, patterns, and examples.
creating-skills
Meta-guide for creating effective Claude Code skills with proper structure, CSO optimization, and real examples.
cursor-agent-orchestration
Cursor 3.7 orchestration guide: when to plan, when to delegate, nested subagents, multi-environment handoffs, /best-of-n, and Await for long-running branches.
cursor-mcp-optimization
Cursor 3.7 MCP optimization: browser Design Mode, canvases, Figma, Cloudflare tools, MCP Apps structured content, and direct action patterns.
model-compatibility
Model compatibility guide: prompt hierarchy, M3-first model selection, tool discipline, read-before-edit safety, and context control across models.
skill-authoring
MiniMax M3 + Cursor 3.7 skill authoring: when to use skills, how to structure them, how to keep them deep without duplicating the core, and how to declare model assumptions.