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 instructions/pueraeternis/agentic-project-template/agents-mdgit 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/instructions/pueraeternis/agentic-project-template/agents-md)<a href="https://agentmods.dev/instructions/pueraeternis/agentic-project-template/agents-md"><img src="https://agentmods.dev/badge/instructions/pueraeternis/agentic-project-template/agents-md.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 | $0.00775 | $0.00775 |
| Opus 5 | $0.00387 | $0.00387 |
| Sonnet 5 | $0.00155 | $0.00155 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
agentic-project-template AGENTS.md 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
AI Agent Guide
Purpose
This document defines the universal rules for AI agents working with this repository.
It is intended for any AI coding assistant, including Codex CLI, Cursor, Claude Code, ChatGPT, and future agent-based development tools.
This document contains only repository-independent principles.
Project-specific knowledge belongs in the project documentation.
Repository Philosophy
The repository is the permanent system of record.
Documentation defines:
- project intent;
- implementation strategy;
- architecture;
- engineering decisions;
- implementation plans.
Source code implements documented decisions.
Repository documentation always has higher priority than conversational context.
Framework Overview
This repository provides an AI-first development framework based on a documentation-driven workflow.
The project lifecycle is:
Project Discovery
↓
PROJECT.md
Roadmap Creation
↓
ROADMAP.md
Architecture Design
↓
ARCHITECTURE.md
Engineering Design
↓
ENGINEERING.md
Repository Initialization
↓
Initialized Repository
Plan Creation
↓
PLAN.md
Plan Review
↓
Plan Implementation
↓
Code Review
Additional framework documentation:
METHODOLOGY.md— development methodology and lifecycleKNOWLEDGE_MODEL.md— repository knowledge modelREPOSITORY_MAP.md— repository organization
Read-First Order
Before performing work, read repository documentation in the following order when available:
AGENTS.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.
For repository onboarding, see REPOSITORY_MAP.md.
Documentation Precedence
When information conflicts, use the following priority:
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 · 183 lines · 775 tokens per session scan A 3ec6609a11a0
agentic-project-template AGENTS.md is an instructions file published in the GitHub repository pueraeternis/agentic-project-template (2 stars, last pushed 2mo ago), licensed MIT. It adds 775 tokens to every session, about $0.0039 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 instructions, from other repositories
python-docs-mcp-server AGENTS.md
AGENTS.md instructions for ayhammouda/python-docs-mcp-server, covering repository guidance, project, autonomous agent execution, canonical commands and mcp testing flow.
python-docs-mcp-server CLAUDE.md
Claude Code instructions for ayhammouda/python-docs-mcp-server: Use AGENTS.md as the canonical repository guidance.
extract-llms-docs AGENTS.md
AGENTS.md instructions for nirholas/extract-llms-docs, covering extract-llms-docs development guidelines, project overview, terminal management and contributing.
extract-llms-docs copilot-instructions.md
Copilot instructions for nirholas/extract-llms-docs, covering extract-llms-docs and terminal management.
extract-llms-docs CLAUDE.md
Claude Code instructions for nirholas/extract-llms-docs, covering extract-llms-docs and terminal management.
extract-llms-docs GEMINI.md
Gemini CLI instructions for nirholas/extract-llms-docs, covering extract-llms-docs and terminal management.