agentmods.dev

agent-file-format

A writing guide for creating and editing .agent files, which define an AI agent’s instructions, role, context, and requested output.

In plain words
What is it for?
Use it when defining an agent’s identity, capabilities, current context, templates, model, or structured responses.
Why use it?
It gives agent files a consistent structure and makes prompts easier to test and improve.

Cursor rule for Cursor

24 2mo ago A scan 7 tokens original MIT
View the source file TechNickAI/ai-coding-config
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/technickai/ai-coding-config/agent-file-format
Clone the repo
git clone --depth 1 https://github.com/TechNickAI/ai-coding-config

Made for: Cursor.

Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 283 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 $0.00007 $0.00283
Opus 5 $0.00003 $0.00142
Sonnet 5 $0.00001 $0.00057
Haiku 4.5 $0.00001 $0.00028

Measured 2d ago against content hash 84eae042ca32, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-file-format 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.

.cursor/rules/ai/agent-file-format.mdc · 66 lines

What it actually says

Agent File Format

Structure

---
SYSTEM PROMPT
---

## Identity and Capabilities

Define who the agent IS and what it can do...

---
USER PROMPT
---

## Current Context

Dynamic context with {{ template_variables }}...

Prompt Engineering for Agents

Based on LLM token prediction mechanics:

System Prompt (Static DNA)

  1. Identity: Who the agent IS fundamentally
  2. Philosophy: Core beliefs that guide decisions
  3. Framework: Analytical methodology
  4. Capabilities: What the agent can and cannot do

User Prompt (Dynamic Context)

  1. Current State: Present environment/context
  2. Specific Data: The actual information to process
  3. Decision Ask: Clear output request with format

Best Practices

  • All agents must specify their model explicitly
  • Fail fast - let errors bubble up
  • Use structured output with Pydantic models when possible
  • Track evolution in evolution_history when prompts improve
  • Use proper template syntax for variables

Testing

from pydantic_ai.testing import TestModel

agent = BaseAgent(model_override=TestModel())
agent.test_model.set_response({"result": "test"})

Remember

Agents are AI employees - define their identity clearly and let them excel at their specialized roles.

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. 2d ago First seen · 66 lines · 7 tokens per session scan A 84eae042ca32

Subscribe to this mod's changes

agent-file-format is a cursor rule published in the GitHub repository TechNickAI/ai-coding-config (24 stars, last pushed 2mo ago), licensed MIT. It adds 7 tokens to every session and 283 once invoked, about $0.0000 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 2026-08-30.

Data and AIProductivityWorkflow AutomationWriting and docsai-agentsai-codingclaude-codedeveloper-toolsllm-tools
Related

Other cursor rules, from other repositories

infra-devops

Infrastructure, Cloud, Terraform, Docker & CI/CD Agent.

PlanVault/ai-engineering-playbook · 0 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

typescript

Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.

streamlit/streamlit · 4,669 tokens

coolify-ai-docs

Master reference to all Coolify AI documentation in .ai/ directory.

coollabsio/coolify · 1,426 tokens

python_lib

Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.

streamlit/streamlit · 0 tokens