agent-architect-conventions

agent-architect-conventions is a cursor rule for Cursor from povli/AgentGOD-oss. It costs 645 tokens per session, scanned A, original, MIT.

A set of project rules for designing and building systems made of multiple software agents.

In plain words
What is it for?
Use it to name agents and skills consistently, structure design and implementation files, review designs for known problems, and follow a design-first workflow.
Why use it?
It keeps agent projects organized and requires designs and specifications to be written before implementation begins.

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/povli/agentgod-oss/agent-architect-conventions
Clone the repo
git clone --depth 1 https://github.com/povli/AgentGOD-oss

Made for: Cursor.

Wrote 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.

agentmods badge for agent-architect-conventions

README.md
[![agentmods](https://agentmods.dev/badge/rules/povli/agentgod-oss/agent-architect-conventions.svg)](https://agentmods.dev/rules/povli/agentgod-oss/agent-architect-conventions)
Your own site
<a href="https://agentmods.dev/rules/povli/agentgod-oss/agent-architect-conventions"><img src="https://agentmods.dev/badge/rules/povli/agentgod-oss/agent-architect-conventions.svg" alt="Measured on agentmods" height="20"></a>
Per session 645 This file is loaded in full into every session.
When invoked 645 The same file — it is already loaded in full.
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 $0.00645 $0.00645
Opus 5 $0.00322 $0.00322
Sonnet 5 $0.00129 $0.00129
Haiku 4.5 $0.00064 $0.00064

Measured 5d ago against content hash 7dc39263c085, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-architect-conventions 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 5d 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/agent-architect-conventions.mdc · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentGOD Agent System Conventions

Design-First Principle

Never implement an agent before its design document exists. Follow this order:

  1. Create a system design doc (use ~/.cursor/skills/agent-system-architect/templates/system-design-doc.md)
  2. Create an agent spec for each agent (use ~/.cursor/skills/agent-system-architect/templates/agent-spec.md)
  3. Review design against anti-patterns (~/.cursor/skills/agent-system-architect/references/anti-patterns.md)
  4. Only then proceed to implementation

Agent Naming

  • Agent identifiers: lowercase, hyphens only, 3-50 characters (e.g., code-reviewer, research-scout)
  • Skill directories: match agent identifier exactly
  • Rule files: <agent-name>.mdc or <concern-name>.mdc
  • MCP config keys: match the service name, not the agent name

File Organization

AgentGOD/
├── .cursor/
│   └── rules/           # Project-level rules (always-apply conventions)
├── designs/             # System design documents
│   ├── system-design.md # Overall architecture
│   └── agent-specs/     # Individual agent specifications
├── agents/              # Agent implementation files
├── skills/              # Project-specific skills (if needed)
└── tests/               # Integration and end-to-end tests

Agent Design Constraints

  • Each agent's system prompt must be under 800 words
  • Each agent may use at most 8 tools
  • Each agent connects to at most 3 MCP servers
  • Every destructive operation (file write, API POST/PUT/DELETE, database mutation) requires either:
    • An explicit human approval gate, OR
    • Documented justification for why autonomous execution is safe

MCP Security

  • API keys go in environment variables, never in committed files
  • Use project-scope MCP config (.mcp.json) for project-specific servers
  • Use global config (~/.cursor/mcp.json) only for universally needed servers
  • Document which MCP servers each agent uses and why in the agent spec

Communication Standards

  • All agent-to-agent messages must include: task_id, source_agent, timestamp
  • Define timeout and retry policy for every communication path
  • Implement circuit breakers for external API dependencies
  • Set max iteration limits for any evaluator-optimizer loops (default: 5)

Read the full file on GitHub · 70 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. 5d ago First seen · 70 lines · 645 tokens per session scan A 7dc39263c085

Subscribe to this mod's changes

agent-architect-conventions is a cursor rule published in the GitHub repository povli/AgentGOD-oss (6 stars, last pushed 5mo ago), licensed MIT. It adds 645 tokens to every session, about $0.0032 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.