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/povli/agentgod-oss/agent-architect-conventionsgit clone --depth 1 https://github.com/povli/AgentGOD-ossWrote 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/povli/agentgod-oss/agent-architect-conventions)<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>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 | $0.00645 | $0.00645 |
| Opus 5 | $0.00322 | $0.00322 |
| Sonnet 5 | $0.00129 | $0.00129 |
| Haiku 4.5 | $0.00064 | $0.00064 |
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.
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:
- Create a system design doc (use
~/.cursor/skills/agent-system-architect/templates/system-design-doc.md) - Create an agent spec for each agent (use
~/.cursor/skills/agent-system-architect/templates/agent-spec.md) - Review design against anti-patterns (
~/.cursor/skills/agent-system-architect/references/anti-patterns.md) - 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>.mdcor<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)
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.
- 5d ago First seen · 70 lines · 645 tokens per session scan A 7dc39263c085
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.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.