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/cafreeman/foundry-mcp/foundry-architecturegit clone --depth 1 https://github.com/cafreeman/foundry-mcpWrote 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/cafreeman/foundry-mcp/foundry-architecture)<a href="https://agentmods.dev/rules/cafreeman/foundry-mcp/foundry-architecture"><img src="https://agentmods.dev/badge/rules/cafreeman/foundry-mcp/foundry-architecture.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 | $0.00394 | $0.00394 |
| Opus 5 | $0.00197 | $0.00197 |
| Sonnet 5 | $0.00079 | $0.00079 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade A, and why
foundry-architecture 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.
What it actually says
Foundry MCP Architecture
Project Overview
Foundry MCP: CLI tool and MCP server for deterministic project management and AI coding assistant integration. Manages project specifications in ~/.foundry/ directory structure.
Module Organization
- src/main.rs - CLI entry point
- src/lib.rs - Library exports and foundry_dir() utility
- src/cli/ - CLI arguments and commands
- src/core/ - Core business logic
- src/types/ - Type definitions
- src/utils/ - Utility functions
Project Structure
~/.foundry/PROJECT_NAME/
├── vision.md # High-level product vision
├── tech-stack.md # Technology decisions
├── summary.md # Concise summary for context loading
└── specs/
└── YYYYMMDD_HHMMSS_FEATURE_NAME/
├── spec.md # Feature specification
├── task-list.md # Implementation checklist
└── notes.md # Additional context
Core Principles
- Content Agnostic: Foundry manages structure, NOT content opinions
- LLM-Driven: LLMs provide file content as arguments, not file paths
- User-Controlled: Users control content, CLI manages structure
- Workflow-Aware: Tools provide next-steps guidance for LLM decision-making
Development Priorities
- CLI functionality first, then MCP server
- Identical functionality between CLI and MCP interfaces
- JSON responses with workflow guidance
- Support iterative spec evolution
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 · 47 lines · 394 tokens per session scan A 32eca980f064
foundry-architecture is a cursor rule published in the GitHub repository cafreeman/foundry-mcp (4 stars, last pushed 5mo ago), licensed MIT. It adds 394 tokens to every session, about $0.0020 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
development-workflow
AAMAD modular development workflow for context-aware agent coordination.
checkpoint
Write a committed handoff checkpoint so a fresh session can resume with zero loss. Use when crossing the 40% context line, on every stage transition, and at session end. Writes .trace/checkpoints/ - .md while the agent is still sharp.
feedback-enhanced
Enhanced feedback mechanism with 1-hour timeout - 增强反馈机制，1小时超时.
project-onboarding-rule
Automatically onboards existing projects into the AI-driven development workflow.
linear-in-review
After finishing a Linear issue, set its status to In Review (never Done).
sprint-planning
BMAD BMM Agent: sprint-planning.