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-implementationgit clone --depth 1 https://github.com/cafreeman/foundry-mcpWhat 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 | $0.00000 | $0.00967 |
| Opus 5 | $0.00000 | $0.00483 |
| Sonnet 5 | $0.00000 | $0.00193 |
| Haiku 4.5 | $0.00000 | $0.00097 |
Grade A, and why
foundry-implementation 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 yesterday.
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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Foundry Implementation Patterns
CLI Command Structure
Standard Pattern
// All commands: async fn execute(args: XxxArgs) -> Result<XxxResponse>
pub async fn execute(args: CreateProjectArgs) -> Result<CreateProjectResponse> {
validate_args(&args).context("Invalid arguments")?;
let result = perform_operation(&args).context("Operation failed")?;
Ok(build_response(result))
}
Response Format (REQUIRED)
#[derive(Serialize, Debug)]
pub struct CommandResponse {
// Core data (project, spec, etc.)
pub next_steps: Vec<String>, // REQUIRED: Workflow guidance
pub validation_status: String, // REQUIRED: "complete", "partial", "failed"
#[serde(skip_serializing_if = "Option::is_none")]
pub workflow_hints: Option<Vec<String>>, // OPTIONAL: LLM guidance
}
Error Handling
Context Pattern
use anyhow::{Context, Result};
// Add meaningful context to all operations
std::fs::create_dir_all(&project_dir)
.context(format!("Failed to create project directory: {}", project_dir.display()))?;
// Validate early, fail fast
validate_project_name(&args.project_name)
.context("Invalid project name format")?;
Validation Functions
pub fn validate_project_name(name: &str) -> Result<()> {
if name.is_empty() || !name.chars().all(|c| c.is_alphanumeric() || c == '-' || c == '_') {
anyhow::bail!("Project name must use kebab-case (alphanumeric and hyphens only)");
}
Ok(())
}
User Memory Compliance
Function Returns (Memory #7066344)
- ONLY return what's needed - avoid unused return values
- Use
#[serde(skip_serializing_if = "Option::is_none")]for optional fields - Focus responses on immediate workflow needs
Content Creation (Memory #7065075)
- NEVER implement automatic content generation or summarization
- ALWAYS require LLMs to provide complete content as arguments
- CLI validates format and length, but NOT content quality
// ✅ Good: LLM provides content
pub struct CreateProjectArgs {
pub project_name: String,
pub vision: String, // LLM-provided content
pub tech_stack: String, // LLM-provided content
}
// ❌ Bad: CLI generates content
pub fn generate_summary_from_vision(vision: &str) -> String {
// Never implement this
}
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.
- yesterday First seen · 154 lines · 0 tokens per session scan A 2f67b2cf0c5d
foundry-implementation is a cursor rule published in the GitHub repository cafreeman/foundry-mcp (4 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 967 tokens. 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.
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.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.