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.
git 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-implementation)<a href="https://agentmods.dev/rules/cafreeman/foundry-mcp/foundry-implementation"><img src="https://agentmods.dev/badge/rules/cafreeman/foundry-mcp/foundry-implementation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/cafreeman/foundry-mcp/foundry-implementation"><img src="https://agentmods.dev/badge/rules/cafreeman/foundry-mcp/foundry-implementation.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.00967 |
| Opus 5.5 | $0.00000 | $0.00387 |
| Sonnet 5.5 | $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 2mo 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 — 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.
- 2mo ago 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 7mo 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
rust-module-refactor
Use when splitting Rust modules, moving tests, tightening visibility, or preserving facades during refactors.
rust-architect
PoolAI — Rust Architect workflow: runtime stack, MSYS2, target/ disk, pre-push checks, docs sync.
core
Core STT/TTS abstraction layer documentation.
arc-deref-pattern
When implementing parallel (Mt) algorithms in Verus, do NOT assume.
table-of-contents-standard
Standard section ordering and TOC format for Verus source files.
wrap-vs-specify
When to use externaltypespecification vs wrapper struct for Verus specs.