foundry_load_spec

foundry_load_spec is a command for Cursor from cafreeman/foundry-mcp. It costs 0 tokens per session (1,251 once invoked), scanned A, original, MIT.

A command for loading a complete feature specification from Foundry, a tool that stores project plans and specifications in organized files.

In plain words
What is it for?
Use it to choose a project, discover available specifications, match a search phrase to the right one, and load it for focused development.
Why use it?
It helps locate the intended specification even when the project or feature name is incomplete or slightly different.

Command 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 commands/cafreeman/foundry-mcp/foundry_load_spec
Clone the repo
git clone --depth 1 https://github.com/cafreeman/foundry-mcp

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 foundry_load_spec

README.md
[![agentmods](https://agentmods.dev/badge/commands/cafreeman/foundry-mcp/foundry_load_spec.svg)](https://agentmods.dev/commands/cafreeman/foundry-mcp/foundry_load_spec)
Your own site
<a href="https://agentmods.dev/commands/cafreeman/foundry-mcp/foundry_load_spec"><img src="https://agentmods.dev/badge/commands/cafreeman/foundry-mcp/foundry_load_spec.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,251 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.01251
Opus 5 $0.00000 $0.00626
Sonnet 5 $0.00000 $0.00250
Haiku 4.5 $0.00000 $0.00125

Measured 4d ago against content hash 19f390edc21f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

foundry_load_spec 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.

.cursor/commands/foundry_load_spec.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Load Spec With Foundry

Overview

Load a complete specification using intelligent fuzzy matching to enable focused development work.

Context Gathering & Parameter Resolution

Discovery Workflow for Missing Parameters:

  1. Project Name Missing: Execute list_projects to display available options with metadata and guide user selection
  2. Spec Query Missing: Execute list_specs for the target project and present specs in user-friendly format
  3. Both Present: Proceed directly to fuzzy matching and loading workflow

Validation & Preparation:

  • Verify target project exists in Foundry system before attempting spec operations
  • Set user expectations about fuzzy matching capabilities and potential disambiguation needs
  • Prepare for potential multiple matches requiring user selection

Comprehensive Loading Workflow

Step 1: Intelligent Spec Discovery

Parameter Resolution Strategy:

  • Missing Project: Show list_projects with creation dates and brief descriptions for informed selection
  • Missing Spec: Display list_specs results with feature names, dates, and completion status
  • Fuzzy Matching: Use provided spec query with intelligent pattern matching

Step 2: Spec Loading with Fuzzy Matching

Execute Load Operation:

{"name":"load_spec","arguments":{"project_name":"$1","spec_name":"$2"}}

Match Quality Assessment:

  • High Confidence Single Match: Load directly and proceed to content analysis
  • Multiple Matches: Present candidates with feature names, creation dates, and similarity scores
  • Low Confidence: Show alternatives and ask for clarification or more specific search terms
  • No Matches: Suggest creating new spec or provide spelling/naming guidance

Step 3: Comprehensive Content Analysis

Specification Overview:

  • Feature Summary: Extract and highlight main feature purpose, scope, and value proposition
  • Development Status: Analyze task completion percentage and identify remaining work
  • Context Assessment: Review requirements, acceptance criteria, and implementation approach

Read the full file on GitHub · 125 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. 4d ago First seen · 125 lines · 0 tokens per session scan A 19f390edc21f

Subscribe to this mod's changes

foundry_load_spec is a command 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 1,251 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.