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/Excoriate/mcp-terraform-aws-provider-docsWrote 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/excoriate/mcp-terraform-aws-provider-docs/mcp-tools)<a href="https://agentmods.dev/rules/excoriate/mcp-terraform-aws-provider-docs/mcp-tools"><img src="https://agentmods.dev/badge/rules/excoriate/mcp-terraform-aws-provider-docs/mcp-tools.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 5.1 | $0.00668 | $0.00668 |
| Opus 5 | $0.00334 | $0.00334 |
| Sonnet 5 | $0.00134 | $0.00134 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
mcp-tools 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 8d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Tool Definition Rule
Canonical Example
See tools-issues.ts for a complete, high-quality MCP tool definition.
Required Structure for All MCP Tools
Every MCP tool must be defined as a JavaScript object with the following fields:
name: A unique, descriptive string identifier for the tool.description: A multiline template string (using backticks) containing a plain-text, sectioned, and indented description. Do not use markdown or code block syntax inside the content. The description must be readable in code and must include the following sections, in order:- Purpose: What the tool does and why it exists.
- When to Use: Actionable scenarios for LLMs and users.
- Arguments: List each argument, its type, and its effect. For booleans, clarify behavior for true/false. For pagination or filtering, be explicit.
- Output Format: Describe the structure and fields of the output, including types and any formatting conventions.
- Edge Case Handling: Explicitly document all edge cases (empty results, pagination, missing fields, authentication errors, etc.).
- Integration and Chaining: How this tool can be combined with other tools or workflows.
- Example Usage: At least two example invocations, formatted as plain text (not JSON or markdown).
- Success Criteria: List the conditions for correct and robust tool behavior.
inputSchema: An explicit schema object describing all accepted arguments, with each field’s description clarifying its behavior and effect.
Formatting and Content Requirements
- Use a multiline template string for the description. Do not use markdown, code blocks, or backticks inside the content.
- Indent and line-break sections for maximum readability in code.
- All field names and values in the description should be plain text.
- Argument descriptions must clarify the effect of each value (e.g., “Controls pagination behavior - when true, fetches all pages of issues; when false, only returns the first page (30 issues)”).
- Output format must list all fields, types, and any special formatting or conventions.
- Edge case handling is mandatory and must be explicit.
- Example usage must be included as plain text, not as markdown or code blocks.
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.
- 8d ago First seen · 52 lines · 668 tokens per session scan A 7e26c6e9d9f7
mcp-tools is a cursor rule published in the GitHub repository Excoriate/mcp-terraform-aws-provider-docs (1 stars, last pushed 1y ago), licensed MIT. It adds 668 tokens to every session, about $0.0033 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
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
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.
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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.