aidd-riteway-ai

aidd-riteway-ai is a command for coding agents from paralleldrive/aidd. It costs 31 tokens per session (87 once invoked), scanned B, original, MIT.

A command for writing Riteway AI prompt evaluations, which test how an AI handles multi-step tasks involving tools. It is intended for .sudo evaluation files and agent-skill tests.

In plain words
What is it for?
For writing evaluation files and testing skills that call tools across multiple steps.
Why use it?
It helps create consistent tests for tool-using agent workflows.

Command

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/paralleldrive/aidd/aidd-riteway-ai
Clone the repo
git clone --depth 1 https://github.com/paralleldrive/aidd

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 aidd-riteway-ai

README.md
[![agentmods](https://agentmods.dev/badge/commands/paralleldrive/aidd/aidd-riteway-ai.svg)](https://agentmods.dev/commands/paralleldrive/aidd/aidd-riteway-ai)
Your own site
<a href="https://agentmods.dev/commands/paralleldrive/aidd/aidd-riteway-ai"><img src="https://agentmods.dev/badge/commands/paralleldrive/aidd/aidd-riteway-ai.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 87 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00031 $0.00087
Opus 5 $0.00015 $0.00044
Sonnet 5 $0.00006 $0.00017
Haiku 4.5 $0.00003 $0.00009

Measured 3d ago against content hash 5ba5596bd57c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

aidd-riteway-ai scanned grade B with 1 finding 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 3d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

description: Write correct riteway ai prompt evals for multi-step tool-calling flows. Use when creating .sudo eval files or testing agent skills that use tools.
ai/commands/aidd-riteway-ai.md · 11 lines

What it actually says

🧪 /aidd-riteway-ai

Load and execute the skill at ai/skills/aidd-riteway-ai/SKILL.md.

Constraints { Before beginning, read and respect the constraints in /aidd-please. }

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. 3d ago First seen · 11 lines · 31 tokens per session scan B 5ba5596bd57c

Subscribe to this mod's changes

aidd-riteway-ai is a command published in the GitHub repository paralleldrive/aidd (380 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 87 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.