aod.define

aod.define is a command for Claude Code from davidmatousek/tachi. It costs 23 tokens per session (4,487 once invoked), scanned A, original, Apache-2.0.

A command that creates a product requirements document, a written description of what a product or feature should do, with reviews from several project roles.

In plain words
What is it for?
Use it to draft a new requirements document or revise one using reviewer feedback, with optional autonomous execution.
Why use it?
It turns an idea into an agreed plan and checks it through product, architecture, and team-lead reviews.

Command for Claude Code

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/davidmatousek/tachi/aod.define
Clone the repo
git clone --depth 1 https://github.com/davidmatousek/tachi

Made for: Claude Code.

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 aod.define

README.md
[![agentmods](https://agentmods.dev/badge/commands/davidmatousek/tachi/aod.define.svg)](https://agentmods.dev/commands/davidmatousek/tachi/aod.define)
Your own site
<a href="https://agentmods.dev/commands/davidmatousek/tachi/aod.define"><img src="https://agentmods.dev/badge/commands/davidmatousek/tachi/aod.define.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,487 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 $0.00023 $0.04487
Opus 5 $0.00012 $0.02243
Sonnet 5 $0.00005 $0.00897
Haiku 4.5 $0.00002 $0.00449

Measured 3d ago against content hash 080baa8aad5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aod.define 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 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.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/commands/aod.define.md · 359 lines

How it starts

The opening of the file, as written. The whole thing — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Input

$ARGUMENTS

Consider user input before proceeding (if not empty).

Step 0: Parse --autonomous

  1. If $ARGUMENTS contains --autonomous:
    • Set autonomous = true
    • Strip --autonomous from $ARGUMENTS (trim extra whitespace)
  2. Default: autonomous = false

Step 0y: Parse --revision

  1. If $ARGUMENTS contains --revision:
    • Set revision_mode = true
    • Strip --revision from $ARGUMENTS (trim extra whitespace)
    • Read .aod/revision-context.md for reviewer feedback (contains reviewer name, attempt number, artifact path, and full feedback text)
    • Store feedback as revision_feedback
  2. Default: revision_mode = false

Overview

Wraps ~aod-define skill with automatic Triad triple sign-off.

Flow: Check vision docs → Validate topic → Classify type → Draft PRD → Reviews → Handle blockers → Inject frontmatter → Update INDEX

Step 0: Check Product Vision (Optional)

Check if product vision documents exist:

  • docs/product/01_Product_Vision/product-vision.md

If vision docs DON'T exist (first PRD for this project):

  1. If autonomous == true: Auto-select "Skip". Display: "Auto-selected: Skip vision workshop (autonomous mode)". Proceed directly to Step 1.

  2. Use AskUserQuestion:

    • Quick Vision: Answer 3 questions to create vision docs (recommended for new projects)
    • Skip: Proceed directly to PRD creation (for experienced users)
  3. If "Quick Vision" selected, run mini-workshop:

🎯 Quick Product Vision (3 questions)

Q1: What problem are you solving and for whom?
(1-2 sentences: the pain point and who experiences it)

Q2: What's your solution in one sentence?
(How your product solves the problem differently)

Q3: What are the 2-3 core features?
(Brief list of key capabilities)
  1. Generate docs/product/01_Product_Vision/product-vision.md with their answers:
    • Mission statement (derived from Q1+Q2)
    • Problem statement (Q1)
    • Solution overview (Q2)
    • Core capabilities table (Q3)

Read the full file on GitHub · 359 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. 3d ago First seen · 359 lines · 23 tokens per session scan A 080baa8aad5c

Subscribe to this mod's changes

aod.define is a command published in the GitHub repository davidmatousek/tachi (90 stars, last pushed 21d ago), licensed Apache-2.0. It adds 23 tokens to every session and 4,487 once invoked, about $0.0001 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 2026-08-30.