aod.document

A post-delivery quality review for completed software features, covering code cleanup and project documentation such as changelogs and API references. A changelog records user-visible changes between releases.

In plain words
What is it for?
Use it to review code, improve docstrings, update the changelog and API documentation, review the knowledge base, and prepare the feature for a final merge.
Why use it?
It helps catch unnecessary complexity, missing explanations, and documentation that no longer matches the code before the work is closed.

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/agentic-oriented-development-kit/aod.document
Clone the repo
git clone --depth 1 https://github.com/davidmatousek/agentic-oriented-development-kit

Made for: Claude Code.

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,413 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00021 $0.03413
Opus 5 $0.00010 $0.01707
Sonnet 5 $0.00004 $0.00683
Haiku 4.5 $0.00002 $0.00341

Measured 2d ago against content hash 3b1ce7e498be, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aod.document 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 2d 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

This is a copy

100% identical to aod.document — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/aod.document.md · 277 lines

How it starts

The opening of the file, as written. The whole thing — 277 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 0a: Parse --autonomous

  1. If $ARGUMENTS contains --autonomous:
    • Set autonomous = true
    • Strip --autonomous from $ARGUMENTS (trim extra whitespace)
  2. If $ARGUMENTS does NOT contain --autonomous:
    • Set autonomous = false

Overview

Post-delivery quality review for the completed feature. This is Stage 6 of the AOD lifecycle — the one stage designed for human judgment. Each step presents findings interactively and commits only what the human approves.

Flow: Validate context → Branch → Code simplification → Docs-lint → CHANGELOG → API sync → KB review → PR squash-merge → Report

IMPORTANT: Execute ALL steps 0–7 sequentially. Do not stop or wait for further instructions between steps. After completing each step (including user interaction), immediately proceed to the next step until the Step 7 Report is displayed.

Step 0: Validate Context

  1. Get branch: git branch --show-current
  2. Determine feature number NNN:
    • If on a NNN-* branch: extract NNN from branch name
    • If on main: extract NNN from user input $ARGUMENTS, or detect from most recent feat(NNN) or docs(NNN) commit on main
    • If NNN cannot be determined: prompt the user for the feature number
  3. Find tasks: specs/{NNN}-*/tasks.md → verify all tasks marked [X] (build complete)
  4. If tasks incomplete: warn "Build may not be complete — {incomplete_count} tasks remain" and ask whether to proceed
  5. Display: "Document stage for Feature {NNN}"

Step 0b: Create Document Branch

  1. If not already on main: git checkout main && git pull origin main
  2. Create branch: git checkout -b {NNN}-document-stage
  3. Display: "Working on branch {NNN}-document-stage"

Step 1: Code Simplification

Detect changed code files and run /simplify for human review.

1a: Detect Changed Files

  1. Run: git diff --name-only main...HEAD
  2. Filter to code extensions: .py, .js, .ts, .jsx, .tsx, .sh, .go, .rs, .java, .rb, .swift, .kt
  3. Exclude: *.lock, *.min.js, *.min.css, *.map, *.generated.*, vendor/, dist/, build/, node_modules/, .aod/, docs/
  4. Store as changed_files list and file_count
  5. If file_count is 0: display "No code files changed — skipping simplification", proceed to Step 2
  6. If file_count > 50: warn "Large diff ({file_count} files). Simplify may take several minutes." and ask whether to continue or skip

Read the full file on GitHub · 277 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. 2d ago First seen · 277 lines · 21 tokens per session scan A 3b1ce7e498be

Subscribe to this mod's changes

aod.document is a command published in the GitHub repository davidmatousek/agentic-oriented-development-kit (22 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 3,413 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to aod.document, differing in 0 lines, and is treated as a copy.