aod.update

A command for applying changes from an upstream project template to the current project. It previews a categorized difference and can apply an approved set of changes.

In plain words
What is it for?
Use it to check for new template commands, skills, or documentation, preview those changes, and update the current project between feature tasks.
Why use it?
It makes it easier to adopt improvements from the source template without manually comparing and copying files.

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

Made for: Claude Code.

Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,096 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 $0.00008 $0.01096
Opus 5 $0.00004 $0.00548
Sonnet 5 $0.00002 $0.00219
Haiku 4.5 $0.00001 $0.00110

Measured 2d ago against content hash bbd6a3263aa8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aod.update 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.update — 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.update.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Run the downstream template update pipeline: fetch the latest AOD-kit template from the pinned upstream, compute a categorized diff, preview what will change, and apply the approved set of changes atomically.

Update direction is always: upstream → downstream

When to Use

  • Periodic check for upstream template improvements (new commands, skills, docs).
  • After a notable upstream release — confirm whether anything safe-to-adopt has landed.
  • Before running /aod.deliver on a large feature if you want the latest tooling.

When NOT to Use

  • During an in-flight feature branch if you're worried about merge noise — do it between features.
  • On a dirty working tree with uncommitted changes you care about — commit or stash first.

Input

$ARGUMENTS

Common flag combinations:

  • (no flags) — interactive TTY: preview, then confirm-to-apply.
  • --dry-run — preview only; never writes.
  • --yes — skip the confirmation prompt; still applies.
  • --edge — fetch upstream main HEAD instead of latest tag (not recommended for production use).
  • --force-retag — proceed even if the pinned tag has been retagged upstream (supply-chain override; logs a warning).
  • --upstream-url=<url> — override the recorded upstream URL (must be https://).

Step 1: Verify Bootstrap State

Check that the adopter project has been bootstrapped:

test -f .aod/aod-kit-version || { echo "Missing .aod/aod-kit-version — run scripts/init.sh first." ; exit 3; }
test -f .aod/personalization.env || { echo "Missing .aod/personalization.env — run scripts/init.sh first." ; exit 3; }

If either file is missing: Display setup instructions pointing at scripts/init.sh and stop execution.

Step 2: Run the Update Pipeline

Invoke the CLI with the provided arguments:

scripts/update.sh $ARGUMENTS

Display the full output to the user so they can see the preview, confirmation prompt (if interactive), and per-operation apply log.

Step 3: Interpret Exit Codes

Read the full file on GitHub · 113 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 · 113 lines · 8 tokens per session scan A bbd6a3263aa8

Subscribe to this mod's changes

aod.update is a command published in the GitHub repository davidmatousek/agentic-oriented-development-kit (22 stars, last pushed 2mo ago), licensed MIT. It adds 8 tokens to every session and 1,096 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to aod.update, differing in 0 lines, and is treated as a copy.