new

new is a command for coding agents from basher83/lunar-claude. It costs 10 tokens per session (475 once invoked), scanned A, original, MIT.

A guided workflow for creating an Architecture Decision Record, or ADR—a document that explains an important technical choice and why it was made.

In plain words
What is it for?
It helps start an ADR, gather the needed context, and prepare criteria for comparing architecture options.
Why use it?
It helps turn an unclear architecture question into a structured decision by collecting the problem, constraints, stakeholders, and possible solutions.

Command

Part of the adr-assistant plugin — 1 skill, 3 commands shipped together

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/basher83/lunar-claude/new
Clone the repo
git clone --depth 1 https://github.com/basher83/lunar-claude

Or install adr-assistant, the plugin that ships this one along with the rest of its 1 skill, 3 commands.

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 new

README.md
[![agentmods](https://agentmods.dev/badge/commands/basher83/lunar-claude/new.svg)](https://agentmods.dev/commands/basher83/lunar-claude/new)
Your own site
<a href="https://agentmods.dev/commands/basher83/lunar-claude/new"><img src="https://agentmods.dev/badge/commands/basher83/lunar-claude/new.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 475 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 5.1 $0.00010 $0.00475
Opus 5 $0.00005 $0.00237
Sonnet 5 $0.00002 $0.00095
Haiku 4.5 $0.00001 $0.00047

Measured 2d ago against content hash f20cea730fd9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

new 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.

plugins/homelab/adr-assistant/commands/new.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Start an Architecture Decision Record workflow for: $ARGUMENTS

Use the adr-methodology skill for criteria frameworks and templates.

Phase 1: Context Gathering

Ask the user to describe:

  1. The Problem: What architectural decision needs to be made? What's driving the need for a decision now?
  2. Constraints: Timeline, team size, existing technology stack, budget limitations, compliance requirements
  3. Stakeholders: Who is affected? Who has decision authority? Who needs to be informed?
  4. Initial Options: Any solutions already under consideration? Prior art or existing patterns?

Wait for user responses before proceeding. Ask follow-up questions if context is insufficient.

Phase 2: Framework Selection

Based on the context, recommend an assessment framework:

  • Salesforce Well-Architected (Trusted/Easy/Adaptable): For enterprise decisions with security, UX, and scale concerns
  • Technical Trade-off (Operational/Development/Integration): For infrastructure and tooling decisions
  • Custom: When neither fits, extract 3-5 key decision drivers and create custom criteria

Explain the recommendation and confirm with user.

Phase 3: Criteria Generation

Generate assessment criteria grouped by the selected framework's pillars. For each criterion:

  • Name: Clear, specific identifier
  • Rationale: Why this criterion matters for THIS decision (not generic)
  • Good looks like: What success means for this criterion

Present criteria as a reviewable list. Ask user to:

  • Add missing criteria
  • Remove irrelevant criteria
  • Adjust importance of criteria

Phase 4: Save State

After user confirms criteria, write to .claude/adr-session.yaml:

topic: "[decision topic]"
status: "criteria_defined"
framework: "[salesforce|technical|custom]"
criteria:
  - name: "[criterion name]"
    pillar: "[framework pillar]"
    rationale: "[why it matters]"
    good_looks_like: "[definition of success]"

Create the .claude/ directory if it doesn't exist.

Read the full file on GitHub · 62 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 · 62 lines · 10 tokens per session scan A f20cea730fd9

Subscribe to this mod's changes

new is a command published in the GitHub repository basher83/lunar-claude (22 stars, last pushed today), licensed MIT. It adds 10 tokens to every session and 475 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 2026-09-03.