generate

generate is a command for coding agents from basher83/lunar-claude. It costs 6 tokens per session (772 once invoked), scanned A, original, MIT.

A command that creates the final Architecture Decision Record after the options have been analyzed. An ADR is a durable document explaining a technical decision and its consequences.

In plain words
What is it for?
It helps capture the decision, describe what becomes easier or harder, and assign the next ADR number in a documentation folder.
Why use it?
It turns the completed analysis into a consistent record that captures the chosen option, reasoning, trade-offs, and decision-makers.

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/generate
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 generate

README.md
[![agentmods](https://agentmods.dev/badge/commands/basher83/lunar-claude/generate.svg)](https://agentmods.dev/commands/basher83/lunar-claude/generate)
Your own site
<a href="https://agentmods.dev/commands/basher83/lunar-claude/generate"><img src="https://agentmods.dev/badge/commands/basher83/lunar-claude/generate.svg" alt="Measured on agentmods" height="20"></a>
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 772 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 $0.00006 $0.00772
Opus 5 $0.00003 $0.00386
Sonnet 5 $0.00001 $0.00154
Haiku 4.5 $0.00001 $0.00077

Measured 2d ago against content hash 00ec45e2a303, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

generate 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/generate.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate the final Architecture Decision Record document.

Use the adr-methodology skill for ADR templates.

Prerequisites Check

Read .claude/adr-session.yaml to retrieve session state.

If file doesn't exist or status is not analyzed:

  • Inform user that options analysis must be completed first
  • Instruct them to run /adr-assistant:analyze to complete the analysis
  • Stop processing

Phase 1: Decision Capture

Display the options matrix summary from state.

Ask user:

  1. Which option are you choosing?
  2. Why? (Reference specific criteria and trade-offs)
  3. Who are the decision-makers? (Names for the ADR header)

Phase 2: Consequences Analysis

Based on the chosen option and its ratings, generate:

What becomes easier:

  • Benefits from Low-risk ratings
  • Advantages over rejected options

What becomes harder:

  • Trade-offs from Medium/High ratings
  • Capabilities lost by rejecting alternatives

Present for user review and refinement.

Phase 3: ADR Number Detection

Scan docs/adr/ directory for existing ADR files.

If directory exists:

  • Find highest numbered ADR (pattern: NNNN-*.md)
  • Next number = highest + 1

If directory doesn't exist:

  • Create docs/adr/ directory
  • Start at 0001

Phase 4: Generate ADR

Use MADR template format. Generate complete ADR including:

  1. Header: Number, title, status (Accepted), date, decision-makers
  2. AI Disclosure: Note that Claude assisted; humans reviewed and decided
  3. Context: Summarize problem and constraints from session
  4. Decision Drivers: Key criteria that influenced the decision
  5. Considered Options: Each option with pros/cons from analysis
  6. Decision: Chosen option with rationale
  7. Consequences: What becomes easier/harder
  8. Appendix: Full assessment matrix from analysis

Phase 5: Output Path

Determine output path:

If $1 provided:

  • Use $1 as the output path

If no argument:

  • Generate path: docs/adr/NNNN-[slugified-title].md
  • Slugify: lowercase, hyphens for spaces, remove special characters

Read the full file on GitHub · 143 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 · 143 lines · 6 tokens per session scan A 00ec45e2a303

Subscribe to this mod's changes

generate is a command published in the GitHub repository basher83/lunar-claude (22 stars, last pushed today), licensed MIT. It adds 6 tokens to every session and 772 once invoked, about $0.0000 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.