analyze

analyze is a command for coding agents from basher83/lunar-claude. It costs 7 tokens per session (526 once invoked), scanned A, original, MIT.

A command in an Architecture Decision Record workflow that compares possible solutions against previously defined decision criteria.

In plain words
What is it for?
It helps list options, rate their risks as low, medium, or high, and record mitigations for significant risks.
Why use it?
It gives technical options a consistent risk assessment instead of relying on an informal or incomplete comparison.

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/analyze
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 analyze

README.md
[![agentmods](https://agentmods.dev/badge/commands/basher83/lunar-claude/analyze.svg)](https://agentmods.dev/commands/basher83/lunar-claude/analyze)
Your own site
<a href="https://agentmods.dev/commands/basher83/lunar-claude/analyze"><img src="https://agentmods.dev/badge/commands/basher83/lunar-claude/analyze.svg" alt="Measured on agentmods" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 526 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 $0.00007 $0.00526
Opus 5 $0.00003 $0.00263
Sonnet 5 $0.00001 $0.00105
Haiku 4.5 $0.00001 $0.00053

Measured 2d ago against content hash b0fd479644af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

analyze 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/analyze.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Continue the ADR workflow by analyzing options against established criteria.

Use the adr-methodology skill for risk rating definitions.

Prerequisites Check

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

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

  • Inform user that criteria must be defined first
  • Instruct them to run /adr-assistant:new [topic] to start the workflow
  • Stop processing

Phase 1: Options Enumeration

Display the topic and criteria from state file.

Ask user to list the options under consideration. For each option:

  • Name/identifier
  • Brief description (1-2 sentences)

If user hasn't identified options, help brainstorm based on the decision context and constraints.

Phase 2: Risk Assessment

For each option, evaluate against every criterion using risk ratings:

Rating Definition
Low Minimal risk to requirements, performance, or scale
Medium Manageable risk with proper governance
High Significant risk without active mitigation

For each rating, include:

  • Risk level (L/M/H)
  • Brief rationale (1-2 sentences)
  • Mitigation strategy (for Medium/High)

Phase 3: Generate Matrix

Present the analysis as a comparison matrix:

Criterion Option A Option B Option C
[name] Risk: L. [rationale] Risk: M. [rationale] Risk: H. [rationale]

After the matrix, summarize:

  • Strongest option per pillar
  • Key trade-offs between top options
  • Any blocking concerns (High risk on critical criteria)

Phase 4: Refinement

Ask user to review and refine:

  • Adjust any ratings that seem off
  • Add missing considerations
  • Clarify trade-off priorities

Phase 5: Save State

After user confirms analysis, update .claude/adr-session.yaml:

topic: "[decision topic]"
status: "analyzed"
framework: "[framework]"
criteria:
  # ... existing criteria ...
options:
  - name: "[option name]"
    description: "[brief description]"
    ratings:
      "[criterion name]":
        risk: "[Low|Medium|High]"
        rationale: "[explanation]"
        mitigation: "[if Medium/High]"

Read the full file on GitHub · 84 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 · 84 lines · 7 tokens per session scan A b0fd479644af

Subscribe to this mod's changes

analyze is a command published in the GitHub repository basher83/lunar-claude (22 stars, last pushed today), licensed MIT. It adds 7 tokens to every session and 526 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.