analyze

analyze is a command for Claude Code from shakerdesigns/read-the-room. It costs 39 tokens per session (340 once invoked), scanned A, original, MIT.

A guide for structuring recommendations with the SCR framework: Situation, Complication, and Resolution. It helps turn a rough idea into a message with context, a clear problem, and a specific recommendation.

In plain words
What is it for?
Use it to prepare pitches, recommendations, proposals, or other messages, then tighten the wording and anticipate objections.
Why use it?
It helps prevent presentations from being vague or poorly ordered. The framework makes clear what the audience needs to know and what action is requested.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

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/shakerdesigns/read-the-room/analyze
Clone the repo
git clone --depth 1 https://github.com/shakerdesigns/read-the-room

Made for: Claude Code.

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/shakerdesigns/read-the-room/analyze.svg)](https://agentmods.dev/commands/shakerdesigns/read-the-room/analyze)
Your own site
<a href="https://agentmods.dev/commands/shakerdesigns/read-the-room/analyze"><img src="https://agentmods.dev/badge/commands/shakerdesigns/read-the-room/analyze.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 340 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 $0.00039 $0.00340
Opus 5 $0.00019 $0.00170
Sonnet 5 $0.00008 $0.00068
Haiku 4.5 $0.00004 $0.00034

Measured 6d ago against content hash 09d31dae00ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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.

commands/analyze.md · 54 lines

What it actually says

You're helping the user structure a message for someone in a receptive C-state using the SCR Framework.

Ask: "What do you need to communicate? Give me the rough version and I'll help you structure it."

Then help them build each component:

S = Situation

What's happening? Start with agreed-upon facts.

Help them identify:

  • What does the audience already know?
  • What's the shared starting point?
  • What context sets the stage?

Template: "We're currently seeing X..." or "As you know, X..."

C = Complication

Why does it matter? Create tension.

Help them articulate:

  • What's the problem or opportunity?
  • What are the consequences if unaddressed?
  • Why should they care NOW?

Template: "The challenge is Y, which means Z..."

R = Resolution

What do you recommend? Be specific.

Help them clarify:

  • What's the recommended action?
  • What are the key steps?
  • What do you need from them?

Template: "I recommend we do A, B, C..."

Review & Refine

Once they have a draft, offer to:

  • Tighten the language
  • Strengthen the complication (more urgency)
  • Make the resolution more specific
  • Anticipate objections

Reminder: SCR works best when they're in a C-state. If you sense they might be defensive, suggest starting with validation first using /validate.

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. 6d ago First seen · 54 lines · 39 tokens per session scan A 09d31dae00ae

Subscribe to this mod's changes

analyze is a command published in the GitHub repository shakerdesigns/read-the-room (18 stars, last pushed 5mo ago), licensed MIT. It adds 39 tokens to every session and 340 once invoked, about $0.0002 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 2026-08-30.