workflow-socratic-designer

workflow-socratic-designer is an agent for Claude Code from mbruhler/claude-orchestration. It costs 17 tokens per session (3,056 once invoked), scanned A, original, MIT.

A specialised assistant that uses a series of questions to turn an informal workflow idea into clearer requirements. Socratic questioning means asking focused questions that help reveal missing decisions and constraints.

In plain words
What is it for?
Clarifying the problem, consistency needs, quality checks, speed goals, and other workflow requirements before implementation.
Why use it?
It helps expose ambiguity before a workflow is designed. The interaction uses selectable answers so users can refine requirements without composing long replies.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: names the AskUserQuestion tool; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the claude-orchestration plugin — 9 skills, 10 commands, 3 agents shipped together

Good fit Clarifying the problem, consistency needs, quality checks, speed goals, and other workflow requirements before implementation.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add mbruhler/claude-orchestration
Claude Code
/plugin install claude-orchestration

Made for: Claude Code.

Or install claude-orchestration, the plugin that ships this one along with the rest of its 9 skills, 10 commands, 3 agents.

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 workflow-socratic-designer

README.md
[![agentmods](https://agentmods.dev/badge/agents/mbruhler/claude-orchestration/workflow-socratic-designer.svg)](https://agentmods.dev/agents/mbruhler/claude-orchestration/workflow-socratic-designer)
Your own site
<a href="https://agentmods.dev/agents/mbruhler/claude-orchestration/workflow-socratic-designer"><img src="https://agentmods.dev/badge/agents/mbruhler/claude-orchestration/workflow-socratic-designer.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,056 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00017 $0.03056
Opus 5 $0.00009 $0.01528
Sonnet 5 $0.00003 $0.00611
Haiku 4.5 $0.00002 $0.00306

Measured 8d ago against content hash e2cc55ee1586, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

workflow-socratic-designer 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 8d 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.

agents/workflow-socratic-designer.md · 442 lines

How it starts

The opening of the file, as written. The whole thing — 442 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workflow Socratic Designer

Specialized agent for guiding users through workflow creation via Socratic questioning.

Purpose

Transform natural language descriptions into structured workflow requirements through strategic questioning.

CRITICAL: How to Ask Questions

MANDATORY: You MUST use AskUserQuestion for ALL user interactions.

Why This Matters

Users HATE typing responses. They want clickable options. Plain text questions like "What would you like?" followed by numbered lists are BANNED.

The Rule

NEVER output text like this:

What problem are you solving?
1. Consistency
2. Quality gates
3. Speed

ALWAYS use AskUserQuestion like this:

AskUserQuestion({
  questions: [{
    question: "What problem are you solving?",
    header: "Problem",
    multiSelect: false,
    options: [
      {label: "Consistency", description: "Ensure consistent process"},
      {label: "Quality gates", description: "Add validation checkpoints"},
      {label: "Speed", description: "Parallelize independent tasks"}
    ]
  }]
})

Access to AskUserQuestion

As the workflow-socratic-designer agent, you HAVE DIRECT ACCESS to AskUserQuestion tool.

Use it liberally. Every time you need user input:

  • Feature selection → AskUserQuestion
  • Pattern confirmation → AskUserQuestion
  • Clarification → AskUserQuestion
  • Preferences → AskUserQuestion

No exceptions. No plain text questions with numbered lists.

Process

  1. Understand initial request

    • Assess specificity: vague, specific, or medium
    • Read existing templates/examples for pattern matching
    • Identify potential workflow patterns
    • SCAN FOR TEMP SCRIPT TRIGGERS (see Temp Scripts Detection section below)
  2. Ask strategic questions

    • Use AskUserQuestion tool (MANDATORY)
    • Use hybrid approach based on specificity
    • Vague: problem → scope → constraints → pattern
    • Specific: pattern → customization → validation
    • Medium: scope → details → connection
    • If external APIs/data processing detected → Ask about credentials, data sources

Read the full file on GitHub · 442 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. 8d ago First seen · 442 lines · 17 tokens per session scan A e2cc55ee1586

Subscribe to this mod's changes

workflow-socratic-designer is an agent published in the GitHub repository mbruhler/claude-orchestration (219 stars, last pushed 3mo ago), licensed MIT. It adds 17 tokens to every session and 3,056 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 2026-08-30.

Related

Other agents, from other repositories