conductor:setup

Commands for scaffolding a software project and setting up its Conductor environment, a set of files that records project context and workflow.

In plain words
What is it for?
Use them to detect the project, create starter files, read or update setup state, and copy templates for selected programming languages.
Why use it?
They help establish the project structure and track setup progress when starting work with the Conductor method.

Command

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/rbarcante/claude-conductor/setup
Clone the repo
git clone --depth 1 https://github.com/rbarcante/claude-conductor
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 2,711 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 $0.00017 $0.02711
Opus 5 $0.00009 $0.01355
Sonnet 5 $0.00003 $0.00542
Haiku 4.5 $0.00002 $0.00271

Measured 2d ago against content hash ab5780bf43cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

conductor:setup 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.

commands/setup.md · 318 lines

How it starts

The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context

!python ${CLAUDE_PLUGIN_ROOT}/scripts/conductor_cli.py --json setup state --get 2>/dev/null; python ${CLAUDE_PLUGIN_ROOT}/scripts/conductor_cli.py --json setup detect

<system_directive>

1.0 SYSTEM DIRECTIVE

You are an AI agent. Set up and manage a software project using the Conductor methodology. Adhere to these instructions precisely and sequentially.

</system_directive>


<cli_reference>

CLI Reference

python ${CLAUDE_PLUGIN_ROOT}/scripts/conductor_cli.py --json setup scaffold
python ${CLAUDE_PLUGIN_ROOT}/scripts/conductor_cli.py --json setup state --set "STEP_NAME"
python ${CLAUDE_PLUGIN_ROOT}/scripts/conductor_cli.py --json setup copy-templates --languages LANG1 LANG2

Fallback: If context injection fails: read conductor/setup_state.json for state, check for .git, package.json, pom.xml, requirements.txt, go.mod, src/, app/, lib/ for project detection.

</cli_reference>


AskUserQuestion Protocol

Full Reference: templates/askuserquestion-patterns.md

Rule Constraint
Header Max 12 characters
Options 2-4 per question
Sequential One question at a time
multiSelect true for additive, false for exclusive

Auto-Generate Behavior: When user selects "Auto-generate", stop asking questions, use context to infer remaining details, generate document, present for approval.


1.1 RESUME CHECK

  1. Parse Injected Context: Check for last_successful_step in first JSON object from # Context.

  2. Resume Mapping:

State Value Resume Action
2.0.2_analysis Skip to Section 2.1
2.1_product_guide Skip to Section 2.2
2.2_product_guidelines Skip to Section 2.3
2.3_tech_stack Skip to Section 2.4
2.4_code_styleguides Skip to Section 2.5
2.5_workflow Skip to 2.5.1 (brownfield) or 2.6 (greenfield)
2.5.1_docs_generated Skip to Section 2.6
3.3_initial_track_generated Announce complete, halt. Use /conductor:newTrack or /conductor:implement

Read the full file on GitHub · 318 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 · 318 lines · 17 tokens per session scan A ab5780bf43cf

Subscribe to this mod's changes

conductor:setup is a command published in the GitHub repository rbarcante/claude-conductor (56 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 17 tokens to every session and 2,711 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.