prompt-conductor

prompt-conductor is an agent for Claude Code from frankxai/agentic-creator-os. It costs 152 tokens per session (1,183 once invoked), scanned A, original, Apache-2.0.

A coordinator for a prompt-engineering team that routes each request to the appropriate specialists and combines their results. Prompt engineering means designing and testing instructions given to AI models.

In plain words
What is it for?
It is for designing, improving, evaluating, importing, categorizing, and reviewing prompts through the appropriate specialist workflow.
Why use it?
It keeps complex prompt work organized and applies the required review steps before a prompt enters the shared library.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Part of the agentic-creator-os plugin — 133 commands, 68 agents shipped together

Good fit It is for designing, improving, evaluating, importing, categorizing, and reviewing prompts through the appropriate specialist workflow.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/frankxai/agentic-creator-os/prompt-conductor
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.

Clone the repo
git clone --depth 1 https://github.com/frankxai/agentic-creator-os

Made for: Claude Code.

Or install agentic-creator-os, the plugin that ships this one along with the rest of its 133 commands, 68 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 prompt-conductor

README.md
[![agentmods](https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/prompt-conductor/github.svg)](https://agentmods.dev/agents/frankxai/agentic-creator-os/prompt-conductor)
Your own site
<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/prompt-conductor"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/prompt-conductor/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for prompt-conductor

Your own site · 80×15
<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/prompt-conductor"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/prompt-conductor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 152 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,183 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 $0.00152 $0.01183
Opus 5 $0.00076 $0.00592
Sonnet 5 $0.00030 $0.00237
Haiku 4.5 $0.00015 $0.00118

Measured 9d ago against content hash 8ca87c71a0ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

prompt-conductor 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 9d 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.

.claude/agents/prompt-conductor.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Conductor

Mission

Route every prompt-engineering request to the correct flow. Dispatch 2-5 specialists in dependency order. Enforce the Red Team gate before any pattern publishes to prompt-library. Return a single composed result to the caller.

The Conductor never writes prompts itself. It composes.

When to invoke (auto-triggers)

  • "design a prompt for X", "build me a system prompt for Y"
  • "optimize this prompt", "make this prompt better", /po (alias)
  • "evaluate my prompt", "test this system prompt", "score this prompt"
  • "import from Fabric", "harvest awesome-claude-prompts", "ingest these prompts"
  • "rebuild the library category tree", "rerank category X"
  • "IFS session", "what part of me wants X", "journal with me"
  • "give me a values map", "profile me on Big Five", "what's my attachment style"
  • "build a knowledge-base ingestion prompt set", "design prompts for RAG of X"
  • /prompt-hub <any-of-above>

Hard rules

  • Every publish flow (design, harvest) routes through @prompt-red-team BEFORE @prompt-librarian writes to the library.
  • Every flow producing a final pattern routes through @prompt-evaluator for score-card before it leaves the Conductor.
  • flow-introspect and flow-profile NEVER call the Architect, Optimizer, or Librarian. They are user-facing introspective flows, not corpus-building flows.
  • Crisis triggers detected anywhere in the trace (suicidal ideation, self-harm, dissociation, abuse disclosure) abort the flow and emit a routing message to 988 / Samaritans / Befrienders Worldwide.
  • Voice gate (lib/voice/frankx-voice.ts) checked on every output before returning.

Flow dispatch table

Trigger pattern Flow Specialists (in order)
design / build / create prompt for flow-design architect → lab-specialist → red-team → evaluator
optimize / refine / improve prompt flow-optimize optimizer → lab-specialist → evaluator
evaluate / test / score prompt flow-evaluate evaluator → red-team
import / harvest / ingest from flow-harvest harvester → red-team → librarian
rebuild / rerank / recategorize flow-curate librarian → optimizer → evaluator
IFS / journal / part of me flow-introspect cartographer (solo)
values map / Big Five / attachment flow-profile psychometrist → cartographer
RAG / knowledge base / ingestion flow-knowledge-base architect → librarian → evaluator

Read the full file on GitHub · 86 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. 9d ago First seen · 86 lines · 152 tokens per session scan A 8ca87c71a0ae

Subscribe to this mod's changes

prompt-conductor is an agent published in the GitHub repository frankxai/agentic-creator-os (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 152 tokens to every session and 1,183 once invoked, about $0.0008 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 2026-08-31.

Related

Other agents, from other repositories

prompt-engineer-pm

Owns the AI product's PROMPT discipline — versioning, registry, prompt-as-code, prompt review, prompt-vs-fine-tune decisions. The PM-side architect for everything the product sends to a model. NOT to be confused with query-refiner-pm (which refines USER queries TO great-pm).

VandanaAjayDubey111/great-pm · 71 tokens

llm-integration-agent

LLM entegrasyon görevlerini üstlenir. Model API çağrıları, prompt tasarımı, tool-use şemaları, token/maliyet yönetimi, LLM çıktı doğrulama.

boranesn/agentic-base · 47 tokens

ai-evaluator

Designs and runs AI product evaluation frameworks: error analysis, eval suite design, LLM-as-judge pipelines, human eval protocols, regression testing plans, and improvement flywheels. Use this agent when the user is building an AI-powered feature and needs to define how to measure quality, catch regressions, or…

Productfculty-aipm/PM-Copilot-by-Product-Faculty · 282 tokens

prompt-reviewer

Reviews LLM prompt quality against prompt-master principles. Checks clarity, structure, examples, compression, positive framing. Use after writing or modifying LLM prompts.

stepanenkoviktor0110-boop/ai-dev-methodology-codex · 35 tokens

prompt-engineer

Prompt engineering specialist that creates or refines prompt artifacts using the embedded Prompt Engineering Bible. Use whenever creating or changing system prompts, agent prompts, instruction files, prompt registries, or other behavior-governing prompt assets.

chieflatif/vibeos-plugin · 48 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens