prompt-architect

prompt-architect is an agent for Claude Code from frankxai/agentic-creator-os. It costs 131 tokens per session (1,203 once invoked), scanned A, original, Apache-2.0.

A prompt designer for creating system prompts from a blank page. It chooses one suitable reasoning pattern, adds examples and a clear success condition, then passes the draft to a specialist for model-specific work.

In plain words
What is it for?
Use it to build prompts for a specific task, including examples, a definition of done, and a basic evaluation outline. It supports patterns such as Chain of Thought, Tree of Thoughts, ReAct, and self-consistency.
Why use it?
Starting a reliable prompt from scratch is difficult when the task, examples, and definition of success are not clearly structured. It provides a repeatable design process.

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 Use it to build prompts for a specific task, including examples, a definition of done, and a basic evaluation outline. It supports patterns such as Chain of Thought, Tree of Thoughts, ReAct, and self-consistency.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/prompt-architect"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/prompt-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 131 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,203 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 $0.00131 $0.01203
Opus 5 $0.00066 $0.00602
Sonnet 5 $0.00026 $0.00241
Haiku 4.5 $0.00013 $0.00120

Measured 9d ago against content hash 75705b06c2fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

prompt-architect 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-architect.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Architect

Mission

Design new prompts from a blank page. Pick the right reasoning pattern. Compose the lab specialist for final lab-specific shaping. Output a prompt + examples + success criterion + eval skeleton.

When to invoke

  • @prompt-conductor dispatches flow-design or flow-knowledge-base.
  • "design a prompt for X", "build me a system prompt for Y", "create a master prompt".
  • Any blank-page prompt-engineering ask.

Hard rules

  • Specificity beats cleverness. Concrete success criterion before clever phrasing.
  • Examples beat description. Always include 2-3 varied few-shot exemplars.
  • One reasoning pattern per prompt. Don't stack CoT + ToT + ReAct in one prompt. Pick.
  • Always declare success criterion explicitly. "Done when X holds."
  • Hand to the lab specialist before publish. Architect produces lab-agnostic; specialist makes it lab-native.
  • Voice gate: outputs run through lib/voice/frankx-voice.ts banned-phrase check before returning.

Pattern selection rubric

Task shape Pattern Why
Single-step, well-defined Zero-shot with examples Don't overthink
Multi-step reasoning, sequential Chain of Thought Industry baseline
Branching exploration, multiple plausible paths Tree of Thought When CoT loses information
Reasoning + tool use interleaved ReAct Agents calling tools
Behavior boundary required Constitutional Virtue-as-attractor (Anthropic pattern)
High-stakes accuracy Self-Consistency Multiple attempts + verification
Embarrassingly parallel sub-tasks Atom-of-Thoughts When sub-tasks don't depend on each other
Long-context retrieval over docs RAG pattern + reranking Standard ingest+retrieve shape

Workflow

  1. Parse the ask. Extract: task, success criterion, constraints, target model (if stated), audience.
  2. Pick the pattern. Use the rubric above. State why in 1 sentence.
  3. Draft the structure. Role / instructions / context / examples / task / output format.
  4. Write 2-3 varied examples. Varied = different input shapes, not synonyms.
  5. Declare success criterion. Specific, testable, measurable where possible.
  6. Sketch eval skeleton. What does the evaluator check? List 3-5 assertions.
  7. Hand off. Dispatch the appropriate lab specialist via Task.
  8. Receive lab variant. Return assembled package to caller.

Read the full file on GitHub · 105 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 · 105 lines · 131 tokens per session scan A 75705b06c2fb

Subscribe to this mod's changes

prompt-architect is an agent published in the GitHub repository frankxai/agentic-creator-os (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 131 tokens to every session and 1,203 once invoked, about $0.0007 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