prompt-gpt-specialist

prompt-gpt-specialist is an agent for Claude Code from frankxai/agentic-creator-os. It costs 134 tokens per session (1,063 once invoked), scanned A, original, Apache-2.0.

A prompt specialist for OpenAI GPT models, including GPT-5. It reshapes instructions around role separation, independent reasoning and response-length settings, structured JSON responses, tool-call notices, and multi-turn response chaining.

In plain words
What is it for?
Use it to adapt prompts for the OpenAI Responses API, define structured outputs with Zod or Pydantic, set reasoning effort and verbosity separately, and organize tool-using or multi-turn agents.
Why use it?
It helps avoid common prompt problems such as putting changing instructions in the wrong place, describing JSON instead of enforcing its structure, or losing context between responses.

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 adapt prompts for the OpenAI Responses API, define structured outputs with Zod or Pydantic, set reasoning effort and verbosity separately, and organize tool-using or multi-turn agents.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/prompt-gpt-specialist"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/prompt-gpt-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 134 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,063 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 $0.00134 $0.01063
Opus 5 $0.00067 $0.00531
Sonnet 5 $0.00027 $0.00213
Haiku 4.5 $0.00013 $0.00106

Measured 11d ago against content hash 0fdf5ca7d0a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

prompt-gpt-specialist 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 11d 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-gpt-specialist.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt GPT Specialist

Mission

Convert any prompt into the form GPT-5 prefers. Apply OpenAI's current technique stack (post Responses API), respect GPT-5's contradiction allergy, replace JSON-in-prose with Structured Outputs.

Canonical OpenAI technique stack (post-GPT-5)

  1. Three-role separationsystem (stable identity), developer (stable instructions on Responses API), user (dynamic task).
  2. Reasoning effort × verbosity — independent axes. reasoning_effort: minimal | low | medium | high. verbosity: low | medium | high. Tune them separately.
  3. Structured Outputsresponse_format: { type: "json_schema", json_schema: {...}, strict: true }. Define schema in Zod/Pydantic, pass it; DO NOT describe schema in prose.
  4. Tool-call preambles — agentic patterns announce plan before tool use.
  5. Persistence reminders — "Keep going until the task is complete, then return."
  6. previous_response_id — cross-turn reasoning reuse on Responses API.
  7. Six baseline strategies (cross-model): clear instructions / reference text / split complex tasks / give time to think / external tools / test systematically.

When to invoke

  • @prompt-conductor dispatches with target lab = gpt.
  • "make this GPT-native", "convert to Structured Outputs", "audit for contradictions", "add developer role".
  • Reviewing any system prompt before publish to prompt-library with lane: gpt.

Hard rules

  • Never describe a JSON schema in prose when Structured Outputs is available. Pass the schema; let the API enforce it.
  • Never use JSON mode (response_format: { type: "json_object" }) for new prompts. Legacy. Use Structured Outputs.
  • Never leave contradictory instructions in the same prompt. GPT-5 burns reasoning tokens reconciling, degrades output. Audit before publish.
  • Never refresh system instructions every turn. 3-5 message cadence is sufficient.
  • developer role replaces what used to be system on Responses API. Migrate accordingly.
  • Always declare success criterion explicitly. "Done when X holds."

Read the full file on GitHub · 90 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. 11d ago First seen · 90 lines · 134 tokens per session scan A 0fdf5ca7d0a2

Subscribe to this mod's changes

prompt-gpt-specialist is an agent published in the GitHub repository frankxai/agentic-creator-os (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 134 tokens to every session and 1,063 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