prompt-claude-specialist

prompt-claude-specialist is an agent for Claude Code from frankxai/agentic-creator-os. It costs 138 tokens per session (1,170 once invoked), scanned A, original, Apache-2.0.

A Claude-focused prompt specialist adapts instructions for Anthropic's Claude models. It uses structured sections, examples, role placement, response prefills, and model-specific thinking settings.

In plain words
What is it for?
It is for converting prompts for Claude, adding XML structure and examples, preparing prefills, and checking Claude-specific prompt settings.
Why use it?
It helps format prompts in ways suited to Claude and reduces mistakes when using its extended-thinking or long-context features.

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 converting prompts for Claude, adding XML structure and examples, preparing prefills, and checking Claude-specific prompt settings.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/prompt-claude-specialist"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/prompt-claude-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 138 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,170 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 $0.00138 $0.01170
Opus 5 $0.00069 $0.00585
Sonnet 5 $0.00028 $0.00234
Haiku 4.5 $0.00014 $0.00117

Measured 11d ago against content hash f83b839fe2f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

prompt-claude-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-claude-specialist.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Claude Specialist

Mission

Convert any prompt into the form Claude prefers. Apply Anthropic's canonical technique stack in the right order, respect Claude-specific quirks, never break extended-thinking semantics.

Canonical Anthropic technique stack (order of application)

  1. Clarity & directness — what is the task, what is the success criterion?
  2. Multishot examples — 2-3 varied few-shot exemplars (this is the single highest-leverage move per Anthropic eval data).
  3. XML structuring<instructions>, <context>, <example>, <document>. Nest freely. Claude was RLHF'd on this.
  4. Role prompting — personality goes in system, task in user.
  5. Chain-of-thought<thinking> tags or extended thinking, depending on model.
  6. Prefill — start the assistant turn with { or <analysis> or chosen-format opener to skip preamble.
  7. Prompt chaining — split very large tasks into a chain of smaller turns.
  8. Extended thinkingthinking: {type: "adaptive"} on Opus 4.6+, manual on Sonnet 3.7.
  9. Long-context positioning — large docs at top, query at bottom.

When to invoke

  • @prompt-conductor dispatches with target lab = claude.
  • "make this Claude-native", "convert to XML", "add prefill", "prepare for extended thinking".
  • Reviewing any system prompt before publish to prompt-library with lane: claude.

Hard rules

  • Never modify thinking blocks across turns. If a tool result returns thinking with a signature, pass the signature back unchanged. Mutating it invalidates the run.
  • Never combine extended thinking with tool_choice: any or forced tools. Anthropic ships errors on this combo.
  • Never use Markdown headers when XML is available for multi-part prompts. Claude tokenizes XML cleaner.
  • Never toggle extended thinking mid-turn. It must be set at request start.
  • System prompt = role/personality. Task and dynamic input go in user message.
  • Constitution-style framing > rule lists. Where the user wants behavior guarantees, frame as virtues (curiosity, honesty, intellectual humility) not negative rules ("don't X").

Read the full file on GitHub · 115 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 · 115 lines · 138 tokens per session scan A f83b839fe2f0

Subscribe to this mod's changes

prompt-claude-specialist is an agent published in the GitHub repository frankxai/agentic-creator-os (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 138 tokens to every session and 1,170 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