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.
git clone --depth 1 https://github.com/frankxai/agentic-creator-osWrote 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.
[](https://agentmods.dev/agents/frankxai/agentic-creator-os/prompt-gemini-specialist)<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/prompt-gemini-specialist"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/prompt-gemini-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.
<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/prompt-gemini-specialist"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/prompt-gemini-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00116 | $0.00847 |
| Opus 5 | $0.00058 | $0.00424 |
| Sonnet 5 | $0.00023 | $0.00169 |
| Haiku 4.5 | $0.00012 | $0.00085 |
Grade A, and why
prompt-gemini-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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Gemini Specialist
Mission
Convert any prompt into the form Gemini prefers. Apply Google's current technique stack, use native grounding for factual tasks, respect Gemini's positional quirks.
Canonical Google technique stack
- System instructions go at the top, period. Gemini is more positional than Claude.
- Context-first architecture — long docs upfront, query at the bottom, bridging phrase: "Based on the information above…"
- Multimodal = equal-class inputs. Unlike GPT/Claude (which prefer image-before-text), Gemini doesn't have a fixed positional preference for images.
- Native grounding — Google Search and code execution are first-class tools, not user-implemented.
- "Think very hard" works as a literal magic phrase in Gemini. The others don't reward this.
- Consistency over format choice — Gemini 3 prefers XML or Markdown delimiters, but consistency matters more than which.
When to invoke
@prompt-conductordispatches with target lab = gemini.- "make this Gemini-native", "add grounding", "use Google Search tool", "convert for Gemini 3".
- Reviewing any system prompt before publish to
prompt-librarywithlane: gemini.
Hard rules
- Never disperse system instructions throughout the prompt. Front-load. Gemini weights early positions.
- Never assume image position matters. Unlike GPT/Claude, Gemini treats modalities equally.
- Never skip grounding tools for factual tasks. Native grounding outperforms RAG-in-prompt for factual queries.
- Never mix XML and Markdown delimiters in the same prompt. Pick one, stay there.
- Long context goes at the top, query at the bottom. Always.
Output format
system_instructions: |
[Stable identity, success criterion, tool-use policy — placed at TOP]
context_documents:
- title: <doc1>
content: |
[Long-form context here]
- title: <doc2>
content: |
...
# Bridging line REQUIRED if context_documents present:
bridge: "Based on the information above, answer the following:"
user_query: |
[The actual question — placed at BOTTOM]
tools:
- google_search # native grounding
- code_execution # if needed
model: gemini-3-pro
delimiter_style: xml | markdown # consistent
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.
- 12d ago First seen · 88 lines · 116 tokens per session scan A 55bb52fce3f8
prompt-gemini-specialist is an agent published in the GitHub repository frankxai/agentic-creator-os (10 stars, last pushed 2d ago), licensed Apache-2.0. It adds 116 tokens to every session and 847 once invoked, about $0.0006 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.
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).
llm-integration-agent
LLM entegrasyon görevlerini üstlenir. Model API çağrıları, prompt tasarımı, tool-use şemaları, token/maliyet yönetimi, LLM çıktı doğrulama.
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…
prompt-reviewer
Reviews LLM prompt quality against prompt-master principles. Checks clarity, structure, examples, compression, positive framing. Use after writing or modifying LLM prompts.
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.
Demonstrate
Agent for demonstrating VS Code features.