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.
npx skills add danielraffel/generous-corp-marketplace --skill prompt-repetition-optimizationgit clone --depth 1 https://github.com/danielraffel/generous-corp-marketplaceWrote 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/skills/danielraffel/generous-corp-marketplace/prompt-repetition-optimization)<a href="https://agentmods.dev/skills/danielraffel/generous-corp-marketplace/prompt-repetition-optimization"><img src="https://agentmods.dev/badge/skills/danielraffel/generous-corp-marketplace/prompt-repetition-optimization/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/skills/danielraffel/generous-corp-marketplace/prompt-repetition-optimization"><img src="https://agentmods.dev/badge/skills/danielraffel/generous-corp-marketplace/prompt-repetition-optimization.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 | $0.00068 | $0.01889 |
| Opus 5 | $0.00034 | $0.00945 |
| Sonnet 5 | $0.00014 | $0.00378 |
| Haiku 4.5 | $0.00007 | $0.00189 |
Grade A, and why
Prompt Repetition Optimization 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Repetition Optimization
Overview
Prompt repetition is a simple yet effective technique discovered by Google Research that improves LLM performance on non-reasoning tasks by enabling each prompt token to attend to every other prompt token. The technique transforms <QUERY> into <QUERY><QUERY>, allowing bidirectional attention in causal language models.
Key benefits:
- 47 wins, 0 losses across major models (Gemini, GPT, Claude, DeepSeek)
- No latency penalty (only affects parallelizable prefill stage)
- No output format changes
- Safe even with reasoning tasks (neutral to slightly positive)
When to Use Prompt Repetition
Best for Non-Reasoning Tasks
Apply prompt repetition to tasks that don't require complex multi-step reasoning:
Multiple Choice Questions:
- Especially effective with "options-first" format (options before question)
- Example: "A, B, C, D... Which is correct?"
List Navigation:
- Finding Nth item in a list
- Finding item between two other items
- Example: "What's the 25th name?" or "What appears between X and Y?"
Simple Queries:
- Fact retrieval
- Basic transformations
- Short prompts (under ~500 characters)
Pattern Recognition:
- Simple classification tasks
- Basic matching operations
Less Effective for Reasoning Tasks
Avoid emphasizing repetition for tasks requiring complex reasoning:
- Multi-step planning
- Complex debugging
- Deep analysis requiring chain-of-thought
- Tasks already using "think step by step"
Note: Prompt repetition is neutral to slightly positive even with reasoning enabled (5 wins, 1 loss, 22 neutral), so it's safe to use but provides minimal benefit.
How to Apply Prompt Repetition
Recognize Opportunities
When user submits a prompt, evaluate if it's a non-reasoning task:
Non-reasoning indicators:
- Short, direct questions
- Multiple choice format
- List-based queries
- Fact retrieval requests
- Simple classification
Reasoning indicators:
- "Plan", "design", "analyze"
- Multi-step requirements
- Complex debugging
- Already using chain-of-thought
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 226 lines · 68 tokens per session scan A e0624444898c
Prompt Repetition Optimization is a skill published in the GitHub repository danielraffel/generous-corp-marketplace (11 stars, last pushed 13d ago), licensed MIT. It adds 68 tokens to every session and 1,889 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…