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 agentmods add skills/fusengine/agents/prompt-optimizationnpx skills add fusengine/agents --skill prompt-optimizationgit clone --depth 1 https://github.com/fusengine/agentsWrote 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/fusengine/agents/prompt-optimization)<a href="https://agentmods.dev/skills/fusengine/agents/prompt-optimization"><img src="https://agentmods.dev/badge/skills/fusengine/agents/prompt-optimization.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.00567 |
| Opus 5 | $0.00016 | $0.00283 |
| Sonnet 5 | $0.00006 | $0.00113 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
prompt-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 yesterday.
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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
It never changes the prompt's original meaning, adds unrequested features, removes existing guardrails, or lengthens the prompt without justification. See common-problems.md for before/after fix patterns and improvement-techniques.md for strengthening via CoT, few-shot, or guardrails.
Prompt Optimization
Skill for analyzing and improving existing prompts.
References
- common-problems.md - Load when: diagnosing a vague or ambiguous prompt — 5 before/after examples (vague instructions, missing context, undefined format, no error handling, weak emphasis)
- improvement-techniques.md - Load when: strengthening a prompt with Chain-of-Thought, few-shot examples, or reinforced guardrails
- scorecard-template.md - Load when: writing the before/after optimization report to hand off
Optimization Workflow
1. ANALYZE current prompt
↓
2. IDENTIFY issues
↓
3. APPLY corrections
↓
4. VALIDATE improvement
↓
5. DOCUMENT changes
Analysis Checklist
Clarity
- Unambiguous instructions?
- Clearly defined objective?
- Precise vocabulary?
Structure
- Well-delimited sections?
- Logical order?
- Clear hierarchy?
Completeness
- Output format defined?
- Error cases handled?
- Examples if needed?
Guardrails
- Explicit limits?
- Forbidden behaviors listed?
- Appropriate security?
For common problem patterns with before/after fixes, see common-problems.md. For techniques to strengthen a prompt (CoT, examples, guardrails), see improvement-techniques.md.
What ships with it
3 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.
- yesterday First seen · 67 lines · 32 tokens per session scan A db6448c3cc76
prompt-optimization is a skill published in the GitHub repository fusengine/agents (25 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 567 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
ai-workflow-architect
Designs AI systems, automations, and agent workflows for a business — identifying which manual work is worth automating, how to structure the system, which tools fit, and what could go wrong. Use this to automate part of an operation, design an agent or MCP workflow, reduce repetitive manual work, connect tools into a…
build-dotnet-agent-service
Build a local-first F# or C# Semantic Kernel agent service with explicit tools, model capability checks, evaluation fixtures, and draft-before-write promotion.
craft-ai
The Craftsman standard for LLM-powered features — prompt-injection surface, key and spend protection, PII reaching model APIs, and reliability/eval discipline. Use whenever work touches an LLM integration: a chatbot or agent, a RAG pipeline, an LLM call from a route or job, tool/function-calling, or reviewing prompts…
expert-ai-engineer
AI/ML engineering specialist — LLM integrations, prompt design, RAG pipelines, embeddings, evals, fine-tuning decisions, agent architectures. Use for any task involving model APIs, prompts, vector stores, or ML tradeoffs. Normally invoked by model-router.
prompt-cookbook
Build a prompt cookbook for one company's actual vertical and roles rather than generic examples. Each recipe names the job it does, who runs it, the prompt itself, what good output looks like, and how to tell when it went wrong. Written for people who have never written a prompt and will not read documentation about…
prompt-fixer
Clean up and clarify a rough prompt before acting on it — fix typos, expand a terse or single-word ask into a clear instruction, repair broken or unclosed {{template}} placeholders, substitute known variables, and strip filler openers. Use whenever a request looks hasty: obvious misspellings, a vague one-or-two-word…