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 LegalQuants/lq-ai --skill enhance-promptgit clone --depth 1 https://github.com/LegalQuants/lq-aiWrote 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/legalquants/lq-ai/enhance-prompt)<a href="https://agentmods.dev/skills/legalquants/lq-ai/enhance-prompt"><img src="https://agentmods.dev/badge/skills/legalquants/lq-ai/enhance-prompt/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/legalquants/lq-ai/enhance-prompt"><img src="https://agentmods.dev/badge/skills/legalquants/lq-ai/enhance-prompt.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 | $0.00105 | $0.02759 |
| Opus 5 | $0.00053 | $0.01380 |
| Sonnet 5 | $0.00021 | $0.00552 |
| Haiku 4.5 | $0.00011 | $0.00276 |
Grade C, and why
enhance-prompt scanned grade C with 1 finding 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
- **Prompts that are clearly outside legal practice.** If the user's prompt has nothing to do with legal work (e.g., "what's a good restaurant in Boston," "write a haiku about my dog"), expand using general role/audience Copies of this mod
1 near-identical copy found in the catalogue:
- enhance-prompt — 89% identical, 19 lines differ
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Enhance Prompt
Rewrite the user's prompt into a more effective version before it is submitted to the model. Show the user what changed and why. Make the expansion visible and editable, never silent.
The point of this skill is not to make every prompt longer. It is to surface the implicit assumptions in a short prompt and turn them into explicit instructions, so the model produces what the user actually wanted on the first try rather than after several rounds of clarification.
When this skill applies
Apply when:
- The user has invoked Enhance Prompt explicitly (button click, skill attachment, or trigger phrase).
- The application has Enhance Prompt's auto-expand toggle enabled and the user has just submitted a prompt.
In auto-expand mode, also apply the skip conditions in the next section before producing an expansion. Auto-expand should not be aggressive — many prompts do not need expansion, and producing an expansion when one is not needed is friction rather than value.
When NOT to apply (skip conditions)
Skip the expansion and let the original prompt through unchanged when:
- The prompt is already well-structured. If the user has already specified role, task, constraints, and output format, expansion adds noise. Heuristic: if the prompt is over ~80 words and contains explicit instructions about format, audience, or scope, skip.
- The prompt is conversational or interpersonal. "thanks," "what did you mean by that," "go ahead," "skip that point" — these are conversational moves, not new tasks. Do not expand.
- The prompt is a follow-up question continuing a prior task. When chat_history shows the user is iterating on a previous answer ("can you also add X," "shorter please," "what about California"), the prior turn supplies context; expansion would discard it. Do not expand.
- The prompt is operational rather than substantive. "summarize the document I just uploaded," "translate this," "format this as a table" — these are direct operational asks; expansion adds friction without adding clarity.
- The user has explicitly opted out for this prompt. If the user has typed
--no-enhance-prompt,[skip enhance prompt], or similar, honor it. - A skill is attached that already expands the prompt itself. If
attached_skillsincludes a skill whose description shows it handles prompt expansion or rewriting, skip — let the attached skill drive.
What ships with it
6 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 · 152 lines · 105 tokens per session scan C e35f77e9ac90
enhance-prompt is a skill published in the GitHub repository LegalQuants/lq-ai (136 stars, last pushed yesterday), licensed Apache-2.0. It adds 105 tokens to every session and 2,759 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). 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…