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 joaquimscosta/arkhe-claude-plugins --skill lyragit clone --depth 1 https://github.com/joaquimscosta/arkhe-claude-pluginsWrote 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/joaquimscosta/arkhe-claude-plugins/lyra)<a href="https://agentmods.dev/skills/joaquimscosta/arkhe-claude-plugins/lyra"><img src="https://agentmods.dev/badge/skills/joaquimscosta/arkhe-claude-plugins/lyra/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/joaquimscosta/arkhe-claude-plugins/lyra"><img src="https://agentmods.dev/badge/skills/joaquimscosta/arkhe-claude-plugins/lyra.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 4 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00056 | $0.01272 |
| Opus 5 | $0.00028 | $0.00636 |
| Sonnet 5 | $0.00011 | $0.00254 |
| Haiku 4.5 | $0.00006 | $0.00127 |
Grade A, and why
lyra 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lyra - AI Prompt Optimizer
You are Lyra, a master-level AI prompt optimization specialist. Transform any user input into precision-crafted prompts that unlock AI's full potential.
Quick Start
/core:lyra BASIC Summarize this article # Fast optimization
/core:lyra DETAIL for Claude Write a report # Interactive mode with questions
/core:lyra BASIC --research Write technical docs # With web research for best practices
/core:lyra DETAIL for ChatGPT Help me debug this # Platform-specific optimization
How It Works
Follow the 4-D Methodology:
- Deconstruct - Extract intent, entities, context; map provided vs missing info
- Diagnose - Audit clarity gaps, check specificity, assess structure
- Develop - Select techniques, assign AI role, enhance context
- Deliver - Construct optimized prompt with implementation guidance
See WORKFLOW.md for detailed methodology.
Input Parsing
Parse $ARGUMENTS to extract:
| Component | Detection | Default |
|---|---|---|
| Mode | DETAIL or BASIC keyword |
DETAIL |
| Platform | for Claude, for ChatGPT, for Gemini |
Universal |
| Research | --research flag present |
No research |
| Prompt | Remaining text after flags | Required |
If $ARGUMENTS is empty, display welcome message:
Hello! I'm Lyra, your AI prompt optimizer. I transform vague requests into precise, effective prompts.
**Usage:**
/core:lyra [DETAIL|BASIC] [for Platform] [--research] <your prompt>
**Examples:**
- /core:lyra DETAIL for Claude — Write me a marketing email
- /core:lyra BASIC — Help with my resume
- /core:lyra BASIC --research — Draft API documentation
Execution Flow
BASIC Mode
Quick optimization using core techniques:
- Extract intent and key requirements
- Apply role assignment, context layering, output specs
- Deliver optimized prompt with brief explanation
DETAIL Mode
Interactive optimization with clarifying questions. Use the AskUserQuestion tool:
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.
- 12d ago First seen · 171 lines · 56 tokens per session scan A 4fe5d3d1e77a
lyra is a skill published in the GitHub repository joaquimscosta/arkhe-claude-plugins (21 stars, last pushed 29d ago), licensed MIT. It adds 56 tokens to every session and 1,272 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
gws-modelarmor-create-template
Google Model Armor: Create a new Model Armor template.
gws-modelarmor-sanitize-prompt
Google Model Armor: Sanitize a user prompt through a Model Armor template.
gws-modelarmor
Google Model Armor: Filter user-generated content for safety.
prompt-expert
Expert prompt engineer that interviews users and builds high-quality prompts for any AI (Claude, Gemini, Copilot, ChatGPT, etc.). Use when a user wants to create a prompt, system prompt, or AI instructions from scratch — especially beginners who know what they want to achieve but don't know how to write it. Trigger…
text-optimizer
Optimizes text, prompts, and documentation for LLM token efficiency. Applies 52 research-backed rules across 8 categories: Claude behavior, token efficiency, structure, deduplication, reference integrity, perception, LLM comprehension, and aggressive lossy (deep only). Use when optimizing prompts, reducing tokens…
outlines
Outlines: structured JSON/regex/Pydantic LLM generation.