Borrowing it
Nothing to install: this file belongs to that0n3guy/mealie-mcp-server-ts. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/that0n3guy/mealie-mcp-server-ts/main/.claude/commands/clavix/improve.mdgit clone --depth 1 https://github.com/that0n3guy/mealie-mcp-server-tsWrote 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/commands/that0n3guy/mealie-mcp-server-ts/improve)<a href="https://agentmods.dev/commands/that0n3guy/mealie-mcp-server-ts/improve"><img src="https://agentmods.dev/badge/commands/that0n3guy/mealie-mcp-server-ts/improve/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/commands/that0n3guy/mealie-mcp-server-ts/improve"><img src="https://agentmods.dev/badge/commands/that0n3guy/mealie-mcp-server-ts/improve.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 | $0.00000 | $0.12867 |
| Opus 5 | $0.00000 | $0.06434 |
| Sonnet 5 | $0.00000 | $0.02573 |
| Haiku 4.5 | $0.00000 | $0.01287 |
Grade C, and why
improve scanned grade C with 2 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 8d 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
**⚠️ Never tell the user a file was saved without verifying it exists.** Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
> Here's the improved version: [show prompt]" How it starts
The opening of the file, as written. The whole thing — 1,684 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clavix: Improve Your Prompt
What This Does
When you run /clavix:improve, I:
- Analyze your prompt quality - 6-dimension assessment (Clarity, Efficiency, Structure, Completeness, Actionability, Specificity)
- Select optimal depth - Auto-choose standard vs comprehensive based on quality score
- Apply improvement patterns - Transform using proven optimization techniques
- Generate optimized version - Create enhanced prompt with quality feedback
- Save for implementation - Store in
.clavix/outputs/prompts/for/clavix:implement
Smart Depth Selection:
- Quality ≥ 75%: Comprehensive depth (add polish and enhancements)
- Quality 60-74%: User choice (borderline quality)
- Quality < 60%: Standard depth (focus on basic fixes)
Important: This is Planning Mode
This is a prompt improvement workflow. Your job is to ANALYZE and IMPROVE the prompt, then STOP.
What this mode does:
- Analyze the user's prompt for quality
- Apply improvement patterns
- Generate an optimized version
- Save to
.clavix/outputs/prompts/
What this mode does NOT do:
- Write application code
- Implement features described in the prompt
- Modify files outside
.clavix/ - Explore the codebase
After improving the prompt: Tell the user to run /clavix:implement --latest when ready to build.
CLAVIX MODE: Prompt Improvement
You are in prompt improvement mode. You help analyze and improve PROMPTS, not implement features.
Your role:
- Analyze prompts for quality
- Apply improvement patterns
- Generate improved versions
- Provide quality assessments
- Save the optimized prompt
- STOP after improvement
Mode boundaries:
- Do not write application code for the feature
- Do not implement what the prompt describes
- Do not generate actual components/functions
- Do not continue after showing the improved prompt
You are improving prompts, not building what they describe.
Self-Correction Protocol
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.
- 8d ago First seen · 1,684 lines · 0 tokens per session scan C b722ef417f04
improve is a command published in the GitHub repository that0n3guy/mealie-mcp-server-ts (0 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 12,867 tokens. A static security scan graded it C with 2 findings (subtle steering, asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
prompt
System instructions for writing effective prompts. Apply when generating commands, skills, agents, or any LLM instructions.
prompt-show
Display full details of a saved prompt by ID.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
ai
Load the Kaizen skill for production-ready AI agent implementation with signature-based programming and multi-agent coordination.
audit-prompt
Evaluate an existing prompt for clarity, effectiveness, and edge cases.
develop-image-prompt.eval
Generates a detailed image generation prompt from a document or content description. Good output: a prompt that is specific, visual, non-abstract, includes style/composition/lighting guidance, and is calibrated to the specified dimensions and style options.