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.
git clone --depth 1 https://github.com/onmyway133/claude-code-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/commands/onmyway133/claude-code-plugins/improve-prompt)<a href="https://agentmods.dev/commands/onmyway133/claude-code-plugins/improve-prompt"><img src="https://agentmods.dev/badge/commands/onmyway133/claude-code-plugins/improve-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/commands/onmyway133/claude-code-plugins/improve-prompt"><img src="https://agentmods.dev/badge/commands/onmyway133/claude-code-plugins/improve-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 | $0.00000 | $0.00578 |
| Opus 5.5 | $0.00000 | $0.00231 |
| Sonnet 5.5 | $0.00000 | $0.00116 |
| Haiku 4.5 | $0.00000 | $0.00058 |
Grade A, and why
improve-prompt 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 1mo 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Improver
Analyze and enhance vague or incomplete prompts before execution.
Usage
/prompt-improver [prompt]
Arguments:
prompt- The original prompt to analyze and improve
Process
Step 1: Analyze the Prompt
Evaluate for:
- Clarity: Is the intent clear?
- Specificity: Are requirements concrete?
- Context: Is there enough background?
- Scope: Are boundaries defined?
- Success criteria: How do we know when it's done?
Step 2: Identify Gaps
Look for missing information:
| Gap Type | Example |
|---|---|
| Ambiguous target | "Fix the bug" - which bug? |
| Missing context | "Update the API" - what change? |
| Unclear scope | "Improve performance" - where? how much? |
| No success criteria | "Make it better" - better how? |
| Missing constraints | "Add a feature" - any limitations? |
Step 3: Research Context
Before asking questions, gather context:
- Check recent git changes
- Look at open files or selections
- Review related code
- Understand existing patterns
Step 4: Generate Clarifying Questions
Ask targeted questions to fill gaps:
To help you effectively, I need to clarify:
1. **Target**: [Specific question about what to change]
2. **Scope**: [Question about boundaries]
3. **Constraints**: [Question about limitations]
4. **Priority**: [Question about what matters most]
Keep questions:
- Specific and actionable
- Limited to 2-4 most important gaps
- Informed by context already gathered
Step 5: Reformulate the Prompt
Once clarified, rewrite as a clear, actionable prompt:
Original: "Fix the login"
Improved: "Fix the login issue where users with special characters in their password cannot authenticate. The bug is in the password validation logic in auth.ts. Success criteria: users can login with any valid password."
Output Format
## Prompt Analysis
**Original**: [original prompt]
**Clarity Score**: Low / Medium / High
**Gaps Identified**:
- [Gap 1]
- [Gap 2]
**Context Found**:
- [Relevant context from codebase]
**Clarifying Questions**:
1. [Question 1]
2. [Question 2]
---
After user responds:
## Improved Prompt
[Clear, specific, actionable version]
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.
- 1mo ago First seen · 107 lines · 0 tokens per session scan A a57728443598
improve-prompt is a command published in the GitHub repository onmyway133/claude-code-plugins (5 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 578 tokens. 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 2026-08-31.
Other commands, from other repositories
evaluation-report
Generate a comprehensive evaluation report for a trained model, highlighting performance, baselines, and subgroup metrics.
experiment-preflight
Audit an ML training script or pipeline for reproducibility, tracking, and basic hygiene before a long run.
leakage-check
Audit data preprocessing and splitting logic for target leakage.
ml-run-review
Review a machine learning training run or experiment configuration for soundness, reproducibility, and evaluation rigor.
prompt-optimize
Legacy slash-entry shim for the prompt-optimizer skill. Prefer the skill directly.
audit-prompt
Evaluate an existing prompt for clarity, effectiveness, and edge cases.