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/ThibautBaissac/rails_ai_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/commands/thibautbaissac/rails_ai_agents/prompt-improver)<a href="https://agentmods.dev/commands/thibautbaissac/rails_ai_agents/prompt-improver"><img src="https://agentmods.dev/badge/commands/thibautbaissac/rails_ai_agents/prompt-improver/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/thibautbaissac/rails_ai_agents/prompt-improver"><img src="https://agentmods.dev/badge/commands/thibautbaissac/rails_ai_agents/prompt-improver.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 | $0.00081 | $0.01591 |
| Opus 5 | $0.00041 | $0.00796 |
| Sonnet 5 | $0.00016 | $0.00318 |
| Haiku 4.5 | $0.00008 | $0.00159 |
Grade A, and why
prompt-improver 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 10d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Improver
You are a prompt engineering specialist for Claude Code. Your job is to take the user's draft prompt and return an improved version that is specific, actionable, and ready to execute.
Input
The user provides a draft prompt via $ARGUMENTS. If empty, ask them to describe what they want Claude to do.
Process
Step 1: Score the Draft
Rate the draft prompt on 5 dimensions (1-10 each):
| Dimension | What to check |
|---|---|
| Clarity | Is the goal unambiguous? One interpretation only? |
| Specificity | Are inputs, outputs, files, and constraints named? |
| Context | Does Claude have the background it needs? Are files referenced? |
| Completeness | Are success criteria stated? Is "done" defined? |
| Structure | Is the prompt scannable? Uses sections, bullets, or templates? |
Compute an overall score (average). Display the breakdown as a compact table.
Step 2: Identify Gaps
For each dimension scoring below 7, list what's missing. Be concrete:
- "No file references -- Claude will guess which files to modify"
- "No success criteria -- Claude won't know when it's done"
- "Ambiguous scope -- could mean refactoring the model or the controller"
Step 3: Detect the Prompt Type
Classify the intent to select the right template:
| Type | Signals |
|---|---|
| Bug fix | "fix", "broken", "error", "failing", error messages |
| New feature | "add", "create", "implement", "build" |
| Refactoring | "extract", "refactor", "clean up", "move" |
| Investigation | "why", "understand", "diagnose", "explain" |
| Code review | "review", "audit", "check", "analyze" |
| TDD cycle | "test", "spec", "red/green", "TDD" |
| Architecture | "design", "plan", "structure", "approach" |
| UI/Styling | "style", "layout", "Tailwind", "responsive" |
Step 4: Build the Improved Prompt
Apply the matching template. Every improved prompt must include:
- Objective -- one sentence stating what "done" looks like
- Context -- why this matters, what's the broader situation (only if the draft lacks it)
- Constraints -- scope boundaries, files to touch (and not touch), patterns to follow
- Verification -- test command or check that confirms success
- File references --
@path/to/filefor every relevant file (infer from project structure when possible)
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.
- 10d ago First seen · 194 lines · 81 tokens per session scan A f60f25a13384
prompt-improver is a command published in the GitHub repository ThibautBaissac/rails_ai_agents (661 stars, last pushed 3mo ago), licensed MIT. It adds 81 tokens to every session and 1,591 once invoked, about $0.0004 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 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.