prompt

prompt is a skill for Claude Code from renanflustosa/octo-cluster. It costs 17 tokens per session (810 once invoked), scanned A, original, MIT.

A prompt-writing helper that turns a rough request into a precise set of instructions for an AI coding tool. It only writes the prompt and does not carry out the requested work.

In plain words
What is it for?
Use it to prepare requests for Cursor or Claude Code, including requests that should ask questions, make a plan, or edit code.
Why use it?
It removes ambiguity and makes the intended task, limits, and success conditions clearer before an AI agent starts. This helps prevent the agent from choosing the wrong approach or editing when it should only explain.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions Claude Code.

Good fit Use it to prepare requests for Cursor or Claude Code, including requests that should ask questions, make a plan, or edit code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/renanflustosa/octo-cluster/prompt
Install

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.

Any agent
npx skills add renanflustosa/octo-cluster --skill prompt
Clone the repo
git clone --depth 1 https://github.com/renanflustosa/octo-cluster

Made for: Claude Code.

Wrote 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.

agentmods badge for prompt

README.md
[![agentmods](https://agentmods.dev/badge/skills/renanflustosa/octo-cluster/prompt/github.svg)](https://agentmods.dev/skills/renanflustosa/octo-cluster/prompt)
Your own site
<a href="https://agentmods.dev/skills/renanflustosa/octo-cluster/prompt"><img src="https://agentmods.dev/badge/skills/renanflustosa/octo-cluster/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.

agentmods 80×15 button for prompt

Your own site · 80×15
<a href="https://agentmods.dev/skills/renanflustosa/octo-cluster/prompt"><img src="https://agentmods.dev/badge/skills/renanflustosa/octo-cluster/prompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 810 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00017 $0.00810
Opus 5 $0.00009 $0.00405
Sonnet 5 $0.00003 $0.00162
Haiku 4.5 $0.00002 $0.00081

Measured 2d ago against content hash 8554aca006cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-18, from the pricing page.

Security

Grade A, and why

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 2d 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.

.claude/skills/prompt/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

prompt

Transform the user message into a professional, precise prompt for the AI coding tool running this skill (Cursor or Claude Code). Never execute the requested task. Output only the optimized prompt package.

Usage: /prompt <any request> — the rest of the user message is the raw request to rewrite.

Raw request: $ARGUMENTS


Role

You are a Prompt Engineering specialist for AI coding agents.

Your mission is to transform any user request into a professional, precise, agent-optimized prompt.

Never execute the requested task.

Your only job is to produce the best possible prompt.


Process

  1. Understand the user's real objective.
  2. Detect ambiguities, implicit requirements, and possible problems.
  3. Fully restructure the request.
  4. Add context when necessary.
  5. Define clear objectives.
  6. Define constraints.
  7. Define success criteria.
  8. Automatically choose the best mode.

Mode selection

Recommend exactly one of the modes below. Name the matching control of the tool in use:

Mode Cursor Claude Code
ASK Ask mode Normal chat; prompt says "do not edit files"
PLAN Plan mode Plan mode (Shift+Tab)
AGENT Agent mode Normal / auto-accept edits

ASK

Use when the user wants to:

  • answer questions
  • explain code
  • research
  • review ideas
  • analyze architecture
  • brainstorm
  • documentation (read/explain, not write into the repo)

PLAN

Use when the work requires planning before modifying files.

Examples:

  • large refactors
  • project reorganization
  • repository cleanup
  • migrations
  • architecture
  • multi-step breakdown
  • audits
  • impact analysis

AGENT

Use when the intent is to execute changes.

Examples:

  • write code
  • edit files
  • create tests
  • implement features
  • fix bugs
  • renames
  • generate documentation into the repo
  • apply refactors

Never recommend AGENT when the request still needs planning.


Required improvements

Whenever possible, add:

  • Role
  • Objective
  • Context
  • Constraints
  • Decision criteria
  • Success criteria
  • Rules
  • Expected response format
  • Execution order
  • What must not be done

Read the full file on GitHub · 170 lines

Changes

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.

  1. 2d ago First seen · 170 lines · 17 tokens per session scan A 8554aca006cb

Subscribe to this mod's changes

prompt is a skill published in the GitHub repository renanflustosa/octo-cluster (4 stars, last pushed 3d ago), licensed MIT. It adds 17 tokens to every session and 810 once invoked, about $0.0001 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 2026-09-16.