A command for creating, improving, reviewing, or designing prompts—written instructions that guide an AI assistant's responses.

Use it to create prompts, optimise existing ones, review their quality, or design a complete AI agent.

It gives prompt-related tasks a clear workflow instead of requiring you to structure every request from scratch.

prompt — Command for coding agents by fusengine: A command for creating, improving, reviewing, or designing prompts

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.

agentmods

npx agentmods add commands/fusengine/agents/prompt

Clone the repo

git clone --depth 1 https://github.com/fusengine/agents

Or install fuse-prompt-engineer, the plugin that ships this one along with the rest of its 6 skills, 2 commands, 7 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/fusengine/agents/prompt.svg)](https://agentmods.dev/commands/fusengine/agents/prompt)

Your own site

<a href="https://agentmods.dev/commands/fusengine/agents/prompt"><img src="https://agentmods.dev/badge/commands/fusengine/agents/prompt.svg" alt="Measured on agentmods" height="20"></a>

Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 789 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00007	$0.00789
Opus 5	$0.00003	$0.00394
Sonnet 5	$0.00001	$0.00158
Haiku 4.5	$0.00001	$0.00079

Measured yesterday against content hash e244fe1e6c3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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.

plugins/prompt-engineer/commands/prompt.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/prompt Command

Command for creating or optimizing prompts using the prompt-engineer agent.

Usage

/prompt [action] [description]

Actions

Action	Description
`create`	Create a new prompt
`optimize`	Improve an existing prompt
`agent`	Design a complete agent
`review`	Analyze an existing prompt

Workflow

1. Action Detection

IF $ARGUMENTS contains "create" or "new":
  → Action: CREATE
IF $ARGUMENTS contains "optimize" or "improve":
  → Action: OPTIMIZE
IF $ARGUMENTS contains "agent" or "assistant":
  → Action: AGENT_DESIGN
IF $ARGUMENTS contains "review" or "analyze":
  → Action: REVIEW
ELSE:
  → Ask for clarification

2. Agent Launch

Launch prompt-engineer agent with:
- Appropriate skill loaded
- User context
- Identified constraints

3. Workflow Execution

For CREATE:

Identify prompt type (system, task, few-shot, meta)
Identify constraints (model, format, domain)
Apply the 9-element Anthropic structure
Generate prompt with appropriate techniques
Validate with quality checklist

For OPTIMIZE:

Analyze current prompt
Identify issues (clarity, structure, completeness, guardrails)
Apply corrections
Generate before/after report
Propose optimized prompt

For AGENT_DESIGN:

Define identity and purpose
Choose architecture pattern
Define workflow
Configure tools and skills
Implement guardrails
Generate complete agent.md file

For REVIEW:

Analyze according to checklist
Score each criterion (clarity, structure, completeness, guardrails)
Identify strengths and weaknesses
Propose recommendations

Examples

Create a system prompt

/prompt create a technical support assistant for a mobile app

Optimize an existing prompt

/prompt optimize [paste the prompt to improve]

Design an agent

/prompt agent a Python-specialized code reviewer

Analyze a prompt

Read the full file on GitHub · 173 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.

yesterday First seen · 173 lines · 7 tokens per session scan A e244fe1e6c3d

Subscribe to this mod's changes

prompt is a command published in the GitHub repository fusengine/agents (25 stars, last pushed today), licensed MIT. It adds 7 tokens to every session and 789 once invoked, about $0.0000 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 2026-09-03.

Building agents Data and AI Prompting claude-agent claude-agents claude-code claude-code-plugin claude-skills claudecode

prompt