save-prompt

save-prompt is a command for coding agents from NikiforovAll/claude-code-rules. It costs 15 tokens per session (356 once invoked), scanned A, original, Apache-2.0.

A command that turns the current conversation into a reusable prompt and saves it as a Markdown file.

In plain words
What is it for?
Use it to create a generalized prompt with placeholders, a short description, and an optional argument hint, saved under a concise kebab-case filename.
Why use it?
It removes conversation-specific details while preserving the general task pattern, so the prompt can be reused later.

Command

Part of the handbook-extras plugin — 7 commands, 4 agents shipped together

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/nikiforovall/claude-code-rules/save-prompt
Clone the repo
git clone --depth 1 https://github.com/NikiforovAll/claude-code-rules

Or install handbook-extras, the plugin that ships this one along with the rest of its 7 commands, 4 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.

agentmods badge for save-prompt

README.md
[![agentmods](https://agentmods.dev/badge/commands/nikiforovall/claude-code-rules/save-prompt.svg)](https://agentmods.dev/commands/nikiforovall/claude-code-rules/save-prompt)
Your own site
<a href="https://agentmods.dev/commands/nikiforovall/claude-code-rules/save-prompt"><img src="https://agentmods.dev/badge/commands/nikiforovall/claude-code-rules/save-prompt.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 356 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.

ModelPer sessionOnce invoked
Fable 5 $0.00015 $0.00356
Opus 5 $0.00008 $0.00178
Sonnet 5 $0.00003 $0.00071
Haiku 4.5 $0.00002 $0.00036

Measured 4d ago against content hash fa4d5b23575a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

save-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 4d 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.

plugins/handbook-extras/commands/save-prompt.md · 27 lines

What it actually says

Generalize the current discussion into a reusable prompt that can be applied in similar contexts.

Think step by step:

  1. Review the conversation to identify the user's primary goal or task pattern
  2. If there is no conversation present, reply to the user that the /save-prompt prompt expects an active discussion to generalize. Keep the reply concise.
  3. Generalize the task into a reusable prompt that could apply to similar scenarios
  4. Extract the core intent, removing conversation-specific details (e.g., specific file names, variable names, or project-specific context)
  5. Craft the generalized multi-line markdown text prompt, using placeholders where appropriate (e.g., "the selected code", "the current file", "the specified functionality")
  6. Write a brief description (1 sentence, max 15 words) explaining the goal of the prompt
  7. If applicable, define an argument-hint that describes the expected inputs for the prompt
  8. Save the resulting prompt in a file${promptFileName}.prompt.md, where ${promptFileName} is the concise action-oriented title in kebab-case format (e.g., explain-code, generate-tests, refactor-functionality)

Here's an example of the expected output format:

---
name: ${The concise title in kebab-case format. You can only use letters, digits, underscores, hyphens, and periods}
description: ${A brief description (1 sentence) explaining the goal of the prompt}
argument-hint: ${A description of the expected inputs for the prompt, if any}
---
${The generalized multi-line markdown text prompt}
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. 4d ago First seen · 27 lines · 15 tokens per session scan A fa4d5b23575a

Subscribe to this mod's changes

save-prompt is a command published in the GitHub repository NikiforovAll/claude-code-rules (141 stars, last pushed 5d ago), licensed Apache-2.0. It adds 15 tokens to every session and 356 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 2026-08-30.