update-prompt

update-prompt is a command for coding agents from stellarshenson/claude-code-plugins. It costs 18 tokens per session (106 once invoked), scanned A, original, MIT.

A command for revising a prompt, system instruction, or agent definition using a researched prompt-writing method. It passes the requested change to a separate prompt-engineering workflow.

In plain words
What is it for?
Use it when improving instructions for an AI agent, refining a system message, or updating a prompt while preserving the full request for the underlying workflow.
Why use it?
It gives prompt changes a defined research-based process instead of relying only on ad hoc wording changes.

Command

Part of the datascience plugin — 20 skills, 15 commands 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/stellarshenson/claude-code-plugins/update-prompt
Clone the repo
git clone --depth 1 https://github.com/stellarshenson/claude-code-plugins

Or install datascience, the plugin that ships this one along with the rest of its 20 skills, 15 commands.

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 update-prompt

README.md
[![agentmods](https://agentmods.dev/badge/commands/stellarshenson/claude-code-plugins/update-prompt.svg)](https://agentmods.dev/commands/stellarshenson/claude-code-plugins/update-prompt)
Your own site
<a href="https://agentmods.dev/commands/stellarshenson/claude-code-plugins/update-prompt"><img src="https://agentmods.dev/badge/commands/stellarshenson/claude-code-plugins/update-prompt.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 106 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 $0.00018 $0.00106
Opus 5 $0.00009 $0.00053
Sonnet 5 $0.00004 $0.00021
Haiku 4.5 $0.00002 $0.00011

Measured 3d ago against content hash d59ed6b9ae0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update-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 3d 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/datascience/commands/update-prompt.md · 12 lines

What it actually says

Update Prompt

Invoke the datascience:update-prompt skill and follow it exactly. It owns the whole procedure; this command only routes into it.

Pass the remainder of this invocation through unchanged as the skill's arguments.

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. 3d ago First seen · 12 lines · 18 tokens per session scan A d59ed6b9ae0a

Subscribe to this mod's changes

update-prompt is a command published in the GitHub repository stellarshenson/claude-code-plugins (3 stars, last pushed 4d ago), licensed MIT. It adds 18 tokens to every session and 106 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 2026-08-31.