improve-prompt

improve-prompt is a command for coding agents from AcKeskin/contexture. It costs 39 tokens per session (253 once invoked), scanned A, original, MIT.

A command that improves prompts for language models and for tools that generate images, video, or audio. It asks questions when important details are missing, then returns a rewritten prompt and a brief explanation.

In plain words
What is it for?
Use it to refine prompts for coding agents, chat models, and generative media tools, with optional notes for specific models.
Why use it?
It helps turn vague requests into clearer instructions without tying them to one model provider.

Command

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/ackeskin/contexture/improve-prompt
Clone the repo
git clone --depth 1 https://github.com/AcKeskin/contexture

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 improve-prompt

README.md
[![agentmods](https://agentmods.dev/badge/commands/ackeskin/contexture/improve-prompt.svg)](https://agentmods.dev/commands/ackeskin/contexture/improve-prompt)
Your own site
<a href="https://agentmods.dev/commands/ackeskin/contexture/improve-prompt"><img src="https://agentmods.dev/badge/commands/ackeskin/contexture/improve-prompt.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 253 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 $0.00039 $0.00253
Opus 5 $0.00019 $0.00127
Sonnet 5 $0.00008 $0.00051
Haiku 4.5 $0.00004 $0.00025

Measured 4d ago against content hash 63b3dd466701, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

improve-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.

commands/improve-prompt.md · 16 lines

What it actually says

Run the improve-prompt skill for the current context.

Any text after /improve-prompt is treated as the prompt to improve. Examples:

  • /improve-prompt — improve the prompt in the recent conversation / current selection; ask what to improve if ambiguous.
  • /improve-prompt write about our new feature — sharpen that text prompt.
  • /improve-prompt a nice picture of a city — treat as a generative-image prompt and improve it for any image model.

The skill classifies the prompt family (text/LLM vs generative media), diagnoses what's missing against the relevant dimensions, interviews the user only when a gap would materially change the output, then returns an improved prompt plus a short rationale (what changed, assumptions, optional per-model notes). Model-agnostic — vendor-specific syntax stays in the optional notes. Mode A only — never auto-fires.

See ~/.claude/skills/improve-prompt/SKILL.md for the full procedure.

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 · 16 lines · 39 tokens per session scan A 63b3dd466701

Subscribe to this mod's changes

improve-prompt is a command published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 253 once invoked, about $0.0002 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.