agentmods.dev

prompt-optimizer

A prompt-editing plugin that clarifies and improves instructions written for several AI models, including GPT-5.6, Claude, Gemini, Kimi, GLM, and DeepSeek-V4.

In plain words
What is it for?
Use it to refine prompts before sending them to the listed AI models. The input does not describe its exact editing workflow.
Why use it?
It helps when an instruction is vague, poorly structured, or not well suited to the model receiving it.

Plugin for Claude Code

6 22d ago A scan tokens not measured original MIT
View the source file IchenDEV/prompt-optimizer-plugins
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.

Claude Code
/plugin marketplace add IchenDEV/prompt-optimizer-plugins
agentmods
npx agentmods add plugins/ichendev/prompt-optimizer-plugins/prompt-optimizer
Clone the repo
git clone --depth 1 https://github.com/IchenDEV/prompt-optimizer-plugins

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

prompt-optimizer 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.

plugins/prompt-optimizer/.claude-plugin/plugin.json · 25 lines

What it actually says

{
  "name": "prompt-optimizer",
  "displayName": "Prompt Optimizer",
  "version": "3.1.0",
  "description": "Clarify and optimize prompts for GPT-5.6, Claude, Gemini, Kimi, GLM, and DeepSeek-V4.",
  "author": {
    "name": "IchenDEV",
    "url": "https://github.com/IchenDEV"
  },
  "homepage": "https://github.com/IchenDEV/prompt-optimizer-plugins",
  "repository": "https://github.com/IchenDEV/prompt-optimizer-plugins",
  "license": "MIT",
  "keywords": [
    "prompt-optimization",
    "prompt-engineering",
    "gpt-5.6",
    "claude",
    "gemini",
    "kimi",
    "glm",
    "deepseek-v4"
  ],
  "skills": "./skills/"
}
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 · 25 lines scan A d222514203b4

Subscribe to this mod's changes

prompt-optimizer is a plugin published in the GitHub repository IchenDEV/prompt-optimizer-plugins (6 stars, last pushed 22d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Data and AIProductivityagent-skillsclaude-code-plugincodex-plugingpt-5-6openaiprompt-engineering
Related

Other plugins, from other repositories

dumb-boss

The anti-sycophant agent skill. An agent that pushes back on a bad instruction instead of complying, without turning into a contrarian.

kg1128/dumb-boss · not measured

prompt-improver

Turn vague agent prompts into precise, verifiable XML specs — then execute or plan. Headless multi-CLI generator. Use when the user says improve prompt, plan carefully, or structure a vague coding request.

owenob1/prompt-improver · not measured

llamaparse-mcp

Unlock document processing and Index v2 retrieval workflows with the LlamaParse Platform MCP.

run-llama/llamaparse-agent-plugins · not measured

claude-md-management-hames

Hames-aware fork of claude-md-management. Audits and revises CLAUDE.md files while honoring the v5.5 kernel + .cursor/rules/ module separation, workspace boundaries, defense-line signatures, and isolated domains.

baek-labs/hames · not measured

motherduck-skills

MotherDuck skills for agents and developers: use the CLI and Guides, explore schemas, write DuckDB SQL, build Dives and Flights, and ship analytics apps and pipelines.

motherduckdb/agent-skills · not measured

claude-prompt

A slash command that rewrites your request into an optimized prompt, then carries it out.

danielkremen818/claude-prompt · not measured