style-guardian

style-guardian is an agent for Claude Code from Mineru98/imagine. It costs 96 tokens per session (836 once invoked), scanned A, original, MIT.

A style-memory helper for image generation. It saves visual details such as colors, art style, lighting, composition, texture, and mood, then reuses them when you ask for a series or a similar image.

In plain words
What is it for?
Use it when creating related images that should look like part of the same series, such as variations of a design or illustration.
Why use it?
It avoids manually describing the same visual style for every image. It stays inactive unless your request clearly asks to continue or match an earlier style.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the imagine plugin — 8 skills, 10 agents shipped together

Good fit Use it when creating related images that should look like part of the same series, such as variations of a design or illustration.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/mineru98/imagine/style-guardian
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.

Clone the repo
git clone --depth 1 https://github.com/Mineru98/imagine

Made for: Claude Code.

Or install imagine, the plugin that ships this one along with the rest of its 8 skills, 10 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 style-guardian

README.md
[![agentmods](https://agentmods.dev/badge/agents/mineru98/imagine/style-guardian.svg)](https://agentmods.dev/agents/mineru98/imagine/style-guardian)
Your own site
<a href="https://agentmods.dev/agents/mineru98/imagine/style-guardian"><img src="https://agentmods.dev/badge/agents/mineru98/imagine/style-guardian.svg" alt="Measured on agentmods" height="20"></a>
Per session 96 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 836 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00096 $0.00836
Opus 5 $0.00048 $0.00418
Sonnet 5 $0.00019 $0.00167
Haiku 4.5 $0.00010 $0.00084

Measured 8d ago against content hash de854b75c48b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

style-guardian 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 8d 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.

agents/style-guardian.md · 51 lines

What it actually says

style-guardian

이전 이미지 생성 실행의 시각적 지문(palette, art_style, corner_radius_estimate, lighting, composition, texture, mood)을 manifest에 보관해 두었다가, 사용자가 "이어서"를 요청할 때 같은 스타일을 재주입한다. 새 이미지를 새롭게 만들지 않고, 직전 이미지와 시각적으로 연속된 결과를 만드는 것이 목적이다.

언제 개입하는가

아래 트리거 중 하나 이상이 감지된 경우에만 개입한다.

  • CLI: --keep 플래그가 인자에 포함됨.
  • 자연어 (한국어): "방금 거랑 비슷하게", "저번 거랑 같은 스타일", "같은 톤으로", "시리즈로", "이어서".
  • 자연어 (영어): "same style as before", "keep the style", "as a series", "match the last one".

트리거가 없는 단일 요청에는 절대 개입하지 않는다.

역할

  1. scripts/lib/style-guardian.jsloadStyle(manifestPath)로 가장 최근 manifest에서 스타일 토큰을 읽는다.
  2. buildStylePrefix(tokens)를 호출해 프롬프트 prefix 문자열을 얻는다.
  3. 사용자 프롬프트 에 prefix를 붙여 imagine 스킬에 전달한다. 사용자 원문은 수정·치환하지 않는다.
  4. 새 생성 결과의 스타일 토큰이 산출되면 saveStyle(manifestPath, tokens)로 다음 실행을 위해 다시 저장한다.

사용자에게 보이는 출력

개입할 때 반드시 다음 한 줄을 먼저 보고한 뒤 생성을 시작한다. 토큰 값은 manifest에서 꺼낸 실제 값으로 채운다:

이전 [<art_style 값>] 화풍과 [<palette 강조색>] 강조색을 유지하여 생성합니다.
  • art_style이 비어 있으면 해당 괄호는 생략한다 (빈 괄호로 두지 않는다).
  • palette가 배열이면 첫 번째 값만 "강조색"으로 보고한다.
  • 추가로 보존된 토큰(lighting, composition 등)은 필요 시 같은 줄 뒤에 덧붙일 수 있다.

예:

이전 [반실사 수채화] 화풍과 [청록색] 강조색을 유지하여 생성합니다.

금기

  • 스타일 임의 변경 금지. 저장된 토큰을 해석·재작성·"더 좋게" 수정하지 않는다. manifest에 있는 값만 그대로 사용한다.
  • 사용자 지시 없는 개입 금지. --keep·시리즈 모드 트리거가 감지되지 않으면 완전히 패스스루. 자동 추론으로 개입하지 않는다.
  • 사용자 프롬프트 치환 금지. prefix는 앞에 덧붙이기만 한다. 사용자 원문 단어는 건드리지 않는다.
  • 토큰 누출 금지. prefix에 manifest 경로, 타임스탬프, 내부 식별자 등 사용자 맥락 밖의 메타데이터를 포함하지 않는다.
  • 재귀 보정 금지. prompt-director 보정 결과에 다시 style prefix를 거는 2차 rewrite 흐름이더라도, prefix 주입은 단 한 번만 수행한다.
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. 8d ago First seen · 51 lines · 96 tokens per session scan A de854b75c48b

Subscribe to this mod's changes

style-guardian is an agent published in the GitHub repository Mineru98/imagine (5 stars, last pushed 9d ago), licensed MIT. It adds 96 tokens to every session and 836 once invoked, about $0.0005 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.

Related

Other agents, from other repositories

entity-tracker

Canonical state keeper for the book pipeline. Maintains ENTITYSTATE.yaml — the single source of truth for every character, location, object, timeline event, plot thread, and world rule, plus what each character knows and when they learned it. Builds the state from the outline, then updates it incrementally as chapters…

felipelobomotta-blip/book-genesis-v4 · 81 tokens

continuity-recorder

A continuity-recording agent that maintains the project’s long-term story memory. It tracks characters, unanswered clues, plot decisions, episode states, and possible setting conflicts.

Supreme-Ultimate/novel-to-script-team · 23 tokens

gamemaker-assets-specialist

The GameMaker Assets Specialist owns all GMS2 asset pipeline management: texture groups, texture pages, audio groups, sprite packing strategy, asset import settings, VRAM budgets, and content loading optimization. They ensure fast load times and controlled memory usage across all target platforms.

TraftG/opencode-game-studio · 54 tokens

pixel-art-animation-reviewer

Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…

AnastasiyaW/codex-claude-code-config · 140 tokens

cover-artist

Generate book cover art prompts from story content. Produces optimized prompts for image generation models (GPT Image, Gemini, FLUX, etc.) that conform to Kindle dimensions.

howells/fiction · 38 tokens

context-finder

Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the knowledge graph, code index, and prior session memory…

futuregerald/futuregerald-claude-plugin · 111 tokens