character-tag-auditor

character-tag-auditor is a skill for Claude Code, Codex from storyAura/lora-tagging-skills. It costs 34 tokens per session (3,212 once invoked), scanned A, original, MIT.

A dataset-review tool for character LoRA training, where a LoRA is a small model add-on trained to reproduce a particular character. It checks image tags against a locked trigger and a visual reference without changing the original tags.

In plain words
What is it for?
Use it to mark each tag as keep, delete, replace, or uncertain, classify it, suggest normalized replacements for allowed appearance or clothing tags, and prepare the character prompt.
Why use it?
It helps keep character descriptions consistent across all training images. It also protects tags for actions, poses, scenes, composition, quality, and ordinary objects from accidental changes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to mark each tag as keep, delete, replace, or uncertain, classify it, suggest normalized replacements for allowed appearance or clothing tags, and prepare the character prompt.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/storyaura/lora-tagging-skills/character-tag-auditor
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.

Any agent
npx skills add storyAura/lora-tagging-skills --skill character-tag-auditor
Clone the repo
git clone --depth 1 https://github.com/storyAura/lora-tagging-skills

Made for: Claude Code, Codex.

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 character-tag-auditor

README.md
[![agentmods](https://agentmods.dev/badge/skills/storyaura/lora-tagging-skills/character-tag-auditor/github.svg)](https://agentmods.dev/skills/storyaura/lora-tagging-skills/character-tag-auditor)
Your own site
<a href="https://agentmods.dev/skills/storyaura/lora-tagging-skills/character-tag-auditor"><img src="https://agentmods.dev/badge/skills/storyaura/lora-tagging-skills/character-tag-auditor/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for character-tag-auditor

Your own site · 80×15
<a href="https://agentmods.dev/skills/storyaura/lora-tagging-skills/character-tag-auditor"><img src="https://agentmods.dev/badge/skills/storyaura/lora-tagging-skills/character-tag-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,212 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 $0.00034 $0.03212
Opus 5 $0.00017 $0.01606
Sonnet 5 $0.00007 $0.00642
Haiku 4.5 $0.00003 $0.00321

Measured 11d ago against content hash e63428dd92b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

character-tag-auditor 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 11d 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.

character-tag-auditor/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Character LoRA Tag Auditor

Return every supplied original tag exactly once with one decision: keep, delete, replace, or uncertain. Never alter the original tag field. Put a normalized target only in replacement_tag. The locked trigger is always keep, is included in the final prompt, and has prompt order 0.

Categories and hard boundary

Use exactly one category: identity, hair, eyes, face, body, clothing, footwear, legwear, wearable_accessory, action, pose, expression, scene, composition, quality, object, or other.

Only hair, eyes, face, body appearance, clothing, footwear, legwear, and wearable accessories may be deleted or replaced. Identity/trigger tags, actions, poses, expressions, scenes/backgrounds, composition/camera terms, quality/style terms, ordinary objects, and other categories are protected: always keep them in dataset files and never replace them. Protected does not mean “include in the character prompt”; these tags normally use include_in_prompt: false.

Decision meanings

  • keep: the original tag is correct and already useful.
  • delete: the original appearance/wearable tag is incorrect, conflicting, redundant, or non-core under the selected style.
  • replace: the feature is correct, but the supplied tag is imprecise or redundantly split; provide one visually confirmed canonical target.
  • uncertain: visual evidence is insufficient. This is safety-preserving and must not modify files.

A replacement target must be one tag: nonempty, different from its source, and without commas, line breaks, or control characters. Never produce a replacement chain or cycle. Several sources may map to one canonical target; the caller keeps its earliest original position.

If a replacement target equals the source because the original tag is already canonical, return keep with an empty replacement_tag. Never use replace merely to confirm or deduplicate an unchanged tag.

Sparse mode (default)

Keep only the current character's core identity: subject identity/count, stable eye and hair traits, signature garments, footwear, and wearable accessories. Delete incorrect/conflicting tags and non-core appearance or wearable detail.

Read the full file on GitHub · 122 lines

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. 11d ago First seen · 122 lines · 34 tokens per session scan A e63428dd92b6

Subscribe to this mod's changes

character-tag-auditor is a skill published in the GitHub repository storyAura/lora-tagging-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 3,212 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.

Related

Other skills, from other repositories

baoyu-danger-gemini-web

Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input, and multi-turn conversations. Use when other skills need image generation backend, or when user requests "generate image with Gemini", "Gemini text generation"…

JimLiu/baoyu-skills · 74 tokens

shortfilm-prompt

Generate cinematic AI shortfilm prompts (works with Seedance 2.0, Xiaoyunque, Sora, Kling, Jimeng, Veo) using the 5-stage structure from Mx-Shell's Zombie Scavenger. Trigger when the user wants transformation sequences, multi-shot narrative shorts, weapon-charge/combat segments, emotional family/pet/farewell…

jnMetaCode/ai-shortfilm-prompts · 100 tokens

video-frame-extractor

A video-frame extraction and analysis helper that selects key frames, describes their contents with a vision model, and creates structured prompts for further creation.

anbeime/skill · 78 tokens

civitai-mcp-ultimate

Ultimate MCP server for Civitai — search models, browse top images with prompts, download LoRAs/Checkpoints, analyze trends. Use when user asks about AI models, LoRAs, checkpoints, Stable Diffusion, Flux, image generation prompts, or Civitai.

timoncool/civitai-mcp-ultimate · 65 tokens

kling-prompter

A prompt-writing guide for Kling 3.0, a video-generation model. It covers short videos, story-driven videos with dialogue or sound, and animating an existing reference image.

cclank/lanshu-awesome-ai-video-kit · 162 tokens

happyhorse-prompter

A tool for writing short prompts for HappyHorse 1.0, an AI video generator that can create video with sound. Its prompts put the main subject first, specify the camera, and describe audible sound when needed.

cclank/lanshu-awesome-ai-video-kit · 116 tokens