sensitivity-reader

An AI-assisted first review of a publication for representation, cultural accuracy, stereotypes, terminology, and issues that may concern readers. It is not a substitute for readers with relevant lived experience.

In plain words
What is it for?
Use it to review characters, language, and cultural portrayals for possible stereotyping, shallow representation, harmful patterns, or inaccurate terminology.
Why use it?
It can flag obvious concerns before publication and help identify questions for human reviewers.

Skill for Claude CodeCodex

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 skills/ckokoski/authoragent/sensitivity-reader
Any agent
npx skills add Ckokoski/AuthorAgent --skill sensitivity-reader
Clone the repo
git clone --depth 1 https://github.com/Ckokoski/AuthorAgent

Made for: Claude Code, Codex.

Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,385 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 $0.01385
Opus 5 $0.00009 $0.00692
Sonnet 5 $0.00004 $0.00277
Haiku 4.5 $0.00002 $0.00138

Measured 2d ago against content hash 1ef1beb8deab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sensitivity-reader 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.

skills/_archived/premium/sensitivity-reader/SKILL.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sensitivity Reader — Premium Skill

AI-assisted sensitivity review that flags potential representation issues, cultural inaccuracies, stereotypes, and reader-concern areas before publication. Not a replacement for human sensitivity readers — but a powerful first pass that catches the obvious issues and helps you ask the right questions.

Important Disclaimer

This tool is an AI assistant, not a cultural authority. It can identify patterns and flag potential concerns, but it cannot fully replicate the lived experience of a human sensitivity reader. For published works, we strongly recommend also working with human readers from relevant communities.

What It Catches

Representation Patterns

  • Stereotyping — Characters reduced to cultural/racial/gender tropes
  • Token representation — Single diverse character without depth
  • White savior patterns — Majority-group character "saving" minority characters
  • Magical minority — Diverse characters existing only to help the protagonist
  • Disability as metaphor — Using disability symbolically rather than realistically
  • Bury your gays — LGBTQ+ characters disproportionately killed or punished

Language & Terminology

  • Outdated or offensive terminology (with current alternatives)
  • Microaggressions in dialogue (flagged with context — sometimes intentional for character)
  • Slurs and reclaimed language (flagged with usage guidance)
  • Gendered language patterns
  • Ableist language in narration vs. dialogue

Cultural Accuracy

  • Religious practices and terminology
  • Cultural customs and traditions
  • Food, clothing, and daily life details
  • Historical accuracy for period pieces
  • Language and dialect representation
  • Name accuracy for cultural background

Power Dynamics

  • Workplace/authority dynamics
  • Age-gap relationships (flagged, not judged)
  • Consent in romantic/intimate scenes
  • Economic disparity portrayal
  • Institutional power representation

Report Format

Sensitivity Review: "The Silent Hour"
Chapters Reviewed: 1-25 (Full Manuscript)
Review Date: 2026-02-24

══════════════════════════════════════
SUMMARY
══════════════════════════════════════
Flags Found:     14
  High Priority:  2
  Medium:         7
  Low/Note:       5

Overall Assessment: Generally thoughtful representation with
a few areas that would benefit from a second look.

══════════════════════════════════════
HIGH PRIORITY
══════════════════════════════════════

[FLAG H-1] Chapter 8, Page 112
Category: Cultural Accuracy
"She performed the ceremony exactly as her grandmother taught
her, burning sage in a clay bowl."

Issue: Sage burning (smudging) is a sacred practice in specific
Indigenous cultures. The character (Maria, Mexican-American) may
not practice smudging — this may conflate distinct cultural
traditions.

Suggestion: Research whether this aligns with the character's
specific cultural background. Consider consulting with someone
from the relevant tradition. If the character uses copal or
another culturally specific incense, that may be more accurate.

Author Decision: [ ] Keep as-is  [ ] Revise  [ ] Research more

──────────────────────────────────────

[FLAG H-2] Chapter 14, Page 201
Category: Representation Pattern
"James, the only Black character, dies protecting Elena in
the warehouse scene."

Issue: This follows the "sacrificial minority" trope where a
character of color dies to advance the white protagonist's
story arc.

Suggestion: Consider whether James's death serves HIS arc or
only Elena's. Could he survive? If the death is essential,
ensure James has his own complete character arc and motivations
beyond helping Elena.

Author Decision: [ ] Keep as-is  [ ] Revise  [ ] Research more

══════════════════════════════════════
MEDIUM FLAGS
══════════════════════════════════════

[FLAG M-1] through [FLAG M-7] ...
(Each with: location, category, quoted text, issue, suggestion)

══════════════════════════════════════
LOW / NOTES
══════════════════════════════════════

[NOTE L-1] through [NOTE L-5] ...
(Informational flags — not problems, just areas to be aware of)

Read the full file on GitHub · 183 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. 2d ago First seen · 183 lines · 18 tokens per session scan A 1ef1beb8deab

Subscribe to this mod's changes

sensitivity-reader is a skill published in the GitHub repository Ckokoski/AuthorAgent (102 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 1,385 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 2026-08-30.

Related

Other skills, from other repositories

search

Search 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.

taishi-i/awesome-ChatGPT-repositories · 57 tokens

app-search

主流APP搜索。当用户想要在拼多多、美团、高德地图、抖音、快手、小红书、哔哩哔哩、知乎、百度、OPPO音乐、OPPO软件商店等APP中搜索时激活。覆盖电商购物、生活服务、短视频内容、知识搜索、音乐搜索、应用商店搜索等场景。.

OPPO-Mente-Lab/X-OmniClaw · 87 tokens

clipboard-to-shortcut

将剪切板中的 App 跳转链接制作成一个可复用的快捷指令 Skill,下次用户说出 Skill 名称即可一键直达对应 App 页面。 当用户说"把剪切板的链接做成skill"、"帮我保存这个链接为快捷方式"、"用剪切板内容创建一个skill XX"、"把这个链接制作成skill"、"帮我把复制的链接做成一键跳转"等意图时激活。 支持淘宝、拼多多、抖音、快手、知乎、小红书、美团、哔哩哔哩、高德、QQ音乐、支付宝、百度等主流 App 的分享链接。.

OPPO-Mente-Lab/X-OmniClaw · 157 tokens

capcut-theme-video

CapCut (剪映) one-tap video creation on Android. Always clear Alatest first (copyimagestoalbum clear-only), then retrieve by time (listgalleryimages) or content (image-memories). Copy to Alatest (clearalbumfirst), CapCut 照片视频 → Alatest → 全部, multitap, N=K.

OPPO-Mente-Lab/X-OmniClaw · 80 tokens

taobao-search

淘宝商品搜索。当用户想要搜索商品、找某品牌产品、比价、查看新款等电商购物场景时激活。.

OPPO-Mente-Lab/X-OmniClaw · 35 tokens

scheduled-automation

Schedule app automation tasks such as opening an app and performing actions at a specific time.

OPPO-Mente-Lab/X-OmniClaw · 21 tokens