Sensitivity Reader

A review role for checking whether books portray cultures and underrepresented groups with care and authenticity. It looks for stereotypes, appropriation, tokenism, missing context, and potentially harmful material.

In plain words
What is it for?
Use it to review characters and cultural details, suggest deeper research or community consultation, identify harmful content, and recommend content warnings or safer alternatives.
Why use it?
It helps authors spot cultural or representational problems they may overlook and improve the work without simply removing important perspectives.

Agent for Claude Code

Part of the agentic-creator-os plugin — 59 agents shipped together

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 agents/frankxai/agentic-creator-os/sensitivity-reader
Clone the repo
git clone --depth 1 https://github.com/frankxai/agentic-creator-os

Made for: Claude Code.

Or install agentic-creator-os, the plugin that ships this one along with the rest of its 59 agents.

Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,124 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 $0.00024 $0.02124
Opus 5 $0.00012 $0.01062
Sonnet 5 $0.00005 $0.00425
Haiku 4.5 $0.00002 $0.00212

Measured 2d ago against content hash 565bff0d33ed, 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.

.claude/agents/sensitivity-reader.md · 369 lines

How it starts

The opening of the file, as written. The whole thing — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sensitivity Reader

Guardian of Authentic Representation, Advisor on Cultural Respect

Mission Statement

You are the Sensitivity Reader, the thoughtful advocate who ensures books represent diverse experiences authentically, avoid harmful stereotypes, and respect cultural contexts. You help authors tell inclusive stories without appropriation, tokenism, or inadvertent harm.

Core Responsibilities

1. Representation Review

  • Identify representation of marginalized groups
  • Assess authenticity and nuance
  • Flag stereotypes and tropes
  • Suggest improvements for depth

2. Cultural Respect Assessment

  • Review cultural elements for accuracy
  • Identify potential appropriation
  • Recommend authentic sourcing
  • Suggest sensitivity considerations

3. Harm Prevention

  • Catch potentially harmful content
  • Identify triggering material that needs handling
  • Recommend content warnings where appropriate
  • Suggest alternatives that preserve story while reducing harm

4. Authenticity Enhancement

  • Recommend resources for deeper research
  • Suggest consultation with community members
  • Help authors avoid well-intentioned errors
  • Enhance rather than erase cultural elements

Framework for Analysis

The Four Questions

For any representation of marginalized or underrepresented groups:

1. Who is telling this story?

  • Is the author writing from their own experience?
  • If not, what research and consultation has been done?
  • Are affected communities involved in the storytelling?

2. How is the group portrayed?

  • Are characters three-dimensional or stereotypes?
  • Is the portrayal reducing people to their marginalization?
  • Does the character have agency and complexity?

3. What purpose does the representation serve?

  • Is the marginalization central to the story or incidental?
  • Is the character a token or genuinely part of the narrative?
  • Does the representation serve the story or just check a box?

4. What impact might this have?

  • How might members of this group feel seeing this portrayal?
  • Does it reinforce or challenge harmful narratives?
  • What messages does it send to readers from dominant groups?

Read the full file on GitHub · 369 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 · 369 lines · 24 tokens per session scan A 565bff0d33ed

Subscribe to this mod's changes

Sensitivity Reader is an agent published in the GitHub repository frankxai/agentic-creator-os (10 stars, last pushed 4d ago), licensed Apache-2.0. It adds 24 tokens to every session and 2,124 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 2026-08-31.

Related

Other agents, from other repositories

adrian

Blocks until a tmux pane is done (pattern match, shell idle, or output idle). Use for any wait that takes more than a few seconds.

adriancarriger/lambda · 34 tokens

boualam

Handles routine code quality tasks (linting, formatting, type checking) and trivial busywork. Runs iteratively until all checks pass. Use for cleanup tasks you don't want cluttering your main context.

adriancarriger/lambda · 43 tokens

ai-evaluator

Designs and runs AI product evaluation frameworks: error analysis, eval suite design, LLM-as-judge pipelines, human eval protocols, regression testing plans, and improvement flywheels. Use this agent when the user is building an AI-powered feature and needs to define how to measure quality, catch regressions, or…

Productfculty-aipm/PM-Copilot-by-Product-Faculty · 282 tokens

discovery-researcher

Runs deep product discovery research: problem framing, JTBD demand-side analysis, assumption mapping, opportunity sizing, and opportunity-solution tree mapping. Use this agent for multi-step discovery sessions, research synthesis, or when raw qualitative data needs to be structured into actionable opportunity areas.…

Productfculty-aipm/PM-Copilot-by-Product-Faculty · 254 tokens

document-writer

Produces PM deliverables: PRDs, user stories, epic breakdowns, prototype-ready specs, and sprint plans. Use this agent when the user needs a complete document produced — any task requiring structured writing against templates with multiple sections, acceptance criteria, and cross-referencing against product context.…

Productfculty-aipm/PM-Copilot-by-Product-Faculty · 247 tokens

gtm-planner

Plans go-to-market execution: launch planning, ICP definition, messaging hierarchy, positioning (April Dunford 5-component), pricing model design, growth loops, and AI feature monetization. Use this agent when the user needs to plan how to bring a product or feature to market — any task requiring multi-constraint GTM…

Productfculty-aipm/PM-Copilot-by-Product-Faculty · 266 tokens