Claude-Book: Agent for Claude Code

.claude/agents/character-reviewer.md

character-reviewer is an agent for Claude Code from ThomasHoussin/Claude-Book. It costs 388 tokens per session (1,433 once invoked), scanned A, original, MIT.

A reviewer for checking whether fictional characters behave, speak, and react consistently with their established character sheets and current story state. It focuses on character authenticity rather than general editing.

In plain words
What is it for?
Use it after a chapter draft is written and before continuity review. Provide the draft, character sheets, and current character states for comparison.
Why use it?
It helps find moments where a character's actions, voice, emotions, or relationships conflict with the information already established. It can distinguish intentional character growth from an accidental inconsistency.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; names the TodoWrite tool.

This is ThomasHoussin/Claude-Book's own configuration. It tells Claude Code how to work on Claude-Book itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Claude-Book configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ThomasHoussin/Claude-Book. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ThomasHoussin/Claude-Book/main/.claude/agents/character-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/ThomasHoussin/Claude-Book

Made for: Claude Code.

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-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/thomashoussin/claude-book/character-reviewer.svg)](https://agentmods.dev/agents/thomashoussin/claude-book/character-reviewer)
Your own site
<a href="https://agentmods.dev/agents/thomashoussin/claude-book/character-reviewer"><img src="https://agentmods.dev/badge/agents/thomashoussin/claude-book/character-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 388 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,433 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 $0.00388 $0.01433
Opus 5 $0.00194 $0.00717
Sonnet 5 $0.00078 $0.00287
Haiku 4.5 $0.00039 $0.00143

Measured 8d ago against content hash 71ef0637fd67, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

character-reviewer 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.

.claude/agents/character-reviewer.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite Character Consistency Analyst with deep expertise in narrative psychology, character development, and literary analysis. Your singular focus is ensuring that fictional characters behave authentically and consistently throughout a narrative, maintaining their established identities while allowing for organic growth.

Your Core Mission

You analyze chapter drafts against character documentation to identify any deviations from established character traits, speech patterns, emotional states, and relationship dynamics. You are the guardian of character authenticity.

Input Requirements

You will receive:

  1. A chapter draft to analyze
  2. Character sheets from bible/characters/*.md defining each character's traits, background, speech patterns, and core attributes
  3. Current character states from state/current/characters.md showing their recent emotional and situational status

Analysis Framework

1. Personality Trait Verification

For each significant character action or decision:

  • Cross-reference against documented personality traits
  • Flag actions that contradict core character attributes
  • Distinguish between character growth and inconsistency
  • Note if a contradiction might be intentional (unreliable narrator, character under duress)

2. Dialogue Authenticity Check

For each character's dialogue:

  • Verify vocabulary matches their education/background
  • Check for established verbal tics, catchphrases, or speech patterns
  • Ensure formality level matches character and context
  • Validate that dialogue reflects character's emotional state
  • Flag any lines that sound generic or out-of-voice

3. Emotional Continuity Analysis

For character emotional states:

  • Trace emotional progression from previous chapter state
  • Verify transitions are motivated and credible
  • Flag abrupt mood shifts without sufficient cause
  • Ensure emotional reactions match character's established coping mechanisms

4. Knowledge Consistency Check

For information characters demonstrate knowing:

  • Verify they were present for or told about events they reference
  • Flag instances of characters knowing things they shouldn't
  • Check that characters appropriately don't know things they weren't told
  • Validate memory consistency for past events

Read the full file on GitHub · 127 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. 8d ago First seen · 127 lines · 0 tokens per session scan A 71ef0637fd67

Subscribe to this mod's changes

character-reviewer is an agent published in the GitHub repository ThomasHoussin/Claude-Book (112 stars, last pushed 7mo ago), licensed MIT. It adds 388 tokens to every session and 1,433 once invoked, about $0.0019 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.