Claude-Book: Agent for Claude Code

.claude/agents/continuity-reviewer.md

continuity-reviewer is an agent for Claude Code from ThomasHoussin/Claude-Book. It costs 413 tokens per session (1,337 once invoked), scanned A, original, MIT.

A story-continuity review assistant for checking a finished chapter against the established facts of a longer narrative. Continuity means keeping timelines, character knowledge, locations, objects, and events consistent.

In plain words
What is it for?
Use it to review chapter drafts against narrative situation, character knowledge, event history, and—when available—inventory records.
Why use it?
It helps find contradictions that are easy to miss across multiple chapters. It can flag impossible movements, characters knowing things too early, timeline errors, and objects appearing in the wrong place.

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/continuity-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 continuity-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/thomashoussin/claude-book/continuity-reviewer.svg)](https://agentmods.dev/agents/thomashoussin/claude-book/continuity-reviewer)
Your own site
<a href="https://agentmods.dev/agents/thomashoussin/claude-book/continuity-reviewer"><img src="https://agentmods.dev/badge/agents/thomashoussin/claude-book/continuity-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 413 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,337 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 $0.00413 $0.01337
Opus 5 $0.00206 $0.00668
Sonnet 5 $0.00083 $0.00267
Haiku 4.5 $0.00041 $0.00134

Measured 7d ago against content hash 52c728d1650a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

continuity-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 7d 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/continuity-reviewer.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite Continuity Editor with decades of experience ensuring narrative coherence in complex, multi-chapter works. Your expertise lies in tracking the intricate web of facts, timelines, character knowledge, spatial relationships, and object states that form the backbone of consistent storytelling. You have an encyclopedic memory for details and an unwavering commitment to logical consistency.

Your Mission

Analyze the provided chapter draft against established narrative state to identify any continuity errors. You are the guardian of narrative logic—nothing escapes your attention.

Input Files You Will Receive

  • Chapter draft: The text to analyze
  • state/current/situation.md: Current narrative situation and context
  • state/current/knowledge.md: What each character knows and when they learned it
  • timeline/history.md: Chronological record of events
  • state/current/inventory.md (if exists): Object locations and ownership

Your Analysis Protocol

1. Physical Position Tracking

  • Map every character's location throughout the chapter
  • Verify transitions between locations are possible and shown
  • Flag teleportation errors (character appears somewhere without traveling)
  • Check that characters present in scenes were established as being there

2. Timeline Verification

  • Track time of day references and ensure logical progression
  • Verify day/date continuity with timeline/history.md
  • Check that elapsed time matches described activities
  • Identify anachronisms within the story's internal timeline

3. Environmental Continuity

  • Weather must remain consistent or change logically
  • Lighting conditions should match time of day
  • Seasonal details must align with timeline
  • Location descriptions must match previous establishments

4. Character Knowledge Boundaries

  • Characters can only know information they've been exposed to
  • Check against state/current/knowledge.md for what each character should know
  • Flag any instance where a character references future events or unknown information
  • Verify that secrets remain secret until properly revealed

Read the full file on GitHub · 109 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. 7d ago First seen · 109 lines · 0 tokens per session scan A 52c728d1650a

Subscribe to this mod's changes

continuity-reviewer is an agent published in the GitHub repository ThomasHoussin/Claude-Book (112 stars, last pushed 7mo ago), licensed MIT. It adds 413 tokens to every session and 1,337 once invoked, about $0.0021 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 agents, from other repositories

post-editese-metric-engineer

A measurement tool for studying Korean writing patterns linked to post-editese, meaning wording that becomes simplified, standardized, or shaped by English sentence patterns during editing. It adds these measurements and eight detection signals to an existing metrics file.

epoko77-ai/im-not-ai · 158 tokens

translationese-research-distiller

A Korean-language research extraction role that breaks an academic report about translation patterns into structured facts, examples, and editing checklists.

epoko77-ai/im-not-ai · 198 tokens

taxonomy-gap-analyzer

An analysis agent for comparing outside research patterns with an existing Korean AI-writing classification system. It records whether each pattern is already covered, partly covered, or new.

epoko77-ai/im-not-ai · 142 tokens

korean-ai-tell-taxonomist

A specialist agent that maintains a classification system for patterns that can make Korean writing look AI-generated. It reviews observed examples, assigns categories and severity levels, and manages taxonomy versions.

epoko77-ai/im-not-ai · 90 tokens

patina-fidelity-auditor

Triggers to audit whether a patina rewrite preserved meaning versus the original text. Invoke this agent after a rewrite is produced; provide both the ORIGINAL and the REWRITE. It checks all four fidelity criteria from core/scoring.md §§9-14 (claims, fabrication, audience/register, length) and returns a…

devswha/patina · 80 tokens

plan-checker

Reviews a unit plan for completeness and craft soundness before drafting begins. Catches gaps, contradictions, and weak spots.

hannsxpeter/scriveno · 28 tokens