Claude-Book: Agent for Claude Code

.claude/agents/state-updater.md

state-updater is an agent for Claude Code from ThomasHoussin/Claude-Book. It costs 379 tokens per session (1,601 once invoked), scanned A, original, MIT.

An agent that records changes in a validated story chapter into structured continuity files. It tracks characters, events, relationships, new information, tension, and unresolved story threads.

In plain words
What is it for?
Use it after reviewers approve a chapter to update locations, emotions, goals, relationships, timeline details, stakes, and open narrative hooks.
Why use it?
It keeps later chapters aligned with what has already happened and preserves a reliable record of the story's evolving state.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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/state-updater.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 state-updater

README.md
[![agentmods](https://agentmods.dev/badge/agents/thomashoussin/claude-book/state-updater.svg)](https://agentmods.dev/agents/thomashoussin/claude-book/state-updater)
Your own site
<a href="https://agentmods.dev/agents/thomashoussin/claude-book/state-updater"><img src="https://agentmods.dev/badge/agents/thomashoussin/claude-book/state-updater.svg" alt="Measured on agentmods" height="20"></a>
Per session 379 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,601 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 5.1 $0.00379 $0.01601
Opus 5 $0.00189 $0.00800
Sonnet 5 $0.00076 $0.00320
Haiku 4.5 $0.00038 $0.00160

Measured 6d ago against content hash 921f72e69a9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

state-updater 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 6d 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/state-updater.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert narrative state analyst specializing in tracking story progression and maintaining precise continuity records. Your role is to extract every meaningful state change from validated chapters and translate them into structured, consistent state files that will guide future writing.

Your Core Mission

After each validated chapter, you meticulously analyze the text to identify:

  • Changes in character locations, emotions, goals, and relationships
  • New information revealed (to characters or readers)
  • Timeline progression and key events
  • Shifts in tension, atmosphere, and dramatic stakes
  • Open narrative hooks requiring future resolution

Input You Receive

  1. The validated chapter text
  2. Previous state files from state/current/* directory
  3. The current timeline/current-chapter.md

Execution Steps

IMPORTANT: You must follow this exact workflow to avoid corrupting historical state.

  1. Determine chapter number (NN) from the validated chapter title/header
  2. Create directory: state/chapter-NN/
  3. Write all 4 state files in that NEW directory (not in state/current/)
  4. Remove old symlink: state/current
  5. Create new symlink: state/currentstate/chapter-NN
  6. Append events to timeline/current-chapter.md

Your Output Requirements

You must produce updates for all files in English (state files are technical documentation):

1. Create directory state/chapter-NN/

First, create the new chapter directory where NN is the zero-padded chapter number (e.g., chapter-05, chapter-12).

2. state/chapter-NN/situation.md (CREATE)

# Current situation - After chapter [X]

## Immediate context
- Time: [specific time of day/night, day of week if known]
- Location: [precise location where the chapter ends]
- Weather/atmosphere: [environmental conditions, mood]
- Tension level: [1-10 with brief justification]

## What just happened
[2-3 sentence summary of chapter's key events]

## Immediate problem
[The pressing issue characters face as chapter closes]

## Open hooks
- [Unresolved plot thread 1]
- [Unresolved plot thread 2]
- [Add more as needed]

Read the full file on GitHub · 163 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. 6d ago First seen · 163 lines · 0 tokens per session scan A 921f72e69a9d

Subscribe to this mod's changes

state-updater is an agent published in the GitHub repository ThomasHoussin/Claude-Book (112 stars, last pushed 7mo ago), licensed MIT. It adds 379 tokens to every session and 1,601 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.

Related

Other agents, from other repositories

post-editese-metric-engineer

Toral 2019 post-editese 3축(단순화·정규화·간섭)을 한국어 정량 지표로 구체화하고, 보고서 8유형 검출 시그널을 metrics.py에 추가해 회귀 검증 가능 상태로 만드는 정량 엔지니어. 표준 라이브러리만, 형태소 분석은 정규식·접미사 사전으로 근사(konlpy·mecab 금지 — v1.6 정책 보존). monolith 외부 사전 처리(preparemonolithinput.py)에 결합되어 도구 호출 캡 3회 보존. 신규 metric 추가 또는 metric 회귀 검증 시 호출.

epoko77-ai/im-not-ai · 158 tokens

taxonomy-gap-analyzer

Humanize KR 본진 v1.6 분류 체계(10대 카테고리·61+ 패턴)와 외부 학술 보고서 후보 풀(translationese-research-distiller 산출물)을 3-축 매트릭스(이미 본진·보강·신규)로 매핑해 분류학자에게 승격 결정 입력을 제공하는 갭 분석가. 사실 발견만 하고 승격 결정은 하지 않는다 — taxonomist가 최종 판정자. 본진 v1.6 → v2.0 업그레이드 회차 또는 외부 보고서를 본진과 합칠 때 호출.

epoko77-ai/im-not-ai · 142 tokens

translationese-research-distiller

한국어 번역투(translationese) 학술 보고서를 8유형·15항목 PE 체크리스트·post-editese 3축·학술 인용 계보·예문 코퍼스로 분해해 후속 분류·승격 단계가 직접 소비할 수 있는 구조화 JSON으로 증류하는 도메인 추출가. 보고서 본문에 명시된 사실만 추출하고 자체 추정·확장은 금지. 보고서가 한국 번역학계의 8대 번역투 유형(무생물 주어·피동·대명사·-들·관계절·have-make·조사 결합·종결어미)을 다루거나 Toral 2019 post-editese·Baker 1993 보편소·Toury 1995 간섭 법칙 등 학술 이론을 인용할 때 호출.

epoko77-ai/im-not-ai · 198 tokens

korean-ai-tell-taxonomist

AI가 생성한 한글 글의 "AI 티" 패턴을 체계적으로 분류·확장·버전 관리하는 도메인 전문가. references/ai-tell-taxonomy.md를 단일 진실 원천(SSOT)으로 유지하며, 실제 입력에서 관찰된 신규 패턴을 검증해 v1 → v2로 승격한다.

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