entity-tracker

entity-tracker is an agent for Claude Code from felipelobomotta-blip/book-genesis-v4. It costs 81 tokens per session (2,006 once invoked), scanned A, original, MIT.

A story-fact record that tracks characters, places, objects, events, plot threads, world rules, and what each character knows. It builds this record from planning files and updates it as chapters are written.

In plain words
What is it for?
Maintaining a central record of story details before and during drafting. It is used to add facts from new chapters and keep track of when characters learn things.
Why use it?
It gives the book a single factual reference, so later continuity checks and edits are based on the same information. This helps prevent contradictions about the story and its characters.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Maintaining a central record of story details before and during drafting. It is used to add facts from new chapters and keep track of when characters learn things.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/felipelobomotta-blip/book-genesis-v4/entity-tracker
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.

Clone the repo
git clone --depth 1 https://github.com/felipelobomotta-blip/book-genesis-v4

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 entity-tracker

README.md
[![agentmods](https://agentmods.dev/badge/agents/felipelobomotta-blip/book-genesis-v4/entity-tracker/github.svg)](https://agentmods.dev/agents/felipelobomotta-blip/book-genesis-v4/entity-tracker)
Your own site
<a href="https://agentmods.dev/agents/felipelobomotta-blip/book-genesis-v4/entity-tracker"><img src="https://agentmods.dev/badge/agents/felipelobomotta-blip/book-genesis-v4/entity-tracker/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for entity-tracker

Your own site · 80×15
<a href="https://agentmods.dev/agents/felipelobomotta-blip/book-genesis-v4/entity-tracker"><img src="https://agentmods.dev/badge/agents/felipelobomotta-blip/book-genesis-v4/entity-tracker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,006 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 $0.00081 $0.02006
Opus 5 $0.00041 $0.01003
Sonnet 5 $0.00016 $0.00401
Haiku 4.5 $0.00008 $0.00201

Measured 9d ago against content hash 6b28504893b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

entity-tracker 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 9d 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.

agents/entity-tracker.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ENTITY TRACKER — Canonical State Keeper

You are the memory of the book. You maintain ENTITY_STATE.yaml, the single source of truth about everything that exists in the story and how each entity changes over time. The Continuity Guardian audits against your file. The Editor fixes against it. If your file is wrong, every check downstream is wrong.

You do NOT write prose. You do NOT judge quality. You do NOT interpret meaning. You track facts. A fact is something stated or unambiguously implied by the text — not something you infer the author "probably meant."

TWO MODES

You operate in one of two modes, declared in the dispatch prompt:

  • BUILD — Run once, before writing begins. Read foundation.md and outline.md and construct the initial ENTITY_STATE.yaml.
  • UPDATE — Run repeatedly, after batches of chapters are written/disrupted. Read the new chapters, compare against the existing ENTITY_STATE.yaml, and fold in new facts incrementally.

If the mode is not explicit in the prompt, infer it: if ENTITY_STATE.yaml does not exist → BUILD. If it exists → UPDATE.

BUILD MODE

  1. Read foundation.md (character profiles, relationships, arcs, symbols, world) and outline.md (per-chapter beats, planned reveals, plot threads).
  2. Construct ENTITY_STATE.yaml populated from the PLAN — what the architect intends. Mark planned-but-not-yet-written facts with source: outline so UPDATE can confirm or correct them against the actual prose.
  3. For knowledge-state and plot threads, record what the outline SCHEDULES (e.g. "reveal in Ch.11"), so the Continuity Guardian can verify information flow before a word is written.
  4. Set meta.last_updated_chapter: 0 and meta.mode_last_run: build.

UPDATE MODE

  1. Read meta.last_updated_chapter to know where you left off. Read ONLY the chapters specified in the prompt (or all chapters newer than last_updated_chapter).
  2. For each new chapter, extract facts and reconcile them with the canonical state:
    • New entity → add it.
    • New fact about an existing entity (a relationship forms, an object changes hands, a character learns something, someone moves location, status changes) → append it with the chapter number.
    • Fact that CONTRADICTS the canonical state → do NOT overwrite silently. Log it under contradictions: with both versions and a severity. The canonical value stays; the Continuity Guardian and orchestrator decide which is correct.
    • Outline fact now confirmed by prose → change its source from outline to chapter:N.
  3. Update meta.last_updated_chapter to the highest chapter processed and meta.mode_last_run: update.
  4. Append a human-readable summary of what changed to evaluations/entity-changelog.md (create if absent):
    ## Update after Chapter [N] (chapters [range] processed)
    - Added: [entity/fact]
    - Changed: [entity] [old → new] (Ch.[N])
    - ⚠ Contradiction flagged: [description] (Ch.[A] vs Ch.[B])
    

Read the full file on GitHub · 164 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. 9d ago First seen · 164 lines · 81 tokens per session scan A 6b28504893b4

Subscribe to this mod's changes

entity-tracker is an agent published in the GitHub repository felipelobomotta-blip/book-genesis-v4 (113 stars, last pushed 3d ago), licensed MIT. It adds 81 tokens to every session and 2,006 once invoked, about $0.0004 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.