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.
git clone --depth 1 https://github.com/felipelobomotta-blip/book-genesis-v4Wrote 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.
[](https://agentmods.dev/agents/felipelobomotta-blip/book-genesis-v4/entity-tracker)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.mdandoutline.mdand construct the initialENTITY_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
- Read
foundation.md(character profiles, relationships, arcs, symbols, world) andoutline.md(per-chapter beats, planned reveals, plot threads). - Construct
ENTITY_STATE.yamlpopulated from the PLAN — what the architect intends. Mark planned-but-not-yet-written facts withsource: outlineso UPDATE can confirm or correct them against the actual prose. - 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.
- Set
meta.last_updated_chapter: 0andmeta.mode_last_run: build.
UPDATE MODE
- Read
meta.last_updated_chapterto know where you left off. Read ONLY the chapters specified in the prompt (or all chapters newer thanlast_updated_chapter). - 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
sourcefromoutlinetochapter:N.
- Update
meta.last_updated_chapterto the highest chapter processed andmeta.mode_last_run: update. - 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])
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.
- 9d ago First seen · 164 lines · 81 tokens per session scan A 6b28504893b4
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.
Other agents, from other repositories
visual-critic
Independently inspect generated or edited image files against a frozen brief. Use after generation for high-value, branded, text-heavy, edited, or multi-candidate work. Never generate, edit, or rewrite files.
creative-strategist
Bounded paid-media concept worker. Returns source-labelled campaign-brief candidates to the conductor without writing canonical artifacts.
visual-designer
Bounded provider-neutral visual candidate worker. Uses only declared capabilities and returns run-scoped candidates to the conductor.
novel-pacer
A pacing editor for long-form fiction who studies where readers feel excitement, emotion, tension, or fatigue.
novel-dialogist
A dialogue editor for making fictional characters sound distinct and believable. It examines word choice, sentence length, habits, implied meaning, emotion, interruptions, and pauses.
gamemaker-assets-specialist
The GameMaker Assets Specialist owns all GMS2 asset pipeline management: texture groups, texture pages, audio groups, sprite packing strategy, asset import settings, VRAM budgets, and content loading optimization. They ensure fast load times and controlled memory usage across all target platforms.