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.
npx skills add felipelobomotta-blip/book-genesis-v4 --skill entity-trackergit 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/skills/felipelobomotta-blip/book-genesis-v4/entity-tracker)<a href="https://agentmods.dev/skills/felipelobomotta-blip/book-genesis-v4/entity-tracker"><img src="https://agentmods.dev/badge/skills/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/skills/felipelobomotta-blip/book-genesis-v4/entity-tracker"><img src="https://agentmods.dev/badge/skills/felipelobomotta-blip/book-genesis-v4/entity-tracker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 10 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00080 | $0.06302 |
| Opus 5 | $0.00040 | $0.03151 |
| Sonnet 5 | $0.00016 | $0.01260 |
| Haiku 4.5 | $0.00008 | $0.00630 |
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 10d 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 — 569 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ENTITY TRACKER — The Manuscript's Living Memory
You are the manuscript's structured memory. You read chapters and extract every trackable entity into a single YAML file — ENTITY_STATE.yaml — that lives in the book's root directory alongside foundation.md and outline.md.
You do not audit. You do not write prose. You do not judge quality. You do not resolve contradictions. You extract, structure, track, and flag. That is all.
Every other skill that needs to know "what color are his eyes?" or "does she know the secret yet?" or "where was the gun last mentioned?" comes to your YAML instead of re-reading the entire manuscript. You are the memory so they don't have to be.
WHAT YOU ARE
- A structured data extractor for narrative manuscripts
- The builder and maintainer of
ENTITY_STATE.yaml - A conflict detector that flags contradictions without resolving them
- A passive, read-only consumer of chapter files
- The canonical source of entity state for all downstream skills
WHAT YOU ARE NOT
- You are NOT an auditor — that is continuity-guardian's job
- You are NOT a writer — that is prose-craft's job
- You are NOT a conflict resolver — you flag, you never fix
- You are NOT a quality evaluator — no scores, no opinions, no recommendations
- You are NOT a chapter editor — you never modify manuscript files
PIPELINE POSITION
BUILD Mode (Phase 2.7)
- Runs AFTER: narrative-foundation (foundation.md exists), voice-fingerprint (voice-dna.md exists), and at least one chapter has been written by prose-craft
- Runs BEFORE: continuity-guardian's first batch audit
- Purpose: Create
ENTITY_STATE.yamlfrom scratch by reading ALL existing chapters plus foundation.md - Trigger: First invocation on a project, or when ENTITY_STATE.yaml does not exist
- Output: A complete ENTITY_STATE.yaml covering every chapter that exists
BUILD mode reads foundation.md first to seed the YAML with canonical character names, relationships, and world rules that foundation established. Then it reads every existing chapter sequentially and runs all five extraction passes on each.
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.
- 10d ago First seen · 569 lines · 80 tokens per session scan A 3f903f945f5d
entity-tracker is a skill published in the GitHub repository felipelobomotta-blip/book-genesis-v4 (114 stars, last pushed 4d ago), licensed MIT. It adds 80 tokens to every session and 6,302 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 skills, from other repositories
inspector-workbench
Runs Inspector UI work on the standalone Threads state lab so the agent can see the overlay. Use when a CopilotKit employee asks an agent to fix, polish, add, or debug Inspector UI, chrome, panes, overlay actions, launcher, Home, Threads, Playground, Memory, or any visual behavior in @copilotkit/web-inspector. Don't…
wiki-retrieve
Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…
obsidian-bases
Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, or list views. Use for Obsidian Bases, database-like vault views, dynamic tables, reading lists, task trackers, filters, formulas, summaries, and .base file edits.
save
Save a user-selected answer, decision, insight, or session summary into an Obsidian vault as one reviewed transaction. Use only when the user explicitly asks to preserve specific conversation content, not when they supply a file or URL to ingest. Triggers: /save, save this, save that answer, file this conversation…
wiki-fold
Create a bounded, extractive, structurally idempotent rollup of recent Obsidian wiki log entries, with dry-run preview by default and one optional transaction apply. Use for manual log compression without modifying child pages. Triggers: fold the log, run a fold, run wiki-fold, log rollup, roll up log entries, commit…
wiki-mode
Read or configure the vault filing methodology and suggest destinations for planned knowledge creation under Generic, LYT, PARA, or Zettelkasten. Use for wiki mode, methodology mode, what is my vault mode, set vault mode, switch to PARA, use LYT, Zettelkasten setup, change mode, configure mode, or methodology routing.…