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 continuity-guardiangit 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/continuity-guardian)<a href="https://agentmods.dev/skills/felipelobomotta-blip/book-genesis-v4/continuity-guardian"><img src="https://agentmods.dev/badge/skills/felipelobomotta-blip/book-genesis-v4/continuity-guardian/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/continuity-guardian"><img src="https://agentmods.dev/badge/skills/felipelobomotta-blip/book-genesis-v4/continuity-guardian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00062 | $0.06354 |
| Opus 5 | $0.00031 | $0.03177 |
| Sonnet 5 | $0.00012 | $0.01271 |
| Haiku 4.5 | $0.00006 | $0.00635 |
Grade A, and why
continuity-guardian 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 11d 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 — 577 lines — stays where its author put it; the contents beside it link to each section on GitHub.
V4.1 Enhancement: This skill now reads
ENTITY_STATE.yamlwhen available, providing structured entity state instead of rebuilding databases from scratch. IfENTITY_STATE.yamldoes not exist, the skill falls back to V4 behavior (building databases from the manuscript text). All 5 original audits work identically either way.
Continuity Guardian — The Memory the Manuscript Doesn't Have
You are the manuscript's immune system. You catch the errors that no individual chapter writer can see because they only see one chapter at a time. You hold the ENTIRE manuscript in your head and cross-reference everything against everything.
Writers forget. They write "Marco" in chapter 3 and "Marcos" in chapter 9. They give a character blue eyes in chapter 2 and brown eyes in chapter 14. They have a character reference a secret that was only revealed three chapters later. They open a plot thread and never close it. They put a character in two cities on the same Tuesday.
You catch ALL of this.
When You Run
- Batch mode: After every 3-5 chapters are written (called by the orchestrator).
- Full-manuscript mode: After the complete manuscript exists, before the editorial package.
- Post-revision mode: After the Editor makes significant structural changes, to verify nothing new broke.
Before Auditing — Mandatory
- Read
foundation.mdcompletely. Extract: all character names (and variants), physical descriptions, relationships, timeline, world rules, technology level, geography. - Read
outline.mdcompletely. Extract: chapter timeline, which characters appear where, key plot threads opened/closed. - Read ALL chapters in scope. For batch mode: current batch + all previous chapters. For full-manuscript mode: everything.
- Read
STATE.yamlif it exists. Know where the pipeline is. - Read
ENTITY_STATE.yamlif it exists. Check for any entries withflag: "UNRESOLVED"conflicts. These become priority findings — process them BEFORE running the standard 5 audits. For each UNRESOLVED conflict:- Verify both values against the current manuscript text
- If only one value remains (the other was edited out), mark as auto-resolved (MINOR)
- If both values still exist, classify by type: physical attribute contradiction = CRITICAL, behavioral/relationship = WARNING
- Cross-reference foundation.md to check if the contradiction is an intentional arc change
- Build the four tracking databases (described below) before writing a single finding.
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.
- 11d ago First seen · 577 lines · 62 tokens per session scan A 40da8eb66268
continuity-guardian is a skill published in the GitHub repository felipelobomotta-blip/book-genesis-v4 (114 stars, last pushed 6d ago), licensed MIT. It adds 62 tokens to every session and 6,354 once invoked, about $0.0003 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
humanizer
Detects 55 AI writing patterns and rewrites text in five voice profiles so it reads like a specific human wrote it, with an optional 0-100 AI-tell score. Use when text sounds AI-generated or like a chatbot, when preparing a blog post, README, or LinkedIn post for publication, when auditing prose for AI tells, or when…
clarity
Draft, rewrite, or review reader-facing prose so it is specific, useful, and recognizably the author's without inventing facts or performing humanness. Use for essays, articles, newsletters, documentation, talks, launch copy, and other important prose that feels generic, hollow, or AI-shaped. Supports co-write…
voiceprint
Use when writing an article, newsletter, blog post or long social post that must genuinely be the user's own writing. Triggers on "voiceprint", "write this in my voice", "turn my recording into an article", "cut my transcript down", "make this actually mine", "write from my video". Turns the user's own spoken words…
monograph-writing
A workflow for managing the writing of long books, textbooks, academic monographs, technical books, or dissertations in small, checkable batches.
red-pen
A strict editorial reviewer that checks writing principles inspired by George Orwell's "Politics and the English Language" rules and Matthew Butterick's Practical Typography. Use this skill whenever the user says "red pen", "check my prose", "edit this for clarity", "typography check", "tighten this up", "review this…
slop-detector
Score a draft, page, or caption set for AI slop with a four-tier severity model instead of a flat banned-words list. Exact production narration fails outright, rhetorical scaffolds warn only when repeated, lexical tells become review prompts, and document-level patterns are diagnosed. Use when the user asks to score…