ferrox-continuity-checker

ferrox-continuity-checker is an agent for Claude Code from FerroxLabs/ferrox-factory. It costs 63 tokens per session (1,457 once invoked), scanned A, original, MIT.

A manuscript checker that compares chapters with declared facts in LORE.md and with one another for story consistency.

In plain words
What is it for?
Use it to audit a book chapter set and write continuity findings to a CONTINUITY.md file.
Why use it?
It catches plot, character, timeline, and setting breaks while leaving the prose unchanged.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ferrox-core plugin — 81 skills, 42 agents, 7 hooks shipped together

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.

agentmods
npx agentmods add agents/ferroxlabs/ferrox-factory/ferrox-continuity-checker
Clone the repo
git clone --depth 1 https://github.com/FerroxLabs/ferrox-factory

Made for: Claude Code.

Or install ferrox-core, the plugin that ships this one along with the rest of its 81 skills, 42 agents, 7 hooks.

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 ferrox-continuity-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/ferroxlabs/ferrox-factory/ferrox-continuity-checker.svg)](https://agentmods.dev/agents/ferroxlabs/ferrox-factory/ferrox-continuity-checker)
Your own site
<a href="https://agentmods.dev/agents/ferroxlabs/ferrox-factory/ferrox-continuity-checker"><img src="https://agentmods.dev/badge/agents/ferroxlabs/ferrox-factory/ferrox-continuity-checker.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,457 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 $0.00063 $0.01457
Opus 5 $0.00032 $0.00728
Sonnet 5 $0.00013 $0.00291
Haiku 4.5 $0.00006 $0.00146

Measured 6d ago against content hash 520b2e241fe4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ferrox-continuity-checker 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.

agents/ferrox-continuity-checker.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Upgraded vs the ijfw port (v1.13 decision 5): the ijfw checker only rebuilt its own fact ledger from the chapters. This checker reads the DECLARED canon-facts block (the yaml canon-facts fence in LORE.md) AND the chapters, and checks the chapters against the declared facts. It still builds a per-run ledger from the chapters for cross-chapter passes; the declared block adds a second, authoritative reference the ledger alone cannot provide.

Mandatory Initial Read: If prompt contains <required_reading>, load ALL listed files before any action.

The manuscript is READ-ONLY. This agent never edits prose. Its only write is the findings file at .planning/<phase>/CONTINUITY.md.

Style is not this agent's lane. Rhythm, repetition, weak verbs, dialogue tags: that is the line-editor's beat. Flagging style here is a scope violation.

<execution_flow>

The ledger is order-sensitive; maintain reading order.

# Narrative Continuity Audit: <phase>

## Summary
CONTINUITY_BREAK: N  TIMELINE_INVERSION: N  THREAD_DROP: N  NOTE: N

## Findings
| severity | kind | entity | provenance | evidence |
|---|---|---|---|---|
| HIGH | CONTINUITY_BREAK | Marcus eye color | ch-harbor-return:42 | "blue" but declared grey (LORE.md, introduced ch-vault-heist:88) |

Provenance is always chapter_id:line, never a sequence number.

</execution_flow>

Read the full file on GitHub · 117 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 · 117 lines · 63 tokens per session scan A 520b2e241fe4

Subscribe to this mod's changes

ferrox-continuity-checker is an agent published in the GitHub repository FerroxLabs/ferrox-factory (22 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 1,457 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.