continuity-editor

continuity-editor is a skill for Claude Code, Codex from Calliope-Editor/writing-skills. It costs 139 tokens per session (2,035 once invoked), scanned A, original, MIT.

A continuity checker for manuscripts that compares the story with its established facts, rules, timeline, objects, and characters’ knowledge.

In plain words
What is it for?
Finding issues such as changing character details, impossible dates, broken world rules, inconsistent object states, and characters knowing things too early.
Why use it?
It makes contradictions visible before readers find them, without deciding which version is correct or rewriting the prose.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Finding issues such as changing character details, impossible dates, broken world rules, inconsistent object states, and characters knowing things too early.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/calliope-editor/writing-skills/continuity-editor
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.

Any agent
npx skills add Calliope-Editor/writing-skills --skill continuity-editor
Clone the repo
git clone --depth 1 https://github.com/Calliope-Editor/writing-skills

Made for: Claude Code, Codex.

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 continuity-editor

README.md
[![agentmods](https://agentmods.dev/badge/skills/calliope-editor/writing-skills/continuity-editor/github.svg)](https://agentmods.dev/skills/calliope-editor/writing-skills/continuity-editor)
Your own site
<a href="https://agentmods.dev/skills/calliope-editor/writing-skills/continuity-editor"><img src="https://agentmods.dev/badge/skills/calliope-editor/writing-skills/continuity-editor/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 continuity-editor

Your own site · 80×15
<a href="https://agentmods.dev/skills/calliope-editor/writing-skills/continuity-editor"><img src="https://agentmods.dev/badge/skills/calliope-editor/writing-skills/continuity-editor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 139 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,035 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 $0.00139 $0.02035
Opus 5 $0.00069 $0.01018
Sonnet 5 $0.00028 $0.00407
Haiku 4.5 $0.00014 $0.00203

Measured 9d ago against content hash b3070222e2ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

continuity-editor 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.

skills/editorial/continuity-editor/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Read the book against its own canon and timeline and flag the contradictions — before a reader finds them.

The one rule

This skill reads, cross-checks, and flags. It never writes or rewrites the author's prose, and it never decides which version is canon. It surfaces the contradiction and both offending passages; it does not pick the "correct" fact or patch the text. Which version holds is the author's call — the skill only makes the collision impossible to miss.

Craft criteria

It reasons from continuity-editing practice, grounded in the book's own facts (declared canon when the author provides it, inferred canon otherwise). It tracks:

  • Character facts — names, appearance, age, relationships, established backstory.
  • Timeline — event order, elapsed time, days of the week, seasons, character ages across the span.
  • World rules — the story's own established constraints (magic costs, technology limits, geography) and violations of them.
  • Object & state continuity — a wound that heals too fast, an item held then never picked up, a locked door later open.
  • Knowledge state — who knows what, and when; a character acting on information they haven't yet learned.
  • Spatial logic — travel times and distances that don't reconcile.

Scope

Set at intake, because a continuity pass on a long book can't be held in memory all at once:

  • Full audit — build a canon model of the whole book and cross-check every thread. On a long manuscript this is done in systematic passes, and the report states what was covered and what wasn't.
  • Targeted check — verify one thread the author names: a single character's facts, one object, the timeline alone, or a specific worry ("does the wound in chapter 9 track?"). Fast, and context-friendly.

Input

Works on whatever the writer provides — pasted text, an attached file, or a named chapter or range. No tool or account assumed. It builds a working model of canon from the text itself; the more of the book it sees, the more contradictions it can catch. Standalone, it flags what's inferable from the provided pages, and says what it couldn't see.

Read the full file on GitHub · 108 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 · 108 lines · 139 tokens per session scan A b3070222e2ba

Subscribe to this mod's changes

continuity-editor is a skill published in the GitHub repository Calliope-Editor/writing-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 139 tokens to every session and 2,035 once invoked, about $0.0007 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 2026-08-31.