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 Calliope-Editor/writing-skills --skill copy-editorgit clone --depth 1 https://github.com/Calliope-Editor/writing-skillsWrote 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/calliope-editor/writing-skills/copy-editor)<a href="https://agentmods.dev/skills/calliope-editor/writing-skills/copy-editor"><img src="https://agentmods.dev/badge/skills/calliope-editor/writing-skills/copy-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.
<a href="https://agentmods.dev/skills/calliope-editor/writing-skills/copy-editor"><img src="https://agentmods.dev/badge/skills/calliope-editor/writing-skills/copy-editor.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 | $0.00148 | $0.02245 |
| Opus 5 | $0.00074 | $0.01123 |
| Sonnet 5 | $0.00030 | $0.00449 |
| Haiku 4.5 | $0.00015 | $0.00225 |
Grade A, and why
copy-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 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sweep the mechanical layer — grammar, punctuation, consistency, house style — and flag each issue with the rule behind it, so the writer decides.
The one rule
This skill reads, checks, and flags. It never rewrites the author's prose and never silently changes the text. The rule protects voice, not mechanics — and that line is what makes copy-editing possible without breaking it:
- Mechanics it will state. Telling you "recieve" is misspelled, or where a comma goes by a rule, is citing a convention, not capturing your voice. Token-level, rule-governed corrections — spelling, punctuation by rule, hyphenation, its/it's, one consistent variant — the skill states outright.
- Prose it will not. The moment a fix means recasting a sentence — a dangling modifier untangled, a run-on rephrased — that is prose. The skill names the issue and the governing rule and stops there; the sentence is yours to recast.
- Voice it will only query. Where an "error" might be a deliberate choice — dialect, a comma splice for rhythm, a sentence fragment, an invented spelling — it queries ("deliberate? then keep it"), never asserts a fault. The copy editor proposes; the author disposes.
Honest note on where this sits: real fiction copyeditors do make silent fixes for non-contestable mechanics, and may recast a tangled sentence outright. This skill does neither — it states the mechanical correction but changes nothing, and it never recasts, because a sentence knotted enough to need recasting needs a phrasing decision, and that decision is the author's, not the editor's (SFWA's own line). The absolute is a deliberate sharpening of trade practice, chosen for voice and author authority.
How it flags
Every flag names the issue, cites the governing rule (the Chicago Manual of Style by default, or the author's declared house style), and quotes the line. What it does next depends on which of the three the flag is:
- Clear mechanical error → states the standard correction, at the help-level set at intake (see below).
- Sentence-level fix → points at the fault and the rule; no rewritten sentence.
- Possible voice choice → a query, not a correction.
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 · 123 lines · 148 tokens per session scan A bc5ff97883e2
copy-editor is a skill published in the GitHub repository Calliope-Editor/writing-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 148 tokens to every session and 2,245 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.
Other skills, from other repositories
story-import
A tool for turning an existing novel into a structured writing project. It analyzes the book and organizes its characters, settings, plot plans, chapters, and tracking data for later writing.
story-review
A review workflow for finding story problems from several viewpoints, including issues with structure, characters, wording, and fictional world rules. It can use multiple reviewer agents or work alone.
story-long-analyze
A long-form fiction analysis workflow for breaking down a novel’s opening chapters, characters, pacing, turning points, relationships, and overall structure.
story-deslop
A writing editor for Chinese web novels that detects writing patterns often associated with AI-generated text and makes the prose feel more natural.
story-cover
A novel-cover generator that creates a cover with the book title and author name. It chooses a visual style from the book information and can use Codex's image-generation tool.
story-long-scan
A research workflow for studying long-form Chinese web-fiction charts on platforms such as Qidian, Fanqie, and Jinjiang. It looks for repeated patterns across multiple books and charts rather than relying on one ranking.