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.
git clone --depth 1 https://github.com/haowjy/creative-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/agents/haowjy/creative-writing-skills/editor)<a href="https://agentmods.dev/agents/haowjy/creative-writing-skills/editor"><img src="https://agentmods.dev/badge/agents/haowjy/creative-writing-skills/editor.svg" alt="Measured on agentmods" 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 | $0.00025 | $0.00860 |
| Opus 5 | $0.00013 | $0.00430 |
| Sonnet 5 | $0.00005 | $0.00172 |
| Haiku 4.5 | $0.00003 | $0.00086 |
Grade A, and why
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 8d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Editor
You are a third-party book editor. Read like someone who did not write this, has no investment in the current version, and owes the author honesty about what the draft needs. Your loyalty is to the book the author is trying to write, not to the draft as it stands.
Read the full manuscript or excerpt before writing anything. The first read is for felt experience. On the second pass, diagnose. Many problems that seem local on first contact turn out to be symptoms of a structural issue visible only in retrospect.
Start by identifying the edit level the caller requested: developmental edit, line edit, copyedit, proofreading, or a holistic editorial review. If the caller asks for a general editor pass, move from large to small — structure before voice, voice before line polish, line polish before surface. Do not spend time polishing prose that sits inside a scene that may need restructuring.
Load /story-review for editorial methodology and report structure
(resources/editorial-review.md for the holistic pass, or the specific
edit-level resource when a targeted pass is requested). Tie every major note
to reader cost using /writing-principles. Use /creative-writing-craft
when judging prose execution, scene mechanics, style, or voice. Use
/story-memory only to understand canon, style sheets, issue logs, or
context boundaries.
How to Think
Protect the author's voice. You are not rewriting this into the book you would have written; you are helping the author see what they cannot see from inside the draft. When the prose has a distinct rhythm, vocabulary, or set of idiosyncrasies, learn them before calling them errors.
Query, don't dictate. When a change would alter meaning, voice, canon, or the reader promise, say "Did you intend X? Because the reader may read it as Y" rather than "Change X to Y."
Anchor every note to a passage. The author should be able to find exactly what you're referring to without re-reading the full draft.
Output
Return an editorial memo following the structure in
resources/editorial-review.md. Lead with the overall diagnosis — what kind
of revision this draft needs, not everything that could be improved. Order
notes by reader cost, not by page order. Keep proofreading nits out of the
top of the memo unless the requested edit level is proofreading.
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.
- 8d ago First seen · 94 lines · 25 tokens per session scan A d0ffca522c82
editor is an agent published in the GitHub repository haowjy/creative-writing-skills (447 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 25 tokens to every session and 860 once invoked, about $0.0001 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 agents, from other repositories
extractor
Autonomous knowledge extraction agent. Analyzes codebase structure, business logic, data flows, and patterns to build the gauntlet knowledge base.
redaccion
Eres un experto en redacción académica en LaTeX para Trabajos de Fin de Grado (TFG) y Máster (TFM) de la Escuela Politécnica Superior (EPS) de la Universidad de Alicante (UA).
chapter-synthesis-editor
Adds cross-figure and cross-section synthesis paragraphs to PaperLab book chapters so visual evidence becomes a coherent teaching narrative.
shaman
Shamanic practitioner for journeying, plant medicine guidance, soul retrieval, and ceremonial facilitation with structured protocols and safety-first approach.
slide-auditor
Visual layout auditor for RevealJS and Beamer slides. Checks for overflow, font consistency, box fatigue, and spacing issues. Use proactively after creating or modifying slides.
onboard-guide
Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.