autonovel-genre-pack

autonovel-genre-pack is a skill for Claude Code, Codex from DukeTwoCan/autonovel-agent-skills. It costs 32 tokens per session (731 once invoked), scanned A, original, MIT.

Authoring rules for AutoNovel genre packs, which are data files that guide an automated novel-writing pipeline for a particular genre.

In plain words
What is it for?
Use it to create, extend, or validate a genre pack, including its manifest, world rules, characters, story beats, drafting guidance, and safeguards.
Why use it?
It prevents genre packs from being assembled inconsistently or with the wrong files. It also separates pack design from writing the novel itself.

Skill for Claude CodeCodex

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

Good fit Use it to create, extend, or validate a genre pack, including its manifest, world rules, characters, story beats, drafting guidance, and safeguards.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/duketwocan/autonovel-agent-skills/autonovel-genre-pack
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 DukeTwoCan/autonovel-agent-skills --skill autonovel-genre-pack
Clone the repo
git clone --depth 1 https://github.com/DukeTwoCan/autonovel-agent-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 autonovel-genre-pack

README.md
[![agentmods](https://agentmods.dev/badge/skills/duketwocan/autonovel-agent-skills/autonovel-genre-pack/github.svg)](https://agentmods.dev/skills/duketwocan/autonovel-agent-skills/autonovel-genre-pack)
Your own site
<a href="https://agentmods.dev/skills/duketwocan/autonovel-agent-skills/autonovel-genre-pack"><img src="https://agentmods.dev/badge/skills/duketwocan/autonovel-agent-skills/autonovel-genre-pack/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 autonovel-genre-pack

Your own site · 80×15
<a href="https://agentmods.dev/skills/duketwocan/autonovel-agent-skills/autonovel-genre-pack"><img src="https://agentmods.dev/badge/skills/duketwocan/autonovel-agent-skills/autonovel-genre-pack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 731 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 $0.00032 $0.00731
Opus 5 $0.00016 $0.00365
Sonnet 5 $0.00006 $0.00146
Haiku 4.5 $0.00003 $0.00073

Measured 12d ago against content hash b6ba9afbb047, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

autonovel-genre-pack 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 12d 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/creative/autonovel-genre-pack/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AutoNovel Genre Pack Authoring

Create or revise data-driven genre packs. This skill is not invoked during novel generation.

Workflow

Hermes supplies ${HERMES_SKILL_DIR} as this skill's directory. Outside the Hermes harness, run the repository-relative commands in ../autonovel/genres/AUTHORING.md from the repository root.

  1. Read ../autonovel/genres/AUTHORING.md completely. Use its category decision guide, manifest contract, file responsibilities, size targets, combination tests, and definition of done.
  2. Choose one stable kebab-case ID, one category, and only the task files the pack genuinely needs. Accepted scaffold file IDs are contract, world, characters, beats-primary, beats-modifier, drafting, slop, guardrails, and patterns.
  3. If the pack does not exist, scaffold it before writing content:
    python ${HERMES_SKILL_DIR}/../autonovel/lib/genre_pack.py scaffold --id <pack-id> --category <category> --files <comma-separated-file-ids> --genres-root ${HERMES_SKILL_DIR}/../autonovel/genres
    
    Never scaffold over an existing pack. Extend its manifest and files directly instead.
  4. Replace template comments with pack-specific rules. Keep universal craft in ../autonovel/references/; do not duplicate it in a pack.
  5. Declare tags, aliases, dependencies (includes), conflicts, beat capability, sections, and optional patterns in manifest.json.
  6. Validate the pack and its dependency graph:
    python ${HERMES_SKILL_DIR}/../autonovel/lib/genre_pack.py validate --pack <pack-directory> --genres-root ${HERMES_SKILL_DIR}/../autonovel/genres
    
  7. Inspect task paths and estimated context cost:
    python ${HERMES_SKILL_DIR}/../autonovel/lib/genre_pack.py inspect --pack <pack-id> --genres-root ${HERMES_SKILL_DIR}/../autonovel/genres
    
  8. Dry-run a synthetic profile through compilation:
    python ${HERMES_SKILL_DIR}/../autonovel/lib/genre_resolver.py compile --state <synthetic-state.json> --task all --genres-root ${HERMES_SKILL_DIR}/../autonovel/genres --workspace <temporary-workspace>
    
    Confirm selection, primary beats, required sections, optional omissions, and conflicts behave as intended.
  9. Run focused tests before declaring the pack complete:
    python -m pytest tests/test_genre_pack.py tests/test_genre_registry.py tests/test_genre_resolver.py tests/test_genre_compile.py tests/test_genre_patterns.py tests/test_genre_integration.py -q
    

Read the full file on GitHub · 53 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. 12d ago First seen · 53 lines · 32 tokens per session scan A b6ba9afbb047

Subscribe to this mod's changes

autonovel-genre-pack is a skill published in the GitHub repository DukeTwoCan/autonovel-agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 731 once invoked, about $0.0002 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.

Related

Other skills, from other repositories