Skip to content
SkillScript-led5,773 tokens in use

story-setup

Deploys the Oh Story writing toolkit into your project: hooks, sub-agents, rules and reference files for Claude Code, Codex, OpenCode and other agents.

8,793 stars on the repository MIT Licensezenstory-ai/oh-story-claudecode · skills/story-setup
npx skills add zenstory-ai/oh-story-claudecode -y -g
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing story-setup costs

120tokens idle
5,773tokens in use
31,282tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Script-led

Script-ledMixedModel-led

Most of this skill is scripts, so it behaves much the same whichever model runs it.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: references/antigravity/hooks/story_antigravity_hook.js, references/antigravity/hooks/story_hook_core.js, references/codex/hooks/run-story-hook.sh, references/codex/hooks/story_codex_hook.py, references/opencode/plugin.ts, references/opencode/pre-commit.sh, references/opencode/story_hook_core.js, references/templates/hooks/check-prose-after-write.sh, references/templates/hooks/detect-story-gaps.sh, references/templates/hooks/guard-outline-before-prose.sh, references/templates/hooks/lib/common.sh, references/templates/hooks/lib/sentinel.sh, references/templates/hooks/post-compact.sh, references/templates/hooks/pre-compact.sh, references/templates/hooks/session-end.sh, references/templates/hooks/session-start.sh, references/templates/hooks/story_hook_cli.js, references/templates/hooks/story_hook_core.js, references/templates/hooks/validate-story-commit.sh, references/zcode/hooks/story_hook_core.js, references/zcode/hooks/story_zcode_hook.js, scripts/copy-path-safety.py, scripts/deploy-antigravity-skills.py, scripts/generate-antigravity-agents.mjs, scripts/merge-antigravity-hooks.py, scripts/merge-claude-settings.py, scripts/merge-codex-hooks.py, scripts/merge-project-instructions.py.

Touches

shelldetectednetworkdetectedwrites filesdetectedgitdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter8/15
  • Structure22/25
  • Examples12/15
  • Output10/15
  • Size13/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Fair
  • Writes files−8

    does this on the machine, and the frontmatter does not say so

    references/antigravity/hooks/story_antigravity_hook.js, line 119
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    references/antigravity/hooks/story_hook_core.js, line 5
  • File that was not read−15

    a file the skill ships that was not read, so what it does is unknown

    references/codex/AGENTS.md.tmpl
  • File that was not read−5

    a file the skill ships that was not read, so what it does is unknown

    references/codex/hooks/run-story-hook.cmd
  • File that was not read−5

    a file the skill ships that was not read, so what it does is unknown

    references/generic/AGENTS.md.tmpl
  • File that was not read−5

    a file the skill ships that was not read, so what it does is unknown

    references/openclaw/AGENTS.md.tmpl
  • File that was not read−5

    a file the skill ships that was not read, so what it does is unknown

    references/opencode/AGENTS.md.tmpl
  • Reaches the network−10

    does this on the machine, and the frontmatter does not say so

    references/templates/hooks/session-start.sh, line 67

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity100
  • Maintenance100
  • Community60
  • Maturity28
  • Momentum40

story-setup prepares a writing project for the rest of the Oh Story skills. It works out which agent host you are using, confirms the project folder, copies the right hooks, sub-agents, rules and reference files for that host, merges its own block into your CLAUDE.md or AGENTS.md, and writes a deployment marker.

It supports Claude Code, OpenCode, Codex, Google Antigravity, ZCode, OpenClaw and Reasonix, plus a generic file mode for web AI and custom agents. Existing user configuration is kept, and the deployment can be repeated safely. A check mode only diagnoses.

What You Get

  • Hooks, sub-agents and rules installed for your agent host
  • A managed block in CLAUDE.md or AGENTS.md that tells the agent how to use the writing skills
  • A deployment marker file with version, target host and reference location
  • A check mode that diagnoses a broken or outdated setup and reports it
  • An author-friendly report of what works now and what to do next, such as opening a new session

Common Use Cases

  • Preparing a new folder before writing the first chapter of a book
  • Updating a project after the skill package has been upgraded
  • Adding a second agent host to a project already set up for another

What Makes It Unique

It is the infrastructure step of the package: one command covers seven agent hosts, merges its configuration into existing files by managed blocks, and keeps your own settings and manuscripts untouched. It stops before writing anything when its bundled packages are incomplete or when the project is newer than the skill.

Under The Hood

The skill reads its own bundled reference folders and your project, then copies files into the project root and the host’s configuration folders. It installs hooks that run in later agent sessions: they show project status, guard outlines before prose, check chapters after they are written and validate commits. The Claude Code session-start hook also calls the GitHub releases API with curl at most once a day to look for a new version, and an environment variable turns that off. Setup merges settings files for Claude Code, Codex and Antigravity with bundled Python and Node scripts, writes a deployment marker, and runs a path-safety script before recursive copies. It asks questions through the agent when the host or target is unclear. It writes many files and changes agent configuration.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers