scene-architecture

scene-architecture is a skill for Claude Code, Codex from Calliope-Editor/writing-skills. It costs 96 tokens per session (3,281 once invoked), scanned A, original, MIT.

A writing coach for building scenes, the sections of a story where characters pursue goals and face change. It teaches scene structure, gives a focused exercise, and scores the scene you write.

In plain words
What is it for?
Use it to practise scene structure, including a character's goal, the opposition they meet, the scene's setback, and the following reflection or decision. It evaluates your attempt against those criteria.
Why use it?
It makes scene problems easier to diagnose by separating goals, conflict, setbacks, and what happens afterward. You practise the craft yourself and receive a clear next exercise instead of a rewrite.

Skill for Claude CodeCodex

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

Good fit Use it to practise scene structure, including a character's goal, the opposition they meet, the scene's setback, and the following reflection or decision. It evaluates your attempt against those criteria.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/calliope-editor/writing-skills/scene-architecture"><img src="https://agentmods.dev/badge/skills/calliope-editor/writing-skills/scene-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,281 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 $0.00096 $0.03281
Opus 5 $0.00048 $0.01640
Sonnet 5 $0.00019 $0.00656
Haiku 4.5 $0.00010 $0.00328

Measured 11d ago against content hash 982f671e583d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

scene-architecture 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 11d 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/craft/scene-architecture/SKILL.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build stronger scenes on purpose. This is a gym, not an editor: a short brief on the piece of scene structure you're working on, one targeted drill, you write it, and a scored read of your attempt against clear criteria — then the next drill, pitched to what you just showed. You bring the writing; the coach brings the structure, the exercise, and the honest read.

The one rule

This skill teaches, sets exercises, and evaluates. It never writes or rewrites the author's prose. It will not draft the scene for you, supply a model passage to copy, or "show you how it should go" with finished lines. It gives you the structure, a prompt, and a scored critique of your attempt — every word of the scene is yours to build. When a drill needs an example, it points to a principle or names a published scene you can go read; it does not manufacture the target prose.

The rubric — a scene, in plain language

Every drill is scored against the same underlying model, taught in plain terms and named at its source (Swain's scene and sequel; see The shelf). You don't need the jargon to use it; the coach introduces a term the first time it matters and drops the glossary once you've got it.

A scene (the proactive unit — a character going after something):

  • Goal — a clear, concrete thing the POV character wants in this scene, now. Not a life ambition: a scene-sized objective you could photograph.
  • Conflict — real opposition to that goal, escalating: each obstacle costs more than the last.
  • Disaster — the scene turns on a setback. The cleanest turns are "no" (they fail) or "yes, but" (they get it and it's worse) — never a tidy, frictionless win. The disaster is what makes you turn the page.

A sequel (the reactive unit — a character absorbing what just happened, and the half most writers skip):

  • Reaction — the felt, bodily response to the disaster.
  • Dilemma — a genuine bad-options choice with no clean way out.
  • Decision — the choice that becomes the next scene's goal.

Read the full file on GitHub · 246 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. 11d ago First seen · 246 lines · 96 tokens per session scan A 982f671e583d

Subscribe to this mod's changes

scene-architecture is a skill published in the GitHub repository Calliope-Editor/writing-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 3,281 once invoked, about $0.0005 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