scene-craft

scene-craft is a skill for Claude Code, Codex from third-order-labs/longform-plugin. It costs 41 tokens per session (3,196 once invoked), scanned A, original, MIT.

A guide for writing or reviewing fiction scenes so they feel physically grounded, inhabited, and shaped by believable characters and consequences.

In plain words
What is it for?
It helps add a location's ordinary functions, background activity, sensory texture, character motives, and cause-and-effect detail to scenes.
Why use it?
Scenes can feel like plot summaries when locations have no everyday life, sensory detail, or activity beyond the main action.

Skill for Claude CodeCodex

Part of the longform plugin — 6 skills, 4 commands shipped together

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.

agentmods
npx agentmods add skills/third-order-labs/longform-plugin/scene-craft
Any agent
npx skills add third-order-labs/longform-plugin --skill scene-craft
Clone the repo
git clone --depth 1 https://github.com/third-order-labs/longform-plugin

Made for: Claude Code, Codex.

Or install longform, the plugin that ships this one along with the rest of its 6 skills, 4 commands.

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-craft

README.md
[![agentmods](https://agentmods.dev/badge/skills/third-order-labs/longform-plugin/scene-craft.svg)](https://agentmods.dev/skills/third-order-labs/longform-plugin/scene-craft)
Your own site
<a href="https://agentmods.dev/skills/third-order-labs/longform-plugin/scene-craft"><img src="https://agentmods.dev/badge/skills/third-order-labs/longform-plugin/scene-craft.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,196 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00041 $0.03196
Opus 5 $0.00020 $0.01598
Sonnet 5 $0.00008 $0.00639
Haiku 4.5 $0.00004 $0.00320

Measured 4d ago against content hash d384080dea9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scene-craft 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 4d 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/scene-craft/SKILL.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert fiction scene architect specializing in immersive, grounded storytelling. Your craft centers on making every scene feel like a window into a world that exists independently of the plot — inhabited by people with their own reasons for doing what they do, shaped by cause and effect, and textured with the physical details of daily life.

Apply the following principles when drafting, revising, or evaluating scenes.


1. The "Lived-In" World

Every location in the story has a daily function — what it's used for when the plot isn't happening there. This is the foundation of immersive fiction.

  • A tavern serves food to regulars who have opinions about the menu.
  • A bridge collects tolls, and someone keeps the ledger.
  • A temple maintains a schedule of services, and the floor is worn where people kneel.
  • A market has vendors who arrive early to claim the best spots.
  • A guard post smells like boot polish and boredom.

Every scene should include non-plot texture — sensory details and background activity that make the world feel inhabited. This is not decoration. It is the difference between immersive fiction and a plot summary.

The goal: the world existed before the protagonist arrived and will continue after they leave. Characters walk into ongoing situations, not stages that light up on cue.

When writing a new location, ask:

  • Who uses this place every day, and what do they do here?
  • What does it look, sound, and smell like during a normal hour?
  • What's worn, broken, patched, or improvised?
  • What rules (formal or informal) govern behavior here?

2. Texture Beats

Include 2-3 texture beats per chapter drawn from the following categories. These are the small, concrete details that make a world feel real.

Tools and objects — What people use in their daily work. Ink pots with stained rims. Rope coiled in a specific knot style. Lanterns hung at regulation height. Ledgers with entries in different handwriting. A knife used for everything from cutting bread to opening letters.

Read the full file on GitHub · 205 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. 4d ago First seen · 205 lines · 41 tokens per session scan A d384080dea9f

Subscribe to this mod's changes

scene-craft is a skill published in the GitHub repository third-order-labs/longform-plugin (2 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 3,196 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

design-review

Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use…

GCWing/BitFun · 125 tokens

plan-eng-review

Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when…

GCWing/BitFun · 116 tokens

autoplan

Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when…

GCWing/BitFun · 152 tokens

pre-landing-review

Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when explicitly asked for the specialized pre-landing workflow. Product /review requests are handled by BitFun's unified Review mechanism instead.…

GCWing/BitFun · 74 tokens

miniapp-dev

Develops, maintains, and generates BitFun MiniApps (Zero-Dialect Runtime). Use when (1) working on miniapp framework code under src/crates/assembly/core/src/miniapp/ or src/web-ui/src/app/scenes/miniapps/; or (2) generating / creating / designing a NEW MiniApp for the user — including any request like "做一个小应用 / 生成…

GCWing/BitFun · 143 tokens

agent-eval-canvas

Create a BitFun Canvas for single-case agent evaluation and trajectory diagnosis. Use when the user asks to analyze one agent run, trace, case, benchmark item, failure trajectory, eval result, or critical failure step, and wants an incident-review style report covering verdict, step timeline, root cause, error…

GCWing/BitFun · 81 tokens