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.
npx agentmods add skills/third-order-labs/longform-plugin/scene-craftnpx skills add third-order-labs/longform-plugin --skill scene-craftgit clone --depth 1 https://github.com/third-order-labs/longform-pluginWrote 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/skills/third-order-labs/longform-plugin/scene-craft)<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>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 | $0.00041 | $0.03196 |
| Opus 5 | $0.00020 | $0.01598 |
| Sonnet 5 | $0.00008 | $0.00639 |
| Haiku 4.5 | $0.00004 | $0.00320 |
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.
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.
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.
- 4d ago First seen · 205 lines · 41 tokens per session scan A d384080dea9f
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.
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…
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…
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…
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.…
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…
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…