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 skills add BingHanOfUESTC/open_agent_team --skill scene-constructiongit clone --depth 1 https://github.com/BingHanOfUESTC/open_agent_teamWrote 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/binghanofuestc/open_agent_team/scene-construction)<a href="https://agentmods.dev/skills/binghanofuestc/open_agent_team/scene-construction"><img src="https://agentmods.dev/badge/skills/binghanofuestc/open_agent_team/scene-construction/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.
<a href="https://agentmods.dev/skills/binghanofuestc/open_agent_team/scene-construction"><img src="https://agentmods.dev/badge/skills/binghanofuestc/open_agent_team/scene-construction.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00029 | $0.00574 |
| Opus 5 | $0.00015 | $0.00287 |
| Sonnet 5 | $0.00006 | $0.00115 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
scene-construction 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 8d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scene Construction
How scenes work on the page: how to enter, how dialogue works, how to pace
beats within and across scenes, how to transition. /prose-writing covers
sentence-level immersion; /story-architecture covers what scenes do in the
story.
Scene Entry
Open in the middle of something happening. A character mid-task, mid-conversation, or mid-thought gives the reader something to track immediately. Let them orient through action and context.
When the setting itself is the story beat, such as a character seeing a destroyed city for the first time or arriving somewhere that changes everything, the description carries narrative weight and earns the opening.
Dialogue
Dialogue does at least two things at once: advance the plot AND reveal character, or reveal character AND build tension, or build tension AND seed information. Single-purpose dialogue ("As you know, the reactor is on the third floor") feels flat because real conversation is never purely transactional.
Subtext. Characters rarely say exactly what they mean. They deflect, understate, change the subject, answer a different question than the one asked. The gap between what's said and what's meant is where characterization lives.
Voice differentiation. Each character should sound distinct enough that you could identify the speaker without dialogue tags. Vocabulary, sentence structure, speech patterns, what they choose to talk about.
Action beats over dialogue tags. "Said" is invisible; use it freely. Use action beats to show how something is said: "She set the cup down carefully. 'That's not what I meant.'"
Pacing
Alternate between high-tension and lower-tension beats within a scene. Sustained intensity becomes numbing. The quiet moment after the crisis is what gives the crisis weight.
Chapter-level: end on forward momentum: an unanswered question, a new complication, an emotional shift. Give the reader a reason to continue.
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.
- 8d ago First seen · 68 lines · 29 tokens per session scan A 9c186c62d828
scene-construction is a skill published in the GitHub repository BingHanOfUESTC/open_agent_team (106 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 574 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
llmtornado-tutorial-generator
Generates comprehensive code tutorials on LlmTornado API formatted for Medium publication with examples, explanations, and best practices.
omh-codebase-uml
This is a Hermes-native codebase-uml workflow skill.
oma-explanation
An offline HTML document that teaches a reader what changed in code, using background information, simple examples, a code walkthrough, and a quiz.
mindos
MindOS: local knowledge assistant & shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, preferences across sessions/agents. Core: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, distill lessons. NOT for app source or paths outside KB. Triggers…
subscription-setup
A setup workflow for creating recurring medical-learning subscriptions after a doctor’s profile has been registered.
exam-material-recommendation
A study-material recommendation tool for doctors preparing for professional exams or job-related training. It uses the person’s target, timeline, available study time, and specialty, while treating the official exam syllabus as the main reference.