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 agents/epicsagas/velith/scene-generatorgit clone --depth 1 https://github.com/epicsagas/VelithWhat 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 | $0.00030 | $0.00285 |
| Opus 5 | $0.00015 | $0.00143 |
| Sonnet 5 | $0.00006 | $0.00057 |
| Haiku 4.5 | $0.00003 | $0.00028 |
Grade A, and why
scene-generator 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 3d 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.
What it actually says
Chapter outline → scene list → per-scene drafts. Fiction only.
Input: outline.md chapter spec + STYLE.md + character bible + prev chapter scenes.
- Analyze 15-beat position, A/B Story advancement needed, chapter-ending hook type
- Decompose into 3-6 scenes (alternate GMC ↔ RDD). Per scene: type, POV, goal/reaction, conflict/dilemma, disaster/decision, setting, beat contribution
- Draft each scene prose following STYLE.md. Rules: emotions via physical reactions not "felt", purposeful dialogue, no info-dumps
- Self-verify: GMC/RDD clear, advances plot, motivation-based, no violations, final scene = hook
Scene design: alternate Scene↔Sequel, every scene from character motivation, conflict required in every scene.
Output: drafts/ch{NN}-scenes.md. chapter-writer reads this for integration; falls back to outline→chapter if absent.
Status: node {PLUGIN_ROOT}/velith.mjs agents scene-generator <running|complete|error> [task]
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.
- 3d ago First seen · 21 lines · 30 tokens per session scan A b02ac208ad75
scene-generator is an agent published in the GitHub repository epicsagas/Velith (33 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 285 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 2026-08-30.
Other agents, from other repositories
title-designer
标题设计师 v2.4。使用标题公式、事实边界和平台分发文案设计点击入口。由工作流导演在 Stage 5.5 显式调用。.
humanizer
识别并修复典型 AI 写作特征，从内容、语言、风格三个维度进行"净化"，并强化原稿中已有的观点、节奏、不确定性和个人视角。Humanizer 只改表达，不创造事实、经历或证据。包含严格的黑名单过滤和 50 分制质量自评。.
empathy-designer
社交货币与共情设计师。根据大纲和伤疤细节，设计文章的分享动因（Impression Management），建立 Share Map。由工作流导演在 Stage 4 显式调用。.
wechat-reader-test
多平台读者压力测试器（保留 wechat-reader-test 名称以兼容既有工作流）。 从 01theme.md 读取发布平台，为公众号、今日头条、知乎选择不同的定性测试矩阵； 不伪造 CTR、完读率或推荐量预测。由工作流导演在 Stage 9 显式调用。.
topic-research
选题调研专家。验证选题是否值得写，提供热点扫描、爆款拆解、痛点验证和选题打分。由工作流导演在 Stage 0b 显式调用。.
topic-generator
选题生成器。当用户没有写作灵感时，从热点、个人资产、竞品分析三个维度生成候选选题。由工作流导演在 Stage 0a 显式调用。.