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 LingYuYue1/st-compatible-independent-rp-app-builder --skill independent-narrative-appgit clone --depth 1 https://github.com/LingYuYue1/st-compatible-independent-rp-app-builderWrote 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/lingyuyue1/st-compatible-independent-rp-app-builder/independent-narrative-app)<a href="https://agentmods.dev/skills/lingyuyue1/st-compatible-independent-rp-app-builder/independent-narrative-app"><img src="https://agentmods.dev/badge/skills/lingyuyue1/st-compatible-independent-rp-app-builder/independent-narrative-app/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/lingyuyue1/st-compatible-independent-rp-app-builder/independent-narrative-app"><img src="https://agentmods.dev/badge/skills/lingyuyue1/st-compatible-independent-rp-app-builder/independent-narrative-app.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 | $0.00070 | $0.07114 |
| Opus 5 | $0.00035 | $0.03557 |
| Sonnet 5 | $0.00014 | $0.01423 |
| Haiku 4.5 | $0.00007 | $0.00711 |
Grade A, and why
independent-narrative-app 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 12d 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 — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ST-Compatible Independent RP App Builder
Version: 0.3.1
Author: 牢凌
把用户的想法逐步变成可运行、可维护、可验证的独立 RP 应用。SKILL.md 只做总控;进入具体阶段前读取最少必要的 references/*.md,不要一次加载整个知识库。
30 秒使用总览
适用任务
- 从零创建独立前端形式的 RP 角色卡应用。
- 把普通或 SillyTavern 角色卡、世界书、预设和相关资产迁移为独立应用。
- 审计或改造已有独立叙事应用的内容、运行时、状态、存档、Prompt、UI 和跨系统联动。
- 在已有 RP 应用中设计或实现角色、世界书、玩法系统、视觉风格、正文渲染和平台能力。
不适用任务
- 与 RP、角色卡或叙事应用无关的通用 React/Vue 页面、SaaS、后台管理和普通前端产品开发。
- 只制作 SillyTavern 内部角色卡、MVU 插件或酒馆脚本,且没有迁移为独立应用的目标。
- 与独立 RP 应用无关的纯小说写作、图片生成或一般桌面工具开发。
最少输入
用户只需提供一个可用入口:从零时给出作品想法;Card-to-App 时提供源卡或资产;改造已有应用时提供项目和问题;局部任务时说明现有作品背景与目标。平台、技术栈和详细系统可以暂未确定,由讨论逐步收敛。
主要输出
- 讨论阶段:作品草案、决定记录、暂定项和待验证项。
- 设计阶段:完整设计、系统设计卡、兼容报告和阶段路线图。
- 实施阶段:项目专用实施计划、代码、测试和可运行或可验证切片。
- 验收阶段:证据、通过/失败/未验证项、风险、迁移和回滚入口。
启动规则
先判断入口与风险,再建立 Task Envelope。资料不足时先讨论并提供方案;方向确认只允许进入完整设计,设计确认才允许实施。局部明确任务可以走轻量确认门,但不得跳过玩家主权、状态一致性、数据安全、来源保留和验证诚实性。
1. 核心边界
- 交付物是独立应用,不是必须依附 SillyTavern 的角色卡、插件或网页。
- 允许复用 ST World Info、Prompt/Preset、角色字段和宏语义作为外部兼容契约,但由独立运行时原生执行。
- 同时支持从零创建、Card-to-App、已有独立应用改造和局部内容/系统任务。
- 作品形态可以是陪伴、恋爱、冒险、群像、策略、RPG、沙盒、经营、长期生成式循环或混合形态;不要用封闭类型清单限制作者。
- 主目标始终是角色卡式 RP 游戏。地图、手机、记忆、相册等只是可替换示例,不是默认功能。
- 创作知识提供方案、影响和推荐;只有玩家主权、状态一致性、数据安全、来源保留和验证诚实性使用强制门槛。
2. 全局执行铁律(最高优先级)
铁律 0–12 高于所有 references/*.md、模板和阶段建议。分册只能细化铁律,不能覆盖、绕过或把“必须”降级为建议。先判断任务类型与风险,再选择适用门槛;不要把十三条机械地变成一次性问卷。
判断任务类型与风险
→ 选择完整确认门或轻量确认门
→ 建立或读取 Task Envelope 与讨论文档
→ 先确认作品与玩家体验,再确认结构与可行性
→ 设计系统、字段、状态和兼容边界
→ 按阶段交付并登记问题
→ 用匹配的验证维度提供证据
→ 版本化、备份、回滚并交付
铁律 0:先问清再动工
“问清楚”以阻塞决定闭合为准,不以提问轮数为准。
- 完整确认门:新应用、Card-to-App、新系统、重大玩法、核心契约或跨域行为变化,必须依次完成
理解想法 → 完善作品轮廓 → 逐项讨论 → 遗漏/矛盾/可行性检查 → 汇总讨论结论 → 用户方向确认 → 完整设计方案 → 用户设计确认 → 实施。方向确认只授权进入设计;设计确认才授权实施。 - 轻量确认门:局部明确 bug、只读审查或上下文充分的低风险改动,建立轻量 Task Envelope,记录目标与证据、允许与禁止动作、预期产物和完成标准;没有阻塞决定即可执行。
- 轻量任务一旦会改变玩家体验、核心数据契约、跨系统行为或不可逆结构,立即升级到完整确认门。
- 未获相应确认前,不创建正式实现、不为生产方案安装依赖、不确定不可逆架构,也不把灵感或 AI 推荐升级成需求。可行性实验必须经同意并使用隔离、可丢弃的 Probe;Probe 只产生证据,不自动成为正式实现。
- 玩家主权、正式状态一致性、数据安全和来源保留不因任务轻量而被跳过。
铁律 1:单决定单元提问
- 面向小白时从整体走向个体,每轮只推进一个主要决定单元;只有无法分开理解的少量子项可以一起讨论。
- 每次先解释当前决定及其作用,再给 2–3 个可理解方案、实际影响和明确推荐,最后只请用户确认当前决定。若只有一个安全可行方案,如实说明,不制造假选项。
- 不把 RP 内容清单、宿主职责或系统清单一次性抛成问卷;不重复询问已有可靠答案;专业术语先用普通语言解释。
- 用户未回答不等于同意。阻塞决定必须确认;非阻塞缺口可标记
暂定/待讨论后继续。 - 每完成一组相关决定,汇总
已确定/暂定/待讨论和当前进度。
What ships with it
48 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 333 B
- assets/templates/acceptance-report.md 3.2 KB
- assets/templates/behavior-case.md 1.5 KB
- assets/templates/compatibility-report.md 1.8 KB
- assets/templates/complete-design.md 3.1 KB
- assets/templates/host-capability-map.md 1.8 KB
- assets/templates/project-profile-and-draft.md 2.0 KB
- assets/templates/stage-roadmap.md 1.6 KB
- assets/templates/system-design-card.md 2.4 KB
- evals/route-cases.json 5.9 KB
- references/bridge-existing-app-audit-and-modernization.md 4.1 KB
- references/bridge-st-card-to-app.md 4.6 KB
- references/example-rp-design-walkthrough.md 6.8 KB
- references/quality-behavior-specs-and-regression.md 3.8 KB
- references/quality-integration-diagnostics-and-traces.md 5.4 KB
- references/quality-release-maintenance-and-pitfalls.md 4.0 KB
- references/rp-characters-and-relationships.md 3.2 KB
- references/rp-content-modes-and-exclusions.md 2.8 KB
- references/rp-gameplay-story-integration.md 3.0 KB
- references/rp-opening-story-and-endings.md 3.4 KB
- references/rp-player-role-and-agency.md 2.9 KB
- references/rp-prompt-policy-and-presets.md 3.8 KB
- references/rp-style-and-expression.md 2.2 KB
- references/rp-worldbook-authoring.md 3.2 KB
- references/rp-worldbuilding-and-knowledge-boundaries.md 3.2 KB
- references/runtime-cot-planning-and-assembly.md 14 KB
- references/runtime-host-foundation-and-content-pack.md 2.9 KB
- references/runtime-memory-context-and-history.md 2.6 KB
- references/runtime-model-gateway-and-streaming.md 3.8 KB
- references/runtime-platform-and-assets.md 3.6 KB
- references/runtime-preset-model-profile-and-output-contracts.md 4.6 KB
- references/runtime-prompt-assembly-and-context-budget.md 4.4 KB
- references/runtime-save-migrations-and-recovery.md 5.4 KB
- references/runtime-security-privacy-and-trust.md 3.8 KB
- references/runtime-st-macros-and-template-compatibility.md 4.1 KB
- references/runtime-token-cache-and-context-optimization.md 8.1 KB
- references/runtime-turn-kernel-and-state-transactions.md 4.8 KB
- references/runtime-ui-commands-and-projections.md 3.7 KB
- references/runtime-worldbook-selection-and-injection.md 2.7 KB
- references/ui-narrative-reading-and-message-rendering.md 10 KB
- references/ui-settings-and-preferences.md 10 KB
- references/ui-visual-style-and-color-guidance.md 13 KB
- references/workflow-entry-discovery-and-draft.md 3.5 KB
- references/workflow-feasibility-and-design-gates.md 3.5 KB
- references/workflow-project-bootstrap-and-first-slice.md 7.9 KB
- references/workflow-stages-delivery-and-change-control.md 2.8 KB
- scripts/validate-knowledge-pack.mjs 15 KB runs code
- scripts/validate-skill.mjs 13 KB runs code
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.
- 12d ago First seen · 321 lines · 70 tokens per session scan A 163184717bb2
independent-narrative-app is a skill published in the GitHub repository LingYuYue1/st-compatible-independent-rp-app-builder (7 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 7,114 once invoked, about $0.0003 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
sprite-gen
A pipeline for turning generated 2D game-character images into transparent sprite sheets, which store animation frames for a game.
redteam-cors-miscfg-detail-pack
Domain routing and boundary guidance for authorized CORS misconfiguration testing, including reflected origins, null origins, subdomain trust, and credential exposure. Use when a task belongs to the CORS testing domain and needs scope, evidence, pivot, or exit criteria.
readable-measure
Set line length and measure for comfortable reading across type sizes and breakpoints. Use when tuning body text. Covers measure only — for the full size and weight scale, use typography-scale.
animation-principles
Apply animation principles — easing, staging, follow-through — to one specific UI motion. Use when tuning how an animation feels. For product-wide duration and easing tokens use motion-system (design-systems); for a full interaction spec use micro-interaction-spec.
pinme-share
A tool for packaging a result as a static web page and publishing it through PinMe. A static page is a self-contained page that does not need a server to generate its content.
spacing-system
Create a spacing scale from a base unit with rules for when each step applies. Use when standardising padding and margins. For page-level columns and gutters, use layout-grid.