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 Flamesnake/talespindle --skill skillgit clone --depth 1 https://github.com/Flamesnake/talespindleWrote 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/flamesnake/talespindle/skill)<a href="https://agentmods.dev/skills/flamesnake/talespindle/skill"><img src="https://agentmods.dev/badge/skills/flamesnake/talespindle/skill/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/flamesnake/talespindle/skill"><img src="https://agentmods.dev/badge/skills/flamesnake/talespindle/skill.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 | $0.00082 | $0.06044 |
| Opus 5.5 | $0.00033 | $0.02418 |
| Sonnet 5.5 | $0.00016 | $0.01209 |
| Haiku 4.5 | $0.00008 | $0.00604 |
Grade B, and why
talespindle-author scanned grade B with 1 finding 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 1mo 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
3. 检查客户端 MCP 配置是否注册 `talespindle`，命令指向该工作区的绝对路径 `dist/cli.js mcp`。仓库根目录 `.mcp.json` 不是通用标准，也不能证明 Codex 已注册服务器。Codex 默认读取 `~/.codex/config.toml`，可信项目可读取 `.codex/config.toml`；可用 `codex mcp add talespindle -- node <绝对路径>/di How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TaleSpindle · Agent 互动叙事创作指南
通过 MCP 服务器 talespindle 用工具构建文字冒险游戏，最终交付一个自包含单文件 HTML（双击即玩、可发任何人、零依赖）。剧情是纯 JSON 数据，无需写代码。
前置条件：AI 客户端已连接 talespindle MCP 服务器（工具名以 story_ 开头）。旧配置中的服务器键名 ai-text-engine 仍可继续使用。
开工前检查与 MCP 故障处理
先确认当前能力列表中确实存在 story_new、story_validate、story_export 等 story_ 工具。Skill 可见不代表 MCP 已连接；不要尝试调用名称相近的其他服务器。
如果工具不可用，并且当前工作区是 TaleSpindle 源码仓库：
- 运行
npm install（仅在依赖缺失时）与npm run build，再运行node dist/cli.js doctor，确认 MCP、预构建运行时、Skill 和作品目录均为 OK。 - 运行
node scripts/verify-mcp.mjs；只有输出VERIFY OK才说明服务器本身可启动。 - 检查客户端 MCP 配置是否注册
talespindle，命令指向该工作区的绝对路径dist/cli.js mcp。仓库根目录.mcp.json不是通用标准，也不能证明 Codex 已注册服务器。Codex 默认读取~/.codex/config.toml，可信项目可读取.codex/config.toml；可用codex mcp add talespindle -- node <绝对路径>/dist/cli.js mcp注册，或在设置的 MCP servers 中添加 STDIO 服务器。 - 新增或修改配置后重启/刷新 AI 客户端会话，再检查
story_工具。
仍不可用时，向用户说明阻塞并停止创作。不要直接导入 dist/mcp/handlers.js 代替 MCP 创作：这会绕过 transport 的输入边界，也无法证明用户实际配置可用。
作品目录由 TALESPINDLE_HOME 控制并位于其 projects/ 子目录；旧变量 AI_TEXT_ENGINE_HOME 仍兼容。源码仓库默认使用仓库内 projects/。不要把作品写入 Skill 目录、node_modules 或临时脚本。正式 npm 包名为 @marianaj/talespindle。
工具速览
| 工具 | 用途 |
|---|---|
story_new |
创建项目（自动生成 start + 示例结局骨架） |
story_get |
读取完整剧情 JSON |
story_get_node |
读取单个节点及其入边，局部修稿优先使用 |
story_review_transitions |
分页审查“末段 → 选项 → response → 首段” |
story_patch_choice |
只修改一个选项，并用旧值断言防止误改 |
story_upsert_node |
创建/覆盖节点（结局自动登记到结局表） |
story_delete_node |
删除节点（被引用时需 force: true） |
story_delete_ending |
删除结局定义 |
story_upsert_achievement / story_delete_achievement |
管理成就 |
story_upsert_document / story_delete_document |
管理线索/文档（规则守则/便条/信件） |
story_upsert_evidence / story_delete_evidence |
管理可用于推理的证据 |
story_upsert_deduction / story_delete_deduction |
管理证据组合推论 |
story_upsert_character / story_delete_character |
管理人物、关系维度与秘密 |
story_upsert_puzzle / story_delete_puzzle |
管理密码谜题、渐进提示和成功效果 |
story_set_meta |
主题 / HUD / 副标题 / 作者 / 初始声景 / 拟态网站身份 |
story_set_presentation |
用一组短枚举设置界面外壳、字体、密度、形状与选项风格 |
story_validate |
校验 + 路径探索模拟；修订时用 compact:true 省略长见证动作 |
story_evaluate |
作品体验评估；支持紧凑输出，不打总分 |
story_walk |
结局见证与覆盖诊断；最终重放前再请求完整动作 |
story_graph |
mermaid 分支图 |
story_export |
导出单文件 HTML（校验不过会拒绝） |
story_list / story_delete_project |
项目管理 |
story_observability / story_observability_reset |
查看 / 清零本地工具成本摘要 |
What ships with it
6 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.
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.
- 1mo ago First seen · 195 lines · 82 tokens per session scan B e9c8d86627cc
talespindle-author is a skill published in the GitHub repository Flamesnake/talespindle (0 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 6,044 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.
threejs-animation
Three.js animation - keyframe animation, skeletal animation, morph targets, animation mixing. Use when animating objects, playing GLTF animations, creating procedural motion, or blending animations.
threejs-fundamentals
Three.js scene setup, cameras, renderer, Object3D hierarchy, coordinate systems. Use when setting up 3D scenes, creating cameras, configuring renderers, managing object hierarchies, or working with transforms.
threejs-geometry
Three.js geometry creation - built-in shapes, BufferGeometry, custom geometry, instancing. Use when creating 3D shapes, working with vertices, building custom meshes, or optimizing with instanced rendering.
threejs-world-generation
Build deterministic, editable, free-viewpoint Three.js worlds from text or structured briefs. Use for cinematic 3D terrain, semantic regions, procedural biomes, explicit landmarks, environmental scattering, camera fly-throughs, world diagnostics, or requests for a real 3D environment rather than generated 2D footage.…
3d-asset-generation
Generate, reconstruct, inspect, and route production 3D assets for OpenMontage worlds using Atlas Cloud, fal.ai, licensed catalogs, and Blender.