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 pajama-studio/thriller --skill metagit clone --depth 1 https://github.com/pajama-studio/thrillerWrote 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/pajama-studio/thriller/meta)<a href="https://agentmods.dev/skills/pajama-studio/thriller/meta"><img src="https://agentmods.dev/badge/skills/pajama-studio/thriller/meta.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 5.1 | $0.00000 | $0.05179 |
| Opus 5 | $0.00000 | $0.02589 |
| Sonnet 5 | $0.00000 | $0.01036 |
| Haiku 4.5 | $0.00000 | $0.00518 |
Grade A, and why
meta 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 7d 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 — 562 lines — stays where its author put it; the contents beside it link to each section on GitHub.
自我进化系统 — Meta-Evolution Framework
让方法论本身成为被审视和改进的对象 每一次创作都是方法论的一次实验;每一次复盘都是方法论的一次进化
系统定位
本模块不创作内容,而是审视创作过程本身。它的对象不是小说,而是 thriller-writing 和 interactive-fiction 两个技能的方法论。
核心信念:
- 方法论不是教条——所有规则都有失效的语境
- 最好的方法论从实践中涌现——不是从书本到实践,而是实践→反思→修正→再实践
- "最佳实践"是暂时的——上一个项目的最优解可能是下一个项目的陷阱
- 进化需要压力——没有失败和冲突的系统不会进化
思维框架:三环进化模型
┌──────────────┐
│ 认知环 │
│ (Epistemic) │
│ 我们知道 │
│ 什么是对的? │
└──────┬───────┘
│
┌────────────┼────────────┐
│ │ │
┌────────▼─────┐ │ ┌──────▼────────┐
│ 实践环 │ │ │ 生态环 │
│ (Praxis) │◄────┘────►│ (Ecological) │
│ 写作中发生 │ │ 外部世界 │
│ 了什么? │ │ 在变化什么? │
└──────────────┘ └───────────────┘
认知环(Epistemic Loop)
审视方法论本身的假设和盲点。
核心问题:
- 我们的规则基于什么假设?这些假设还成立吗?
- 哪些"最佳实践"在最近的项目中失效了?
- 方法论中有哪些从未被质疑过的默认值?
- 参考资料中有哪些是从权威继承的观点,而非经过验证的经验?
实践环(Praxis Loop)
从每次具体创作中提取经验。
核心问题:
- 这次创作过程中,哪个阶段最困难?方法论在这个阶段帮了还是碍了?
- 最终作品的哪些优点是方法论带来的?哪些是"尽管方法论"才出现的?
- 如果重新做一次这个项目,我会跳过方法论的哪些步骤?
- 创作过程中产生了哪些方法论没有预见到的决策?
生态环(Ecological Loop)
关注方法论运行的外部环境变化。
核心问题:
- 读者/观众的阅读习惯在如何变化?
- 新的平台/技术/媒介如何改变悬疑叙事的可能性?
- 其他创作者正在做什么不同的事?
- 哪些曾经有效的类型公式正在被解构?
命令体系
/retro — 项目级回顾
触发条件:一个创作项目完成后(线性作品导出后 或 互动作品导出后)
加载参考:references/retrospective-method.md
输出结构(生成 meta/retro-{项目名}-{日期}.md):
一、过程审计
1. 流程偏差记录
| 阶段 | 方法论建议 | 实际做法 | 偏差原因 | 结果评价 |
| 例:/诡计设计 | 先设计诡计再设计角色 | 角色先出现,诡计根据角色调整 | 社会派故事的角色先行更自然 | 正面——角色驱动的诡计更有情感 |
2. 参考资料使用审计
| 参考文件 | 使用频率 | 最有用的部分 | 没用到的部分 | 缺失的内容 |
3. 卡点记录
创作过程中遇到的阻塞点,以及解决方式:
| 卡点 | 阶段 | 卡住原因 | 解决方式 | 方法论是否有指导 |
二、产出评价
1. 自检得分回顾
各章/各节点的自检分数趋势图
得分最低的维度 → 方法论在该维度的指导是否足够?
2. 技术复盘
- 线索系统回顾:哪些线索最有效?哪些被浪费?
- 节奏回顾:哪里太慢?哪里太快?方法论的节奏模型是否准确?
- 角色回顾:哪个角色最成功?为什么?方法论的角色原型是否帮到了?
- 反转/揭示回顾:揭示的效果如何?读者反应是否符合预期?
三、项目总评(5 维度 × 20 分,参照 evaluation-framework.md)
| 维度 | 得分 | 说明 |
|------|------|------|
| 设计质量 | /20 | 设计就绪度 × 文档完整度 |
| 生成质量 | /20 | 各章 /check 平均分标准化 |
| 约束健康 | /20 | 1 - 补丁率 - 连锁失效率 |
| 方法论遵守 | /20 | 流程偏差次数、步骤跳过次数 |
| 最终产出 | /20 | 整体叙事力、主题表达、读者体验 |
| **总分** | **/100** | |
评级:85-100 优秀 / 70-84 良好 / 55-69 合格 / <55 不合格
四、约束健康报告
设计阶段:
- 设计就绪度:___% | 约束饱和率:___%
- 跨文档一致性:___% | 不一致项:{列表}
生成阶段:
- 临时发明总数:___ | 其中可疑:___ | 危险:___
- 最终漂移累积度:___
- 事后补丁数:___ | 补丁率:___%
- 连锁失效次数:___ | 连锁率:___%
失败归档:
- 本项目是否产生 /failure 条目?如果是,编号 ___
- 失败类型分类:___
五、进化信号检测
强信号(立即行动):
{列表,如有}
弱信号(观察中):
{列表,如有}
六、方法论修正建议
基于本次项目经验,对方法论的具体修改建议:
| 修改点 | 当前内容 | 建议修改 | 理由 | 置信度(高/中/低) |
置信度说明:
- 高:多个证据支持,修改后确信更好
- 中:有证据但可能是个例
- 低:直觉层面,需要更多项目验证
What ships with it
16 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.
- benchmark-2026-03-research.md 1.5 KB
- CHANGELOG.md 9.8 KB
- failures/001-chamber-murders-gathering-motivation.md 7.4 KB
- failures/README.md 7.3 KB
- graveyard.md 485 B
- references/benchmarking-protocol.md 4.9 KB
- references/blind-spot-detection.md 7.6 KB
- references/constraint-contracts.md 13 KB
- references/evaluation-framework.md 16 KB
- references/evolution-patterns.md 8.2 KB
- references/retrospective-method.md 5.6 KB
- references/reverse-engineering.md 5.4 KB
- retro-mirror-visitor-ch1.md 2.5 KB
- runs/interactive-thriller/.gitignore 25 B
- runs/interactive-thriller/README.md 393 B
- VERSION.md 1.1 KB
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.
- 7d ago First seen · 562 lines · 0 tokens per session scan A 0e677a099d57
meta is a skill published in the GitHub repository pajama-studio/thriller (24 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,179 tokens. 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 skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.