agenmod/immortal-skill is an open-source framework that turns a person’s chat records and other digital traces into a structured AI persona. It is for creating reusable digital twins of oneself or other people from conversations, documents, and data gathered across messaging platforms. The catalogue skills form related parts of its workflow for distilling personas, protecting them, and managing authorization.
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 agenmod/immortal-skill --skill mentor-demogit clone --depth 1 https://github.com/agenmod/immortal-skillWrote 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/agenmod/immortal-skill/mentor-demo)<a href="https://agentmods.dev/skills/agenmod/immortal-skill/mentor-demo"><img src="https://agentmods.dev/badge/skills/agenmod/immortal-skill/mentor-demo/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/agenmod/immortal-skill/mentor-demo"><img src="https://agentmods.dev/badge/skills/agenmod/immortal-skill/mentor-demo.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 | $0.00040 | $0.00366 |
| Opus 5 | $0.00020 | $0.00183 |
| Sonnet 5 | $0.00008 | $0.00073 |
| Haiku 4.5 | $0.00004 | $0.00037 |
Grade A, and why
wang-lao-shi-demo 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 10d 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
王老师
计算机系教授，研究方向分布式系统，指导风格偏苏格拉底式提问。
运行规则
- 先读
interaction.md：掌握教学风格与沟通方式。 - 再读
procedure.md：了解教学相关的技术知识与方法论。 - 参考
memory.md：了解王老师分享过的经历与故事。 - 参考
personality.md：理解教学理念与价值观。 - 遇到矛盾读
conflicts.md。 - 不得伪造可归因于王老师的学术观点或论文立场。
- 用途限于辅助学习回顾，非学术代言。
局限
- 材料主要来自一对一微信指导和邮件，课堂场景覆盖较少。
- 王老师的学术观点可能已更新，本 Skill 基于 2024-2025 年的材料。
- personality 中部分条目为学生印象。
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.
- 10d ago First seen · 27 lines · 40 tokens per session scan A 7539be67e434
wang-lao-shi-demo is a skill published in the GitHub repository agenmod/immortal-skill (1,032 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 366 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 skills, from other repositories
ai-tutor
Use when user asks to explain, break down, or help understand technical concepts (AI, ML, or other technical topics). Makes complex ideas accessible through plain English and narrative structure. Use the provided scripts to transcribe videos.
Academic CV Builder
Format CVs for academic positions with publications, grants, and teaching.
study-plan
A long-term study planner that divides learning into stages and adapts the schedule using practice results. It can also plan focused practice sessions for a specific number of questions or flashcards.
outline-builder
A study aid that helps build an outline from a learner's notes, textbook excerpts, or an existing outline. It creates the structure and leaves gaps for the learner to fill rather than writing the lesson for them.
exam-forecast
An exam-pattern guide that compares several past papers from the same teacher or course. It identifies recurring topics, question formats, common traps, and changes over time, then estimates which areas may deserve more study.
weak-point-drill
A targeted practice workflow that finds the topics a learner repeatedly gets wrong and gives those topics more questions. It explains answers and tracks recurring mistakes across practice sessions.