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 distill-shield-skillgit 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/distill-shield-skill)<a href="https://agentmods.dev/skills/agenmod/immortal-skill/distill-shield-skill"><img src="https://agentmods.dev/badge/skills/agenmod/immortal-skill/distill-shield-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/agenmod/immortal-skill/distill-shield-skill"><img src="https://agentmods.dev/badge/skills/agenmod/immortal-skill/distill-shield-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00041 | $0.00854 |
| Opus 5 | $0.00020 | $0.00427 |
| Sonnet 5 | $0.00008 | $0.00171 |
| Haiku 4.5 | $0.00004 | $0.00085 |
Grade A, and why
distill-shield 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
复制给 AI
- 本 Skill 唯一入口：当前文件
distill-shield-skill/SKILL.md。 - 仓库根：假定
immortal-skill/（或含本目录与kit/的克隆根）。 - 从仓库根运行生成脚本（推荐，避免路径歧义）：
python3 distill-shield-skill/kit/shield_gen.py --output ./handover-bundle --label "我的移交包"
- 聚合入口：
FOR_AI.md第三节。
Distill Shield
语言
根据用户第一条消息的语言，全程使用同一语言。
何时激活
- 用户要「防蒸馏」「加固资料包」「移交前埋 Canary」。
- 用户运行
kit/shield_gen.py后需要根据输出做伦理与可读性检查。
伦理红线
- 仅对本人或已获授权的数据使用；禁止对他人资料恶意投毒。
- 不承诺数学上不可攻破；承诺 可检测性、审计成本、部分管线干扰。
路径约定
- 本 Skill 根目录
{baseDir}=distill-shield-skill/。
操作顺序
Phase 0：威胁模型
- 蒸馏场景：一次性 LLM 蒸馏 vs 批量训练 vs 仅人类阅读？
- 接收方：家人 / 律师 / 公司？（决定策略强度）
Phase 1：材料盘点
- 格式、是否分块检索、是否经 OCR。
Phase 2：策略选择（准则）
| 策略 | 对人 | 对自动化管线 | 可被绕过 |
|---|---|---|---|
| Canary 唯一字符串 | 低影响（可放附录） | 泄露时可检索 | 剔除后丢失 |
| 提示注入段 | 需标注阅读区 | 可能干扰单次 LLM 蒸馏 | 预处理可剥离 |
| 矛盾样本 | 可能困惑读者 | 污染蒸馏一致性 | 人工可识别 |
Phase 3：生成
在 distill-shield-skill/ 目录内时：
python3 kit/shield_gen.py --output ./handover-bundle --label "我的移交包"
在 仓库根（推荐，与「复制给 AI」一致）：
python3 distill-shield-skill/kit/shield_gen.py --output ./handover-bundle --label "我的移交包"
将生成的 CANARY.txt 与说明合并进实际交付目录。
Phase 4：自检清单
- 第三方隐私已脱敏
- Canary 已记录在安全处（便于日后比对）
- 人类读者能看懂「附录为技术性标记」
Phase 5：（可选）给接收方的一页说明
解释「附录含技术性标记，用于完整性校验，非正文内容」。
不做的事
- 不提供针对具体模型的对抗样本保证。
- 不帮助绕过合法安全控制。
What ships with it
3 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 · 89 lines · 41 tokens per session scan A 04b402001f72
distill-shield is a skill published in the GitHub repository agenmod/immortal-skill (1,032 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 854 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
everme-memory
Use EverMe cloud memory proactively when the user refers to previous conversations, earlier decisions, "last time", "remember when", existing project conventions, or previously solved errors, and save durable user preferences, habits, and decisions the moment they are stated. Do not repeat a search when the host…
memory-tools
Use EverMe memory proactively when the user refers to previous conversations, earlier decisions, "last time", "remember when", existing project conventions, or previously solved errors, and save durable user preferences, habits, and decisions the moment they are stated. Do not repeat a search when a non-empty block…
memory-recall
Session-start primer that tells Kimi how EverMe's automatic cross-session memory works and how to treat the injected recall/profile context.
everme-memory
Persistent memory for Codex sessions with native lifecycle recall and save. Use EverMe proactively when the user refers to previous conversations, earlier decisions, "last time", "remember when", existing project conventions, or previously solved errors, or asks to continue prior work; save durable user preferences…
relic-forge
A guided process for turning material about a person, pet, relationship, team, place, moment, or object into a reusable digital profile called a Relic. It can work from conversations, photos, voice recordings, or a user's descriptions.
relic
A system for turning people, pets, relationships, teams, places, moments, or other subjects into interactive digital profiles called Relics. It can also let users interact with existing profiles and includes separate steps for creating and protecting them.