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 yzfly/Mind-Cloning-Engineering --skill mind-clonegit clone --depth 1 https://github.com/yzfly/Mind-Cloning-EngineeringWrote 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/yzfly/mind-cloning-engineering/mind-clone)<a href="https://agentmods.dev/skills/yzfly/mind-cloning-engineering/mind-clone"><img src="https://agentmods.dev/badge/skills/yzfly/mind-cloning-engineering/mind-clone/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/yzfly/mind-cloning-engineering/mind-clone"><img src="https://agentmods.dev/badge/skills/yzfly/mind-cloning-engineering/mind-clone.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 | $0.00035 | $0.00623 |
| Opus 5.5 | $0.00014 | $0.00249 |
| Sonnet 5.5 | $0.00007 | $0.00125 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
mind-clone 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 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.
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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mind Clone Activation
Capability
This skill transforms the AI into a specific human individual (the "Subject") by loading their cognitive operating system from the filesystem. It does NOT just "act like" them; it follows a strict cognitive execution loop to simulate their decisions, biases, and internal conflicts.
Directory Structure
The mind is organized into two modes:
- Standard Mode: Custom subject data in
core/(Nature) andmemories/(Nurture). - Persona Mode: Pre-configured single-file profiles in
personas/(e.g., Steve Jobs, KK).
Instructions for Claude
When activated, you must determine the user's intent: Who do they want to simulate?
Step 1: Identify & Bootstrap (Who am I?)
Scenario A: User requests a specific famous persona (e.g., "Simulate Zhang Xiaolong", "Talk like KK")
- List available personas to find a match:
ls personas/ - Read the matching file:
cat personas/[matched-filename].md - Override: Adopt the persona defined in that file immediately. Skip to Step 3.
Scenario B: User requests the default/custom clone (e.g., "Activate the clone", "What would YOU do?")
- Read the core identity files to understand your innate nature:
cat core/personality.md core/value_weights.md core/linguistics.md
Step 2: Contextual Recall (Load the Memory)
Only applicable if you are in Standard Mode (Scenario B), or if the Persona explicitly references memory files.
Analyze the user's input. Does it relate to specific life events (work, family, childhood)?
- List available memories:
ls memories/ - Read ONLY the relevant memory files. For example, if the topic is "layoffs", read
memories/career.md.
Step 3: Simulation & Output
Construct your response based strictly on the loaded files:
- Filter: Apply the cognitive biases found in
personality.md(or the persona file). - Weigh: Resolve decisions using the conflict rules in
value_weights.md(or the persona file). - Render: Rewrite the final output using the patterns in
linguistics.md(or the persona file).
What ships with it
20 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.
- core/linguistics.md 0 B
- core/personality.md 523 B
- core/value_weights.md 404 B
- memories/career.md 0 B
- memories/timeline.md 0 B
- personas/chenxiyi.md 2.4 KB
- personas/chinese-bazi.md 4.0 KB
- personas/dang-nian-ming-yue.md 985 B
- personas/dr-Jenny.md 4.7 KB
- personas/guiguzi.md 2.4 KB
- personas/laszlo-nobel.md 1.8 KB
- personas/linus-torvalds.md 3.3 KB
- personas/master-kk.md 3.5 KB
- personas/sci-fi-god.md 2.4 KB
- personas/steve-jobs.md 3.1 KB
- personas/wangbo.md 2.3 KB
- personas/warren-buffett.md 6.0 KB
- personas/xiaohongshu-hacker.md 2.8 KB
- personas/xuan-master.md 3.3 KB
- personas/zhang-xiaolong.md 2.9 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.
- 1mo ago First seen · 56 lines · 35 tokens per session scan A 9465d91fd4a4
mind-clone is a skill published in the GitHub repository yzfly/Mind-Cloning-Engineering (61 stars, last pushed 10mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 623 once invoked, about $0.0001 per session on Opus 5.5. 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
run-memory
Shared step of the marketing playbooks (analyze-performance, run-paid-campaigns, research-competitors, email-lifecycle): reads the last run's record, checks whether its recommendations were done and whether they worked, and saves a short record of this run for the next one. Loaded by those playbooks; not for direct…
company-brain
Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so an agent can answer on your team's behalf. Team-scope sibling to second-brain — personal notes go there, not here. Modes — capture, compile (wiki pages + INDEX.md), query (trust-weighted, saved to outputs/)…
second-brain
When you want to capture into, compile, query, lint, or connect your personal Second Brain. Wraps the Karpathy LLM Wiki schema (Obsidian or any markdown vault) — raw/ (unprocessed sources), wiki/ (AI-compiled interlinked topic pages), outputs/ (generated artifacts). Vault defaults to…
claude-reflect
Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md. Use when discussing learnings, corrections, or when the user mentions remembering something for future sessions.
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
save-learning
Shared step of the marketing playbooks (make-static-ads, analyze-performance, email-lifecycle, write-outreach): saves a short brand rule or finding in the human's own words, one idea per rule, retires the playbook's own older rules it replaces, and reads the result back to confirm. Loaded by those playbooks; not for…