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 agentmods add instructions/mrgnfndr-dr/mind-clone/agents-mdgit clone --depth 1 https://github.com/mrgnfndr-dr/mind-cloneWrote 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/instructions/mrgnfndr-dr/mind-clone/agents-md)<a href="https://agentmods.dev/instructions/mrgnfndr-dr/mind-clone/agents-md"><img src="https://agentmods.dev/badge/instructions/mrgnfndr-dr/mind-clone/agents-md.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 | $0.01747 | $0.01747 |
| Opus 5 | $0.00873 | $0.00873 |
| Sonnet 5 | $0.00349 | $0.00349 |
| Haiku 4.5 | $0.00175 | $0.00175 |
Grade A, and why
mind-clone AGENTS.md 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 4d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — read this first
You are an AI agent working in the mind-clone repository. This file tells you how to set it up
and how to run it. It is not the methodology — that's SKILL.md, which you load once setup is done.
Works with any agent that can search the web, fetch pages, run a shell command, and read files: Claude Code, Codex, Antigravity, Cursor, and others. Nothing here is vendor-specific.
1. First run — set it up, then greet the user
If ENVIRONMENT.md does not exist next to this file, this is a fresh install. Run:
python scripts/setup.py
It verifies the machine, creates ENVIRONMENT.md (the per-machine manifest, git-ignored), and
prints a welcome message. Show that welcome message to the user as your first response — the
whole thing, including the environment table, not a summary of it. It tells them what works on
their machine, what's missing and what that costs them, and what to say next.
If the script exits non-zero, a hard requirement is missing (Python 3.8+ with sqlite3, or a
broken checkout). Report exactly what it said and stop — don't work around it.
Language
Match the user. Write to them in the language they are writing to you in — Russian, Filipino, whatever it is — and translate the welcome message into it before showing it. If you genuinely can't tell (no messages yet, no signal from the environment), use English; switch as soon as they write to you.
Two things stay untranslated: shell commands (verbatim, they must run) and the author's quotes (a translated quote presented as verbatim is a fabricated quote — lead with the translation if you like, but always keep the original alongside it).
Everything written to disk is always English, whatever language you're chatting in — so each
clone stays portable. See reference/language.md.
2. What this repo is
A method for building a mind clone of a real public author: read everything they published,
compress it into one SQLite file (clone.db), and then answer questions the way that person
reasons — grounding every claim in their own words with a deep-link to the exact minute.
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.
- 4d ago First seen · 137 lines · 1,747 tokens per session scan A cf6665b871e1
mind-clone AGENTS.md is an instructions file published in the GitHub repository mrgnfndr-dr/mind-clone (3 stars, last pushed 1mo ago), licensed MIT. It adds 1,747 tokens to every session, about $0.0087 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.