mind-clone-build

mind-clone-build is a command for coding agents from mrgnfndr-dr/mind-clone. It costs 12 tokens per session (286 once invoked), scanned A, original, MIT.

A workflow for building a conversational copy of an author’s thinking style from that author’s public writing and other content.

In plain words
What is it for?
Creating or updating a clone under a specified folder, optionally preserving more book text, and producing a methodology guide when the author teaches one.
Why use it?
It organizes discovery, source collection, modeling, and testing so the resulting clone can be checked against material it has not already seen. It also records gaps in the available sources.

Command

Install

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.

agentmods
npx agentmods add commands/mrgnfndr-dr/mind-clone/mind-clone-build
Clone the repo
git clone --depth 1 https://github.com/mrgnfndr-dr/mind-clone

Wrote 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.

agentmods badge for mind-clone-build

README.md
[![agentmods](https://agentmods.dev/badge/commands/mrgnfndr-dr/mind-clone/mind-clone-build.svg)](https://agentmods.dev/commands/mrgnfndr-dr/mind-clone/mind-clone-build)
Your own site
<a href="https://agentmods.dev/commands/mrgnfndr-dr/mind-clone/mind-clone-build"><img src="https://agentmods.dev/badge/commands/mrgnfndr-dr/mind-clone/mind-clone-build.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 286 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00012 $0.00286
Opus 5 $0.00006 $0.00143
Sonnet 5 $0.00002 $0.00057
Haiku 4.5 $0.00001 $0.00029

Measured 5d ago against content hash d9f59ca42954, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

mind-clone-build 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 5d 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.

commands/mind-clone-build.md · 15 lines

What it actually says

Invoke the mind-clone skill in BUILD mode for this request.

Arguments: $ARGUMENTS

  • Treat $ARGUMENTS as the author to clone (plus optional flags: --archive-raw to additionally keep more book text — transcripts/article text are already saved by default; depth quick|standard|exhaustive).
  • Run the full pipeline in SKILL.md: discovery → source table (review gate) → harvest (extract-on-the-fly, with timestamps + deep-links) → cognitive model (lean — a thin index, retrieval does the heavy lifting) → playbook (if the author teaches a methodology) → faithfulness check (held-out smoke test) → finalize. Write everything under ./clones/<author-slug>/.
  • If a clone for this author already exists, ask whether to update/rebuild it or just talk to it (/mind-clone-ask) before overwriting.
  • Follow the language protocol (ask chat language on first use; artifacts in English) and the quality gates (no fabrication, report every coverage gap).
  • To talk to an existing clone instead, use /mind-clone-ask.
Changes

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.

  1. 5d ago First seen · 15 lines · 12 tokens per session scan A d9f59ca42954

Subscribe to this mod's changes

mind-clone-build is a command published in the GitHub repository mrgnfndr-dr/mind-clone (3 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 286 once invoked, about $0.0001 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.